System, method, and device for medical image analysis, diagnosis, risk stratification, decision making and / or disease tracking

Abstract

To provide a system, a method, and a device for medical image analysis, diagnosis, risk stratification, decision making and / or disease tracking.SOLUTION: A system, a device, and a method are configured to analyze non-invasive medical images of a subject to automatically and / or dynamically identify one or more features, such as plaque and vessels, and / or derive one or more quantified plaque parameters, such as radiodensity, radiodensity composition, volume, radiodensity heterogeneity, geometry, location, and / or the like. The system, device, and method are further configured to generate one or more assessments of plaque-based diseases from raw medical images by using one or more of the identified features and / or quantified parameters.SELECTED DRAWING: Figure 2A

Description

Technical Field

[0004] , , ,

[0001] Cross - reference to related applications This application claims the benefit of U.S. Provisional Patent Application No. 62 / 958,032, filed on January 7, 2020, entitled Systems, Methods, and Devices for Cardiovascular Image Analysis, Diagnosis, Severity Classification, Decision Making, and / or Disease Tracking, and is incorporated herein by reference in its entirety. All applications for which foreign or domestic priority is identified in the Application Data Sheet filed herewith are incorporated herein by reference under 37 C.F.R. § 1.57.

[0002] This application relates to systems, methods, and devices for medical image analysis, diagnosis, severity classification, decision making, and / or disease tracking.

Background Art

[0003] Coronary heart disease affects more than 17.6 million Americans. Current trends in the treatment of cardiovascular health problems are almost doubling. First, physicians generally examine a patient's cardiovascular health at a macro - level by, for example, analyzing biochemistry or blood content or biomarkers to determine whether there are high levels of cholesterol components in the patient's bloodstream. In response to high levels of cholesterol, some physicians prescribe one or more drugs, such as statins, as part of a treatment plan to reduce what is recognized as high levels of cholesterol components in the patient's bloodstream. A second general trend in currently treating cardiovascular health problems is to use angiography to​​​​​​​​​​​​​​​​​​​​​​​​​​​ Helps doctors assess a patient's cardiovascular health by identifying major blockages in various arteries In response to the discovery of large blockages in various arteries, physicians sometimes This involves angioplasty, a procedure in which a balloon catheter is guided to the point where the blood vessel is narrowed. Once properly positioned, the balloon is inflated to remove the plaque or fat. They compress or flatten into the arterial wall and / or stretch and open the artery, allowing blood to pass through. In some cases, the balloon may: The stent is positioned within the vessel and expanded to compress the plaque and / or It is used to keep the arteries open and allow more blood to flow. 000 cardiac stent procedures are performed in the United States each year.

[0005] However, a recent $100 million federally funded study found that There is some doubt as to whether the current trends in treatment are the most effective treatment for all types of patients. A recent study included over 5,000 people from 320 regions in 37 countries. Stent and bypass surgery are used to treat patients with moderate to severe stable heart disease. More effective than combined lifestyle changes in patients with stable heart disease New evidence has emerged that this is unlikely. For some, it is common to see patients undergo invasive surgical procedures such as angioplasty and / or heart bypass. Instead, they are prescribed heart medications such as statins and follow certain lifestyle habits, such as regular exercise. This new treatment plan is being implemented in thousands of patients worldwide. An estimated 500,000 cardiac scans are performed annually in the United States. It is estimated that one in five cardiac procedures are performed in patients with stable heart disease. Of every 100,000 patients with stable heart disease, 25% (approximately 23,000) experience chest pain. Therefore, more than 20,000 patients per year undergo invasive The likelihood of forgoing surgical procedures or experiencing no complications as a result of such procedures could be.

[0006] Whether patients should forgo invasive surgical procedures and instead opt for drug treatment plans To determine this, it may be important to better understand the patient's cardiovascular disease. It would be advantageous to have a better understanding of a patient's arterial vascular health. Summary of the Invention

[0007] Various embodiments described herein are directed to medical image analysis, diagnosis, severity classification, decision making, and the like. and / or systems, methods, and devices for disease tracking.

[0008] In particular, in some embodiments, the systems, devices, and methods described herein a computer system configured to automatically and / or dynamically analyze medical images; Non-invasive medical imaging techniques, such as CT images, can be input into the system. to identify one or more coronary arteries and / or plaque therein. For example, in some embodiments, the system may include one or more mechanical Utilizing learning and / or artificial intelligence algorithms to automatically and / or dynamically and dynamically analyze one or more coronary arteries and / or plaque to identify, quantify, and In some embodiments, the system may be configured to: Furthermore, for example, using one or more artificial intelligence and / or machine learning algorithms and one or more coronary arteries and / or utilizes plaques to generate treatment plans, track disease progression, and / or evaluate patients In some embodiments, the device may be configured to provide a medical report on the characteristics of the device. The system may further include, for example, a graphical user interface for identifying, Quantification and / or classification of one or more coronary arteries and / or plaques Visualizations can be configured to be generated dynamically and / or automatically. In some embodiments, different medical imaging scanners and / or different scanners may be used. To calibrate the acquired medical images from the application parameters or environment, the system configured to utilize a normalization device comprising one or more compartments of a substance or substances. It is possible.

[0009] In some embodiments, for algorithm-based medical imaging analysis, and a normalization device configured to facilitate normalization of a medical image of a coronary artery region of a patient. The normalization device has width, length, and depth dimensions and has a proximal surface and a distal surface. a substrate, the proximal surface of which is adapted to be placed adjacent to a surface of a body part of a subject; a plurality of electrodes positioned within the substrate, each configured to hold a sample of a known substance; a first subset of the plurality of compartments, the first subset containing at least one sample of contrast material; A second subset of the compartments is used for algorithm-based medical imaging. maintain samples of material representative of the material to be analyzed by the chemistry analysis; The samples were calcium 1000HU, calcium 220HU, and calcium 150HU. , calcium 130HU, and low-attenuation material 30HU, and a third subset of the compartments holds at least one sample of the phantom material; and a plurality of compartments on the proximal surface of the substrate for adhering the normalization device to a body part of a patient. and an adhesive.

[0010] In some embodiments of the normalization device, a sample of material representative of the material to be analyzed Calcium 1000HU, calcium 220HU, calcium 150HU, calcium Some embodiments of the normalization device include: a material having a low attenuation of 130 HU; and a material having a low attenuation of 30 HU. In this study, at least one contrast agent was selected from iodine, Gad, Tantalum, and Tungsten. One or more of en, Gold, Bismuth, or Ytterbium At least one sample of the phantom material contains water, fat, calcium, uric acid, and air. Contains one or more of qi, iron, or blood.

[0011] In some embodiments of the normalization device, the substrate is a first layer having a plurality of compartments. a first layer, at least some of which are positioned in a first arrangement; a second layer positioned on which at least some of the plurality of compartments are positioned; and a second layer included in the second arrangement. In this case, at least one of the compartments is a self-sealing compartment into which the sample can be injected. The compartment is configured to be self-sealing so that it seals and contains the injected substance. do.

[0012] In some embodiments, the normalization device is used to perform algorithm-based medical imaging. Algorithm-based medical imaging by normalizing medical images for sizing analysis A computer-implemented method for improving the accuracy of imaging analysis is provided, the method comprising: First, medical images of the subject's coronary artery territory are obtained non-invasively by a computer system. and normalizing the device by accessing it and by a computer system non-invasively A second medical image of the subject's coronary artery area obtained by a computer and a normalization device are accessed. and a first medical image and a second medical image are captured by a capture unit of the first medical image. one or more first variable acquisition parameters associated with the second medical image different from the corresponding one or more second variable acquisition parameters associated with the capture. a first image capture technology used to capture the first medical image; , different from the second image capture technology used to capture the second medical image. Alternatively, the first contrast agent used during the capture of the first medical image may be a second contrast agent. at least one of the contrast agents being different from the second contrast agent used during the capture of the medical image; By accessing the normalized device and the computer system, including one identifying a first image parameter of the normalization device in the first medical image; Based in part on the first identified image parameters of the normalized device in the image for Al. Generate normalized first medical images for algorithm-based medical imaging analysis and a second medical image normalization device in the second medical image by the computer system. and identifying a second identified image parameter of the normalization device in the second medical image. Algorithm-based medical imaging analysis based in part on selected image parameters generating a normalized second medical image for the The system includes a computer processor and an electronic storage medium. Normalizing medical images for algorithm-based medical imaging analysis, In some embodiments of the method, algorithm-based medical imaging analysis includes artificial intelligence or machine learning imaging analysis algorithms, The learning imaging analysis algorithm is trained using the images contained in the normalized device. This is what was done.

[0013] In some embodiments, a non-invasive method for normalizing medical images is provided. Quantify and classify coronary plaques within a subject's coronary artery territory based on analysis of aggressive medical images. A computer-implemented method is provided, the method comprising: Access to normalized medical images and raw processed by computer systems A coronary artery identification algorithm configured to use medical images as input is used to identifying one or more coronary arteries in a normalized medical image of one; and The system is configured to utilize raw medical images as input. and using a determination algorithm to determine one or more of the features identified from the first normalized medical image. and a computer system for identifying one or more plaque regions within a coronary artery. One or more vascular morphological parameters and a first normalized medical image are obtained by The quantified plaque parameters of one or more identified plaque regions were analyzed. The set of quantified plaque parameters is used to determine the first positive a volume-to-surface area ratio or function of one or more plaque regions in the normalized medical image; Parameters and parameter sets, including heterogeneity index, geometry, and radiodensity determining a set of one or more of the determined sets of data by a computer system; Vascular morphological parameters and quantified plaque parameters of one or more plaque regions generating a weighted standard for a set of meters and The determined one or more vascular morphological parameters and the determined quantified profile are then Based at least in part on the weighted criteria generated for a set of Lark parameters and classifying one or more plaque regions in the first normalized medical image as stable plaques. or classifying the plaque as vulnerable.

[0014] Quantify and characterize coronary plaque within the subject's coronary artery territory based on non-invasive medical image analysis. In some embodiments of the computer-implemented method, one or more The volume-to-surface area ratio of multiple plaque regions indicates stable plaque. A computerized method for quantifying and classifying coronary plaque within a subject's coronary artery territory based on endoscopic analysis. In some embodiments of the method, one or more plaque areas that are below a predetermined threshold are The heterogeneity of the plaque indicates stable plaque. In some embodiments of a computer-implemented method for quantifying and classifying coronary plaque in a region The heterogeneity index of one or more plaque regions is calculated by The radiation density is determined by generating a spatial mapping of radiation density values ​​across the

[0015] Quantify and characterize coronary plaque within the subject's coronary artery territory based on non-invasive medical image analysis. In some embodiments of the computer-implemented method, the method comprises: based at least in part on the one or more plaque regions classified by the Subjects with regard to one or more of atherosclerosis, stenosis, or ischemia generating an assessment of the coronary artery areas of the subject based on non-invasive medical image analysis. In some embodiments of the computer-implemented method for quantifying and classifying coronary artery plaque in Medical imaging includes CT, X-ray, ultrasound, echocardiography, intravascular ultrasound (IVUS), and MR imaging. Imaging, Optical Coherence Tomography (OCT), Nuclear Medicine Imaging, Proton Emission Tomography PET, single photon emission computed tomography (SPECT), or near-field red obtained using imaging techniques, including one or more of: near-infrared spectroscopy (NIRS); Quantify coronary plaque within the subject's coronary artery territory based on non-invasive medical image analysis. In some embodiments of the computer-implemented method of classifying and classifying one or more vascular morphologies, The parameters include classification of arterial remodeling.

[0016] In some embodiments, a computer-implemented method for normalizing a medical image is used to A method for analyzing a T image and corresponding information is provided, the method comprising computer-executable instructions The patient's age and a set of computed tomography (CT) images of the coronary vessels of the patient subjects, vascular labels, and CT image segments containing information showing stenosis and plaque in coronary vessel segments. a first normalized medical image including arterial information associated with the coronary vessels; and storing information indicating the coronary artery identified in the CT image based on the CT image. Includes a three-dimensional (3D) representation of the coronary vessels depicting the vessels and segment labels; Generate the first panel containing the arterial tree without cardiac tissue between the branches of the arterial tree, and then Displaying in the interface and selecting coronary vessels in the arterial tree in the first panel receiving a first input indicating a first coronary vessel in response to the first input; At least one straightened multiplanar vessel Generate a second panel showing the (SMPR) image and display it in the user interface and a selected coronary vessel CT image generated using one of the set of selected coronary vessel CT images. The third panel, showing a cross-sectional image of the coronary vessels, is generated and displayed in the user interface. and wherein each of the positions along at least one SMPR image is a set of CT images. At least one SMPR image is obtained by correlating it with one of the CT images in the Selection of specific locations along the coronary vessels in the cross-sections of the relevant CT images is shown in the third panel. Generate and display a third panel based on a set of stored CT images. A fourth panel showing at least one anatomical planar image of a selected coronary vessel is generated based on the and displaying in a user interface, the method comprising: Executes computer-executable instructions stored on a non-transitory computer storage medium; or implemented by multiple computer hardware processors.

[0017] In some embodiments of the method for analyzing CT images and corresponding information, one or more The anatomical plane images are axial, coronal, and posterior plane images, respectively corresponding to the selected coronary vessels. Several methods for analyzing CT images and corresponding information are described. In an embodiment, the method further comprises: displaying at least one S receiving a second input indicating a first location along a selected coronary vessel in the MPR image; In response to a second input, generating a CT image associated with a first location of the selected coronary vessel. The cross-sectional image in the third panel shows the coronary vessels selected at the first position. Axial, coronal, and sagittal views of the selected coronary vessels are generated, and a fourth The method further includes displaying the CT image and corresponding information on a panel. In some embodiments, the method further comprises: and receiving a third input indicating a second location along the selected coronary vessel in one SMPR image. and in response to a third input, displaying a CT image associated with a second location of the selected coronary vessel. The image is generated and displayed in the cross-sectional image in the third panel, showing the selected coronary vessel at the second position. generating corresponding axial, coronal, and sagittal views of the selected coronary vessel; Further comprising displaying in a fourth panel.

[0018] In some embodiments of the method for analyzing CT images and corresponding information, the method comprises: Near each segment of the tree, the arterial information is used to indicate the name of the segment. Generates and displays a segment name label and the first segment displayed in the user interface. a list of vessel segment names in response to an input selection of a vessel segment name label; Generates a panel showing the current names of vessel segments and displays it in the user interface. , in response to an input selection of a second segment name label in the list, The first segment name label of the displayed arterial tree in the interface is compared with the second segment name label. Several methods for analyzing CT images and corresponding information are also available. In some embodiments, the method further comprises generating an animation comprising a non-patient-specific graphical representation of the coronary artery tree. Generate an arterial tree of the pose, display it in the user interface, and animate it. In response to the selection of a vessel segment in the vein tree, an image of the selected vessel segment is displayed in SM. The vessel segments displayed in the user interface in the PR image and in the SMPR image Once the location is selected, the stenosis or Generate a panel displaying plaque-related information and display it in the user interface. Some embodiments of the method for analyzing CT images and corresponding information In one embodiment, the method further includes generating and displaying a toolbar in the user interface. The toolbar contains the Lumen Wall Tool, Snap-to Vessel Wall Tool, and Snap-to Vessel Wall Tool. Lumen wall tools, vessel wall tools, segment tools, stenosis tools, plaque overlay tools I-Tool, Snap-To-Centerline Tool, Chronic Total Occlusion Tool, Stent Tool, Use at least one of the following tools: Exclusion Tool, Tracker Tool, or Distance Measurement Tool. include.

[0019] For purposes of this Summary, certain aspects, advantages and novel features of the invention are described herein. Not all such advantages may be achieved in accordance with any particular embodiment of the present invention. It should be understood that this need not be achieved by, for example, achieve one or more of the advantages taught herein, but embodied in a manner that does not necessarily achieve other advantages that may be taught or suggested in the Those skilled in the art will recognize that the present invention may be implemented in various ways.

[0020] All of these embodiments are intended to be within the scope of the invention disclosed herein. These and other embodiments will become readily apparent to those skilled in the art from the following detailed description taken in conjunction with the accompanying drawings. As will be apparent, the present invention is not limited to any particular disclosed embodiment.

[0021] The disclosed aspects are incorporated into and constitute a part of this specification and are not intended to be limiting unless otherwise specified. are provided to illustrate and provide a further understanding of the embodiments, but do not limit the disclosed aspects. The following description is taken in conjunction with the accompanying drawings, in which like numerals refer to like elements throughout the drawings unless otherwise specified. Represents an element of. [Brief explanation of the drawings]

[0022] [Figure 1] 1 is a flowchart illustrating an overview of an example embodiment of a method for medical image analysis, visualization, risk assessment, disease tracking, treatment generation, and / or patient report generation.

[0023] [Figure 2A] 1 is a flowchart illustrating an overview of an example embodiment of a method for analyzing and classifying plaque from medical images.

[0024] [Figure 2B] 1 is a flowchart illustrating an overview of an example embodiment of a method for determining non-calcified plaque from non-contrast CT images.

[0025] [Figure 3A] 1 is a flow chart illustrating an overview of an example embodiment of a method for risk assessment based on medical image analysis.

[0026] [Figure 3B] 1 is a flow chart illustrating an overview of an example embodiment of a method for quantifying atherosclerosis based on medical image analysis.

[0027] [Figure 3C] 1 is a flowchart illustrating an overview of an example embodiment of a method for quantifying stenosis and generating a CAD-RADS score based on medical image analysis.

[0028] [Figure 3D] 1 is a flowchart illustrating an overview of an example embodiment of a method for disease tracking based on medical image analysis.

[0029] [Figure 3E] 1 is a flowchart illustrating an overview of an example embodiment of a method for determining the cause of a change in calcium score based on medical image analysis.

[0030] [Figure 4A] 1 is a flow chart illustrating an overview of an example embodiment of a method for prognosing a cardiovascular event based on medical image analysis.

[0031] [Figure 4B]1 is a flowchart illustrating an overview of an example embodiment of a method for determining patient-specific stent parameters based on medical image analysis.

[0032] [Figure 4B] 1 is a flowchart illustrating an overview of an example embodiment of a method for determining patient-specific stent parameters based on medical image analysis.

[0033] [Figure 5A] 1 is a flowchart illustrating an overview of an example embodiment of a method for generating a medical report regarding patient characteristics based on medical image analysis.

[0034] [Figures 5B-5I] FIG. 1 illustrates an example embodiment of a medical report regarding patient characteristics generated based on medical image analysis.

[0035] [Figure 6A] FIG. 10 shows an example of a user interface that can be generated and displayed on the system and has multiple panels (images) that can show various corresponding views of a patient's arteries.

[0036] [Figure 6B] FIG. 10 illustrates an example of a user interface that can be generated and displayed on the system and has multiple panels that can show various corresponding views of a patient's arteries.

[0037] [Figures 6C-6E] FIG. 10 shows certain details of the multiplanar reconstruction (MPR) vascular image in the second panel and certain functionality associated with this image.

[0038] [Figure 6F] FIG. 1 illustrates an example of a three-dimensional (3D) rendering of a coronary artery tree that allows a user to view the vessels and modify the vessel levels.

[0039] [Figure 6G] FIG. 10 shows an example of a user interface panel that provides shortcut commands that a user may use while analyzing information in the user interface for axial, sagittal, and coronal views of the coronary arteries.

[0040] [Figure 6H] Figure 1 shows an example of a user interface panel for viewing DICOM images in three anatomical planes: axial, coronal, and sagittal.

[0041] [Figure 6I] FIG. 1 shows an example of a user interface panel showing a cross-sectional image of a vessel with a graphical overlay of extracted features of the vessel.

[0042] [Figure 6J] FIG. 10 illustrates an example of a toolbar that allows a user to select different vessels for inspection and analysis.

[0043] [Figure 6K] Figure 6J shows an example of the series selection panel of the user interface in an expanded view of the toolbar shown in Figure 6J, which allows the user to expand the menu and view all of the series (sets of images) available for a particular patient's examination and analysis.

[0044] [Figure 6L] FIG. 10 shows an example of a selection panel that may be displayed on a user interface that may be used to select vessel segments for analysis.

[0045] [Figure 6M] FIG. 10 shows an example of a panel that can be displayed on the user interface to add new vessels onto the image.

[0046] [Figure 6N]Figure 10 shows an example of two panels that can be displayed on the user interface to name or rename vessels in a 3-D arterial tree view.

[0047] [Figure 7A] FIG. 10 illustrates an example of an editing toolbar that allows a user to modify and improve the accuracy of findings resulting from CT scans processed using machine learning algorithms and then by an analyst.

[0048] [Figure 7B-7C] Figure 10 shows an example of the specific functionality of the Tracker tool.

[0049] [Figure 7D-7E] FIG. 10 illustrates the specific functionality of the vessel and lumen wall tools used to modify the lumen and vessel wall contours.

[0050] [Figure 7F] Figure 10 shows the Lumen Snap tool button (left) and the Vascular Snap tool button (right) on the user interface, which can be used to launch the tool.

[0051] [Figure 7G] FIG. 10 shows an example of a panel that can be displayed on the user interface while using the Lumen Snap tool of the Vascular Snap tool.

[0052] [Figure 7H] Figure 10 shows an example of a user interface panel that can be displayed while using the segment tool, allowing for marking the boundaries between individual coronary artery segments on the MPR.

[0053] [Figure 7I] FIG. 10 shows an example of a user interface panel that allows different names to be selected for the segments.

[0054] [Figure 7J] FIG. 10 shows an example of a user interface panel that can be displayed while using the stenosis tool, allowing the user to indicate a marker that marks the extent of stenosis in a blood vessel.

[0055] [Figure 7K] FIG. 10 shows an example of a stenosis button on the user interface that can be used to drop five evenly spaced stenosis markers.

[0056] [Figure 7L] FIG. 10 shows an example of a stenosis button on the user interface that can be used to drop stenosis markers based on the user-edited lumen and vessel wall contours.

[0057] [Figure 7M] FIG. 10 shows stenosis markers on a segment in a curved multiplanar angiogram (CMPR).

[0058] [Figure 7N] FIG. 10 shows an example of a user interface panel that can be displayed while using the plaque overlay tool.

[0059] [Figures 7O-7P] Figure 1 shows the buttons on the user interface that can be selected for plaque threshold.

[0060] [Figure 7Q] FIG. 10 illustrates a panel of a user interface that can receive user input to adjust plaque threshold levels for low-density plaque, non-calcified plaque, and calcified plaque.

[0061] [Figure 7R]FIG. 10 is a cross-sectional view of a blood vessel showing the extent of plaque displayed in the user interface according to the plaque threshold.

[0062] [Figure 7S] FIG. 13 shows a panel that can be displayed showing the plaque threshold in a vessel statistics panel that contains information about the vessel being viewed.

[0063] [Figure 7T] FIG. 10 shows a panel showing a cross-sectional image of a blood vessel that can be displayed using a centerline tool that allows adjustment of the center of the lumen.

[0064] [Figure 7U-7W] 7A and 7B show an example of a panel showing other images of a blood vessel that can be displayed when using the centerline tool; FIG. 7U shows an example of an image that can be displayed when extending the centerline of a blood vessel; FIG. 7V shows an example of an image that can be displayed when saving or deleting centerline edits; and FIG. 7W shows an example of a CMPR image that can be displayed when editing a blood vessel centerline.

[0065] [Figure 7X] FIG. 10 shows an example of a panel that can be displayed while using a chronic total occlusion (CTO) tool used to show a portion of an artery that has 100% stenosis and no detectable blood flow.

[0066] [Figure 7Y] FIG. 10 shows an example of a panel that can be displayed while using the stent tool, allowing the user to mark the extent of the stent within the vessel.

[0067] [Figure 7Z-7AA] FIG. 10 shows an example of a panel that can be displayed while using an exclusion tool, which allows excluding portions of a vessel from analysis, for example due to image aberrations.

[0068] [Figures 7AB-7AC] 7A-7C show examples of additional panels that can be displayed while using the Exclusions tool: FIG. 7AB shows a panel that can be used to add a new exclusion; and FIG. 7AC shows a panel that can be used to add a reason for the exclusion.

[0069] [Figure 7AD-7AG] 7A-7C are diagrams showing examples of panels that can be displayed while using a distance tool that can be used to measure the distance between two points on an image, for example, FIG. 7AD shows a distance tool used to measure distance on an SMPR image, FIG. 7AE shows a distance tool used to measure distance on a CMPR image, FIG. 7AF shows a distance tool used to measure distance on a cross-sectional view of a blood vessel, and FIG. 7AG shows a distance tool used to measure distance on an axial image.

[0070] [Figure 7AH] FIG. 10 shows the "Vascular Statistics" portion (button) of the panel which can be selected to display the Vascular Statistics tab.

[0071] [Figure 7AI] FIG. 13 illustrates the Vascular Statistics tab.

[0072] [Figure 7AJ] Figure 10 illustrates functionality in the vascular statistics tab that allows the user to click through the details of multiple lesions.

[0073] [Figure 7AK] FIG. 10 further illustrates an example of a vessel panel that the user can use to toggle between vessels.

[0074] [Figure 8A] Figure 1 shows an example of a user interface panel showing stenosis, atherosclerosis, and CAD-RADS results of analysis.

[0075] [Figure 8B] FIG. 10 illustrates an example of a portion of a panel displayed on a user interface that allows selection of a region or combination of regions (e.g., left aorta (LM), left anterior descending artery (LAD), left circumflex artery (LCx), right coronary artery (RCA)), according to various embodiments.

[0076] [Figure 8C] FIG. 10 shows an example of a panel that can be displayed on the user interface, showing an animated representation of a coronary artery tree ("Animated Arterial Tree").

[0077] [Figure 8D] Figure 10 shows an example of a panel that can be displayed on the user interface, showing region selection using an animated arterial tree.

[0078] [Figure 8E] FIG. 10 shows an example panel that can be displayed on the user interface showing a summary by region.

[0079] [Figure 8F] Figure 1 shows an example panel that can be displayed on the user interface showing the SMPR image of a selected vessel, and the corresponding statistics of the selected vessel.

[0080] [Figure 8G] FIG. 10 shows an example of a portion of a panel that can be displayed in a user interface showing the presence of a stent, displayed at the segment level.

[0081] [Figure 8H] FIG. 10 shows an example of a portion of a panel that can be displayed in a user interface, showing the presence of a CTO at the segment level.

[0082] [Figure 8I]FIG. 10 shows an example of a portion of a panel that can be displayed in a user interface, indicating left or right dominance of a patient.

[0083] [Figure 8J] Figure 10 shows an example of a panel that can be displayed on the user interface, showing an animated arterial tree illustrating the abnormalities found.

[0084] [Figure 8K] FIG. 8J shows an example of a portion of a panel that may be displayed on the panel of FIG. 8J that may be selected to show details of the anomaly.

[0085] [Figure 9A] FIG. 10 illustrates an example of an atherosclerosis panel that can be displayed on a user interface, displaying a summary of atherosclerosis information based on analysis.

[0086] [Figure 9B] FIG. 10 illustrates an example of a vessel selection panel that can be used to select vessels for which a summary of atherosclerosis information is displayed on a segment-by-segment basis.

[0087] [Figure 9C] FIG. 10 shows an example of a panel that can be displayed on the user interface showing atherosclerosis information per segment.

[0088] [Figure 9D] FIG. 10 shows an example of a panel that can be displayed on the user interface containing patient-specific data on stenosis.

[0089] [Figure 9E] FIG. 10 shows an example of a portion of a panel that can be displayed on a user interface, where segment details are displayed when a count is selected (e.g., by hovering over the number).

[0090] [Figure 9F] FIG. 10 shows an example of a portion of a panel that can be displayed on a user interface, showing stenosis per segment in graphical form, for example a bar graph of stenosis per segment.

[0091] [Figure 9G] FIG. 10 shows another example of a panel that can be displayed on the user interface, showing vascular information, such as percent diameter stenosis and minimum lumen diameter.

[0092] [Figure 9H] FIG. 10 shows an example of a portion of a panel that can be displayed on a user interface showing a legend for percent diameter stenosis.

[0093] [Figure 9I] FIG. 10 shows an example of a panel that can be displayed on the user interface showing minimum and reference luminal diameters.

[0094] [Figure 9J] Figure 9I shows a portion of the panel shown and illustrates how details of a specific minimum lumen diameter can be quickly and efficiently displayed by selecting (e.g., by mouse-over) the desired graphic of the lumen.

[0095] [Figure 9K] FIG. 1 shows an example of a panel that can be displayed in a user interface, showing CADS-RADS score selection.

[0096] [Figure 9L] FIG. 10 shows an example of a panel that can be displayed in the user interface showing further CAD-RADS details generated in the analysis.

[0097] [Figure 9M]FIG. 10 shows an example of a panel that can be displayed in the user interface, showing a table showing the quantitative stenosis and vascular output determined during the analysis.

[0098] [Figure 9N] FIG. 10 shows an example of a panel that can be displayed in the user interface showing a table showing quantitative plaque output.

[0099] [Figure 10] 10 is a flowchart illustrating a process 1000 for analyzing and displaying CT images and corresponding information.

[0100] [Figures 11A-11B] 11A and 11B are exemplary CT images illustrating how plaque can appear differently depending on the image acquisition parameters used to capture the CT image; FIG. 11A shows a CT image reconstructed using filtered back projection, and FIG. 11B shows the same CT image reconstructed using iterative reconstruction.

[0101] [Figures 11C-11D] 11A and 11B show another example showing that plaque can appear differently in a CT image depending on the image acquisition parameters used to capture the CT image; FIG. 11C shows a CT image reconstructed using iterative reconstruction, and FIG. 11D shows the same image reconstructed using machine learning.

[0102] [Figure 12A] FIG. 1 is a block diagram representing one embodiment of a normalization device that can be configured to normalize medical images for use in the methods and systems described herein.

[0103] [Figure 12B] FIG. 1 is a perspective view illustrating an embodiment of a normalization device including a multilayer substrate.

[0104] [Figure 12C]FIG. 12C is a cross-sectional view of the normalization device of FIG. 12B showing various compartments positioned therein to hold samples of known substances used during normalization.

[0105] [Figure 12D] FIG. 10 is a top view showing an example arrangement of multiple compartments within a normalization device, where in the illustrated embodiment, the multiple compartments are arranged in a rectangular or grid pattern.

[0106] [Figure 12E] FIG. 10 is a top view showing another example arrangement of multiple compartments within a normalization device, where in the illustrated embodiment, the multiple compartments are arranged in a circular pattern.

[0107] [Figure 12F] FIG. 10 is a cross-sectional view of another embodiment of a normalization device showing various features, including adjacently arranged compartments, a self-sealing, fillable compartment, and compartments of various sizes.

[0108] [Figure 12G] FIG. 10 is a perspective view illustrating one embodiment of an attachment mechanism for a normalization device that uses hook-and-loop fasteners to secure the substrate of the normalization device to the fasteners of the normalization device.

[0109] [Figures 12H-12I] FIG. 1 illustrates an embodiment of a normalization device including an indicator configured to indicate an expiration status of the normalization device.

[0110] [Figure 12J] 1 is a flowchart illustrating an exemplary method for normalizing medical images for algorithm-based medical imaging analysis, where normalizing medical images improves the accuracy of algorithm-based medical imaging analysis.

[0111] [Figure 13]FIG. 1 is a block diagram illustrating one embodiment of a system for medical image analysis, visualization, risk assessment, disease tracking, treatment generation, and / or patient report generation.

[0112] [Figure 14] FIG. 1 is a block diagram illustrating an embodiment of a computer hardware system configured to execute software that implements one or more embodiments of a system for medical image analysis, visualization, risk assessment, disease tracking, treatment generation, and / or patient report generation. DETAILED DESCRIPTION OF THE INVENTION

[0113] Some embodiments, examples, and illustrations are disclosed below, but the inventions described herein are not intended to be limiting. The disclosure extends beyond the specifically disclosed embodiments, examples, and illustrations, and Other uses of the invention, as well as obvious modifications and equivalents of the invention, will occur to those skilled in the art. It will be understood that embodiments of the present invention will be described with reference to the accompanying drawings, throughout which: Like numbers refer to like elements throughout. Terms used in the description presented herein include: It is merely because it is used in conjunction with a detailed description of certain specific embodiments of the present invention. Therefore, it should not be construed in any limiting or restrictive manner. The embodiments may have several novel features, any of which may independently provide desirable attributes. or are essential to the practice of the inventions described herein.

[0114] Introduction Disclosed herein are methods for medical image analysis, diagnosis, triage, decision making, and / or are systems, methods, and devices for disease tracking. Coronary heart disease is a Affecting over 10 million Americans. The trend is almost twofold. First, doctors generally have to rely on, for example, biochemistry or blood content. Or analyzing biomarkers to see if a patient has high levels of cholesterol in their bloodstream. It examines the cardiovascular health of patients at a macro level by determining whether or not they have a high level of In response to the high cholesterol in the bloodstream, some doctors have reported that patients As part of the treatment plan, sterols may be used to reduce perceived sterol content. Prescribe one or more medications, such as fluticasone.

[0115] The second general trend in currently treating cardiovascular health problems is to use angiography to Helps doctors assess a patient's cardiovascular health by identifying major blockages in various arteries In response to the discovery of large blockages in various arteries, physicians sometimes This involves angioplasty, a procedure in which a balloon catheter is guided to the point where the blood vessel is narrowed. Once properly positioned, the balloon is inflated to remove the plaque or fat. They compress or flatten into the arterial wall and / or stretch and open the artery, allowing blood to pass through. In some cases, the balloon may: The stent is positioned and expanded within the vessel to compress the plaque and / or It is used to keep the arteries open and allow more blood to flow. 000 cardiac stent procedures are performed in the United States each year.

[0116] However, a recent $100 million federally funded study found that There is some doubt as to whether the current trends in treatment are the most effective treatment for all types of patients. A recent study included over 5,000 people from 320 regions in 37 countries. Stent and bypass surgery are used to treat patients with moderate to severe stable heart disease. More effective than combined lifestyle changes in patients with stable heart disease New evidence has emerged that this is unlikely. For some, undergoing invasive surgical procedures such as angioplasty and / or heart bypass is Instead, they were prescribed heart medications such as statins and had to follow certain lifestyle changes, such as regular exercise. This new treatment plan has benefited thousands of patients worldwide. An estimated 500,000 cardiac surgeries are performed annually in the United States. It is estimated that one in five tent procedures is performed in patients with stable heart disease. Of the estimated 100,000 patients with stable heart disease, 25% (approximately 23,000) experience chest pain. Therefore, it is estimated that over 20,000 patients per year are the likelihood of forgoing extensive surgical procedures or experiencing no complications as a result of such procedures; is possible.

[0117] Patients forgoing invasive surgical procedures and instead opting for drug treatment plans, and / or Alternatively, the patient's cardiovascular disease may be further assessed to determine whether a more effective treatment plan should be developed. It may be important to better understand the arterial health of patients. For example, it may be advantageous to have a better understanding of the extent to which plaque buildup in a patient's body is It helps to understand whether it is mostly fatty deposits or mostly calcified material deposits. The former situation requires treatment with cardiac drugs such as statins, while the latter In this situation, the patient can be treated without prescribing cardiac medication or implanting a stent of some kind. However, if plaque buildup persists, it should be monitored periodically. Severe enough to cause severe stenosis or narrowing of arterial blood vessels, affecting the heart muscle If blood flow becomes blocked, a stent may be implanted to open the blood vessels further. These patients may have a heart attack or sudden cardiac death (SCD), so a stent should be implanted. Invasive angioplasty procedures may be necessary. Sudden cardiac death is the leading cause of natural death in the United States. Cardiovascular disease is one of the causes of death in adults, accounting for approximately 325,000 deaths per year. It accounts for approximately half of all deaths. SCD is twice as common in men as in women. occurs in people in their mid-30s to mid-40s. Over 50% experience sudden cardiac arrest without warning. is doing.

[0118] For millions of people with heart disease, the blood flowing through the arteries in the patient's body is simply circulated. There is a need to understand not just the chemical or chemical content of these proteins but also their overall arterial health better. For example, some of the systems, devices, and methods disclosed herein In embodiments, "benign" or stable plaque or plaque containing hardened calcified content is Arteries with vascular disease are not considered life-threatening to the patient, but are considered "malignant" or potentially dangerous. Bad plaque or plaque containing fatty material can rupture within the artery. This can release fatty substances into the arteries, making them more dangerous to life. These fatty substances, when released into the bloodstream, can cause inflammation, This can lead to the formation of a blood clot. A blood clot in an artery can block blood from moving to the heart muscle. This can lead to heart attacks or other cardiac events. In some cases, blood may flow through fatty plaque rather than through calcified plaque. It is generally difficult for blood to flow through areas where blood has accumulated. There is a need to better understand and analyze walls.

[0119] Additionally, blood tests and drug treatment plans can help reduce cardiovascular health problems and prevent cardiovascular events. Although such treatment methodologies may help reduce cardiovascular events (e.g., heart attacks), risk of misperceiving the extent of risk and / or being unable to identify or diagnose it; For example, simply analyzing a patient's blood chemistry may However, patients may have arterial vessels with significant amounts of malignant plaque, a fatty deposit of material, along the vessel walls. Similarly, angiograms may not identify the extent of stenosis or narrowing of the blood vessels. However, it is not clear how much of the arterial wall is significantly affected by malignant plaque. The extent of such malignant plaque accumulation within the arterial wall may not be clearly identified. It may be an indicator of patients at high risk of suffering a cardiovascular event such as a heart attack. The presence of malignant plaque can lead to rupture, and fatty material can build up in the arteries. They are released into the bloodstream, which can then cause blood clots in the arteries. Mochi can stop blood flow to the heart tissue, which can lead to a heart attack. Therefore, the arterial wall can be analyzed and / or assessed for malignancy. Regardless, there is a need for new techniques to identify the extent of plaque accumulation within the arterial wall. be.

[0120] The various systems, methods, and devices disclosed herein address the above-mentioned challenges. In particular, various embodiments described herein are directed to medical image analysis, diagnostic imaging, and Systems, methods, and data for diagnosis, severity classification, decision making, and / or disease tracking In some embodiments, the systems, devices, and The method includes a computer configured to automatically and / or dynamically analyze medical images. Non-invasive medical images, such as CT images, can be input into the data system. Utilizing imaging techniques to identify one or more coronary arteries and / or plaque therein. For example, in some embodiments, the system may be configured to: utilizes machine learning and / or artificial intelligence algorithms to automatically and / or or dynamically analyze to identify and quantify one or more coronary arteries and / or plaque. In some embodiments, the system may be configured to: The system may further include, for example, one or more artificial intelligence and / or machine learning algorithms. The system is used to identify, quantify, and / or classify one or more coronary arteries and and / or plaques may be used to generate treatment plans, track disease progression, and / or It can be configured to provide medical reports on patient characteristics. In an embodiment, the system further comprises a display, e.g., in the form of a graphical user interface. , identified, quantified, and / or classified one or more coronary arteries and / or prostate Lark visualizations can be configured to be generated dynamically and / or automatically. Additionally, in some embodiments, different medical imaging scanners and / or different To calibrate the medical images obtained from the scan parameters or environment, the system Utilizing a normalization device comprising one or more compartments of one or more substances. It can be configured as follows.

[0121] As discussed in more detail herein, the systems, devices, and methods described herein include: Automatic and quantitative analysis of various parameters related to plaque, cardiovascular arteries, and / or other structures. More specifically, the methods described herein allow for quantitative and / or dynamic analysis. In some embodiments, medical images of a patient, such as coronary CT images, may be taken at a medical facility. Rather than being viewed by a physician or performing a general assessment of a patient, medical images are In one embodiment, a biomarker is provided that is configured to perform the one or more analyses in a reproducible manner. Therefore, in some embodiments, The systems, methods, and devices described herein are capable of performing automated and / or dynamic processes. can be used to provide a quantified measure of one or more features of a coronary CT image. For example, in some embodiments, the main server system may configured to identify one or more blood vessels, plaque, and / or fat; Based on the identified features, in some embodiments, the system may, for example, Radiodensity of one or more areas of the plaque, stable plaque and / or unstable plaque the identity of the sphere, its volume, its surface area, its geometry, its heterogeneity, and / or Configured to generate one or more quantified measurements from raw medical images, such as In some embodiments, the system can also be configured to measure, for example, diameter, volume, shape, etc. One or more quantifications of blood vessels from raw medical images, such as blood vessel morphology, blood vessel size, and / or other parameters. Measurements can be generated based on the identified features and / or quantified measurements. In some embodiments, the system uses raw medical images to perform, for example, atherosclerosis. Plaque-based diseases or conditions, such as atherosclerosis, stenosis, and / or ischemia may be configured to generate and / or track progress of risk assessments of Additionally, in some embodiments, the system may perform quantized color mapping of different features. GUI visualization of one or more identified features and / or quantified measurements, such as In some embodiments, the systems described herein can be configured to generate The systems, devices, and methods are designed to reduce cardiovascular events, major adverse cardiovascular events (MACE), and ), rapid plaque progression, and / or non-response to the drug. In particular, some implementations utilize medical image-based processing to evaluate the In this form, the system analyzes only non-invasively acquired medical images to identify the target. The method may be configured to automatically and / or dynamically assess such health risks of a person. In some embodiments, one or more of the processes are performed using AI and / or ML algorithms. In some embodiments, the method described herein can be automated using algorithms. One or more of the processes described can be performed reproducibly within minutes. This does not produce a reproducible prognosis or assessment, takes a significant amount of time, and / or This is in stark contrast to existing standards today, which require extensive or invasive procedures.

[0122] As such, in some embodiments, the systems, devices, and The method provides the physician and / or patient with specific information about the patient's plaque that does not exist today. Quantitative and / or measured data can be provided. For example, some experiments In an embodiment, the system may, for example, measure the radiation density of pixels and / or regions within a medical image. The intensity values ​​were used to estimate the volume of stable and / or unstable plaque, its proportion to the total vessel volume, and Provide specific figures regarding ratios, percentage of stenosis, and / or other In some embodiments, quantification can be performed by image processing and downstream analysis. Such a detailed level of plaque parameters provides a novel approach to assessing patient health and This can provide more accurate and useful tools for assessing risk and / or risk.

[0123] Overall Overview In some embodiments, the systems, devices, and methods described herein are Automated and / or automated image analysis, diagnosis, severity classification, decision making, and / or disease tracking. Figure 1 shows the medical image analysis, visualization, risk assessment, and disease 1 shows an overview of an example embodiment of a method for patient tracking, treatment generation, and / or patient report generation. As shown in FIG. 1, in some embodiments, the system , e.g., one or more images of a subject, such as a medical image of a coronary artery region of a subject or patient. The medical imaging system is configured to evaluate and / or analyze medical images.

[0124] In some embodiments, prior to obtaining the medical image, at block 102, a normalization device Attached to the subject and / or placed within the field of view of a medical imaging scanner For example, in some embodiments, the normalization device comprises water, calcium, and and / or other, having one or more compartments containing one or more substances. Additional details regarding normalization devices are provided below. Medical Images Scanning scanners produce images with different scalable radiodensities of the same object. This may be done, for example, depending on the type of medical imaging scanner or device used. Not only the type, but also the scan parameters for the specific day and / or time the scan was taken. As a result, the results of two different analyses of the same subject may differ depending on the data and / or environment. Even if a scan is performed, the brightness and / or may vary in darkness, which may reduce the accuracy of the analysis results processed from that image. Taking such differences into account, in some embodiments, one or more A normalized device with known elements is scanned with the subject, and the resulting The resulting image is translated, transformed, and and / or can be used as a standard for normalization. In some embodiments, the normalization device may be attached to a subject and / or administered to a medical institution. The device is positioned within the field of view of a medical imaging scan.

[0125] In some embodiments, at block 104, the medical institution then For example, the medical images are of a coronary artery region of a subject or patient. In some embodiments, the systems disclosed herein can be used with X-ray, dual Low Energy Computed Tomography (DECT), Spectral CT, Photon Counting Detector CT, ultrasound such as echocardiography or intravascular ultrasound (IVUS), magnetic resonance (MR) imaging Imaging, Optical Coherence Tomography (OCT), Positron Emission Tomography (PET) and and nuclear medicine imaging, including single-photon emission computed tomography (SPECT), near-field such as, but not limited to, infrared spectroscopy (NIRS), and / or others. , image domain or projection, as raw scan data or any other medical data As used herein, the term "computer-aided design" can be configured to incorporate CT data from a domain. The terms CT image data or CT scan data refer to processed CT image data. Process such data through an artificial intelligence (AI) algorithm system to generate It may replace any of the medical scanning modalities and processes described above. In some embodiments, data from these imaging modalities can be Allows cardiovascular phenotypes to be determined, and image domain data, projection domain data , and / or a combination of both.

[0126] In some embodiments, at block 106, the medical institution also collects non-image data from the subject. For example, this can be achieved through blood tests, biomarkers, and In some embodiments, Block 1 may include a At block 108, the medical institution may provide one or more medical images and / or other Non-imaging data can be sent to the main server system. In this embodiment, the main server system receives medical images and / or receive and / or otherwise access other non-imaging data. It can be configured as follows.

[0127] In some embodiments, at block 112, the system One or more medical images can be automatically stored and / or accessed from It can be configured to analyze dynamically and / or dynamically. For example, some implementations In an embodiment, the system captures raw CT image data and analyzes identified features in the CT data. Artificial intelligence (AI) algorithms are used to identify, measure, and / or analyze various aspects of arteries. algorithms, machine learning (ML) algorithms, and / or other physics-based algorithms In some embodiments, the algorithm can be configured to apply the algorithm to the raw CT data. The raw medical image data is input into a cloud-based data In some embodiments, the medical image is uploaded to a repository system. Image data processing is cloud-based using AI and / or ML algorithms Some embodiments involve processing data in a computing system. So, the system will run for about 1 minute, about 2 minutes, about 3 minutes, about 4 minutes, about 5 minutes, about 6 minutes, about 7 minutes, about 8 minutes. , about 0 minutes, about 10 minutes, about 15 minutes, about 20 minutes, about 30 minutes, about 35 minutes, about 40 minutes, about 45 minutes, Approximately 50 minutes, approximately 55 minutes, approximately 60 minutes, and / or defined by two of the above values Within the scope, it can be configured to analyze raw CT data.

[0128] In some embodiments, the system utilizes a blood vessel identification algorithm to identify blood vessels in a medical image. The method can be configured to identify and / or analyze one or more blood vessels. In some embodiments, the system utilizes a coronary artery identification algorithm to identify coronary arteries in medical images. can be configured to identify and / or analyze one or more coronary arteries of In some embodiments, the system utilizes a plaque identification algorithm to configured to identify and / or analyze one or more plaque regions within the image. In some embodiments, a blood vessel identification algorithm, a coronary artery identification algorithm, , and / or the plaque identification algorithm uses AI and / or ML algorithms For example, in some embodiments, a blood vessel identification algorithm, a coronary artery identification algorithm, and / or plaque identification algorithms in one or more vessels, coronary arteries, and It can be trained on multiple medical images where the plaque and / or plaque regions are pre-identified. Based on such training, for example, in some embodiments, a convolutional neural network By using a network, the system extracts blood vessels, coronary arteries, and and / or plaque presence and / or parameters automatically and / or dynamically The device may be configured to identify the

[0129] Therefore, in some embodiments, processing of medical images or raw CT scan data The theory determines and / or determines the presence and / or absence of specific arterial vessels in a patient's body. This may include analyzing medical images or CT data to identify or identify the disease. While specific arteries may naturally exist in a particular patient, Certain arteries may not exist in other patients.

[0130] In some embodiments, at block 112, the system further comprises, for example, AI and / or Or use ML algorithms to identify vessels, coronary arteries, and / or plaques. In particular, in some embodiments, the system may be configured to analyze For example, arterial remodeling, curvature, volume, width, diameter, length, and / or other The method may be configured to determine one or more vascular morphological parameters. In an embodiment, the system may, for example, identify one or more plaques shown in a medical image. Area volume, surface area, geometry, radiation density, volume-to-surface ratio or function, non-uniformity Determine one or more plaque parameters, such as the sex index, and / or other "Radioconcentration" as used herein refers to electromagnetic It is a broad term referring to the relative inability of light (e.g., X-rays) to pass through matter. Radiation density values ​​are obtained from image data (e.g., in film, print, or electronic format) The radiodensity value of an image corresponds to the density of the material shown in the image.

[0131] In some embodiments, at block 114, the system identifies and / or or subject time point analysis utilizing analyzed vessels, coronary arteries, and / or plaques. In some embodiments, the system may be configured to perform one using automatic and / or dynamic image processing of one or more medical images taken from different time points to identify and / or characterize one or more blood vessels, coronary arteries, and / or plaques. and deriving one or more parameters and / or classifications thereof. For example, as described in more detail herein, in some embodiments The system generates one or more quantification metrics of the plaque, and / or Alternatively, the identified plaque regions may be classified as benign or malignant. Further, in some embodiments, at block 114, the system may The method can be configured to generate one or more treatment plans for the subject based on the In some embodiments, the system comprises one or more AI and / or ML algorithms. The method utilizes algorithms to identify and / or analyze blood vessels or plaques and to identify one or more Derive quantitative metrics and / or classifications of the number and / or generate treatment plans. The system can be configured to achieve this.

[0132] In some embodiments, if previous scans or medical images of the subject exist, the system The system performs one or more time-based analyses, such as disease tracking, in block 126. For example, in some embodiments, the system may be configured to One or more quantified patterns derived from the subject's previous scans or medical images If the system has access to the parameters or classifications, it will or one or more quantified parameters or classifications derived from medical images; and comparing the results to determine the progression and / or status of the subject's disease. do.

[0133] In some embodiments, in block 116, the system Graphical user interface (GUI) or other visualization of the results automatically and and / or dynamically generate a set of images, including, for example, an identified blood vessel, a plaque, Region, coronary artery, quantified metrics or parameters, risk assessment, proposed treatment plan The results of the analysis may include: In some embodiments, the system can perform a CT scan in, for example, 10-15 minutes or less. - Analyze the arteries present in the data and display various images of the arteries present in the patient's body. In contrast, for example, benign or malignant plaque or any other factor To perform a visual assessment of the CT scan to identify stenosis alone, without considering the skill level This can take anywhere from 15 minutes to over an hour depending on the patient and may require the assistance of a radiologist and / or cardiologist. There may be significant variability between imaging devices.

[0134] In some embodiments, at block 118, the system Other visualizations, analysis results, and / or treatments may be configured to be sent to the healthcare provider. In some embodiments, at block 120, the medical institution's physician then Investigate and / or confirm the GUI or other visualization, analysis results, and / or treatment may be acknowledged and / or corrected.

[0135] In some embodiments, at block 122, the system performs a medical record on the patient characteristics. Ports can be configured to be further generated and sent to the patient, who can then block them. In some embodiments, a medical report regarding patient characteristics may be received at 124. The report is based on analytical results derived from medical image processing and analysis and / or It can be dynamically generated based on other things generated from the The report should include identified vessels, plaque areas, coronary arteries, and quantified metrics or parameters. the meter, risk assessment, suggested treatment plan, and / or any other It may include the results of the analysis.

[0136] In some embodiments, one or more of the processes shown in FIG. 1 may be performed in a single patient, e.g., Repeated testing at different times can be used to track the progression and / or status of a patient's disease. This can be done.

[0137] Image processing-based classification of benign versus malignant plaques As noted above, in some embodiments, the systems, methods, and and the device distinguishes benign versus malignant plaques based on medical image analysis and / or processing. Automatically and / or dynamically identify and / or characterize plaques or stable versus unstable plaques. For example, in some embodiments, the system is configured to perform AI and and / or ML algorithms to identify areas within, along, or within arteries. configured to identify areas within an artery that exhibit plaque buildup and / or outside the artery. In some embodiments, the system may include a proximal endoscope associated with an arterial vessel wall. The system can be configured to identify the contours or boundaries of a Lark accumulation. In this state, the system detects lines that define the shape and configuration of the plaque buildup associated with the artery. In some embodiments, the system may be configured to render or generate , whether the plaque buildup is a specific type of plaque, and / or whether the specific plaque buildup is In some embodiments, the composition or properties of the product can be identified. The system may be configured to characterize plaques binary, sequentially, and / or continuously. In some embodiments, the system may be configured to: The intense color or dark grayscale nature of the image and / or its attenuated density Determination of the same (e.g., using the Hounsfield unit scale or other) determining that the type of plaque accumulation identified is "malignant" plaque; For example, in some embodiments, the system may determine whether the brightness of the plaque is predetermined. to identify a particular plaque as a "malignant" plaque if it is darker than the level In some embodiments, the system may be configured to: Benign pigmentation based on the range of white shades and / or light gray scale properties For example, in some embodiments, the system The system classifies a particular plaque as "missing" if the plaque's brightness is less than a predetermined level. In some embodiments, the plaque may be identified as "benign." The system is configured to determine that dense areas on the CT scan are associated with "malignant" plaque. The system can then identify areas of benign plaque that correspond to the white areas. In some embodiments, the system can be configured to: of total plaque, benign plaque, and / or malignant plaque identified in multiple vessels It can be configured to identify and determine total area and / or volume. In an embodiment, the system may include a method for determining the extent of identified plaques overall, the extent of benign plaques, and and / or the length of the area of ​​the malignant plaque. In this embodiment, the system may include a method for determining the extent of identified plaques, the extent of benign plaques, and The system can be configured to determine the breadth of the extent of benign and / or malignant plaque. Plaque, among other things, is unlikely to cause a heart attack and may show significant plaque progression. are considered to be ischemic because they are less likely to be ischemic and / or Conversely, "bad" plaques are significantly more likely to cause heart attacks, among other things. likely to indicate plaque progression and / or ischemia, In some embodiments, "benign" plaques are considered to be It may be considered as such because it is unlikely that it will cause a reflow phenomenon. Since "intact" plaques are unlikely to undergo reflow during coronary revascularization, may be regarded as

[0138] Figure 2A shows a method for analyzing and classifying plaque from medical images that can be obtained non-invasively. 2A is a flowchart illustrating an overview of an example embodiment of the block diagram of FIG. At block 202, in some embodiments, the system may include a coronary region of the subject. medical images that can be generated and / or stored in the medical image database 100; The medical image database 100 can be configured to access the system. and / or may be locally accessible via a network connection Medical images can be remotely located and accessible via, for example, CT, Dual Energy Computed Tomography (DECT), Spectral CT, Photon Counting CT, X-ray, ultrasound, echocardiography, intravascular ultrasound (IVUS), magnetic resonance (MR) imaging ging, optical coherence tomography (OCT), nuclear medicine imaging, proton emission tomography PET, single photon emission computed tomography (SPECT), or near-field infrared May include images obtained using one or more modalities, such as spectroscopy (NIRS) In some embodiments, the medical images may be contrast-enhanced CT images, non-contrast enhanced CT images, or Trust CT images, MR images, and / or any of the modalities mentioned above It includes one or more of the images obtained.

[0139] In some embodiments, the system may include one or more medical images as discussed herein. The system may be configured to automatically and / or dynamically perform one or more analyses. For example, in some embodiments, at block 204, the system selects one or more arteries. The one or more arteries may be, among others, coronary arteries, May include the carotid arteries, aorta, renal arteries, lower extremity arteries, upper extremity arteries, and / or cerebral arteries In some embodiments, the system uses image processing to One or more AIs are used to automatically and / or dynamically identify arteries or coronary arteries. and / or ML algorithms. In some embodiments, the one or more AI and / or ML algorithms For a set of medical images in which coronary arteries are identified, a convolutional neural network It can be trained using neural networks (CNNs), which can then be used to develop AI and / or ML Algorithms can automatically identify arteries or coronary arteries directly from medical images In some embodiments, the arteries or coronary arteries are identified by size and / or location. It is determined.

[0140] In some embodiments, at block 206, the system detects one or more can be configured to identify multiple plaque regions. The system uses image processing to automatically identify one or more plaque regions and / or or dynamically identify using one or more AI and / or ML algorithms. For example, in some embodiments, one or Multiple AI and / or ML algorithms analyze medical images in which plaque regions are identified. A convolutional neural network (CNN) can be trained on a set of This allows AI and / or ML algorithms to directly extract data from medical images. In some embodiments, the system allows for automated identification of target regions. For each coronary artery identified in the image, the vessel wall and lumen wall were identified. In some embodiments, the system can then be configured to: In some embodiments, the system is configured to determine the volume between the plaque. The system is generally programmed with or without normalization using, for example, a normalization device. By setting a predetermined threshold or range of radiation concentration values ​​that are associated with a lark, To identify plaque areas based on radiodensity values ​​commonly associated with plaque. It can be configured as follows.

[0141] In some embodiments, the system, at block 208, extracts one or more The system automatically and / or In some embodiments, the one or more blood vessels are dynamically determined. Quantification of morphological and / or plaque parameters derived from medical images For example, in some embodiments, the system may include: Utilizing AI and / or ML algorithms or other algorithms to Configured to determine multiple vascular morphological parameters and / or plaque parameters As another example, in some embodiments, the system may include a positive arterial remodeling, negative arterial remodeling, and / or intermediate arterial remodeling and one or more classifications of plaque-induced arterial remodeling, which may further include: In some embodiments, the method may be configured to determine vascular morphological parameters. The classification of arterial remodeling was based on the maximum vessel diameter in the plaque area and the normal database. Arterial remodeling can be detected based on the ratio of the diameter to the normal reference vessel diameter in the same area. In some embodiments, the system determines a classification of the maximum When the ratio of the vessel diameter to the normal reference vessel diameter in the same area exceeds 1.1, arterial remodeling is considered to be important. In some embodiments, the system may be configured to classify the When the ratio of the maximum vessel diameter in the plaque area to the normal reference vessel diameter is less than 0.95, The method can be configured to classify vascular remodeling as negative. In this state, the system measures the ratio of the maximum vessel diameter in the plaque area to the normal reference vessel diameter to be 0. A value between 95 and 1.1 can be configured to classify arterial remodeling as intermediate.

[0142] Additionally, as part of block 208, in some embodiments, the system may include a block 201, one or more plaque regions and / or one or more blood vessels Or it may be configured to determine the geometry and / or volume of the artery. For example, the system may be configured to detect whether the geometry of a particular plaque region is circular or oval or other shapes. In some embodiments, the method can be configured to determine the shape of the plaque region. Geometry can be a factor in assessing plaque stability. In some embodiments, the system derives from medical images the curvature, diameter, length, and The device may be configured to determine the volume, and / or any other parameter.

[0143] In some embodiments, as part of block 208, the system , the volume and / or surface area of ​​the plaque area, and / or e.g. the volume-to-surface area ratio or other relationship of the plaque area, such as the diameter, radius, and / or thickness of the In some embodiments, the ratio of the volume to the surface area can be determined. A small plaque can indicate that the plaque is stable. In some embodiments, the system detects a volume to surface area ratio of the plaque region that is less than a predetermined threshold. A ratio can be configured to determine that is indicative of stable plaque.

[0144] In some embodiments, as part of block 208, the system The method can be configured to determine the heterogeneity index of the plaque region. In some embodiments, plaques with low heterogeneity or high homogeneity are characterized by the fact that the plaque is stable. Therefore, in some embodiments, the system may: The heterogeneity of the plaque area below a predetermined threshold is determined to be indicative of stable plaque. In some embodiments, the heterogeneity or uniformity of the plaque region can be measured. The quality of the plaque is determined based on the heterogeneity or homogeneity of the radiodensity values ​​within the plaque area. Therefore, in some embodiments, the system may be configured to measure the geometry of the plaque region. spatial mapping, such as a three-dimensional histogram, of radiation density values ​​within or across The method can be configured to determine the plaque heterogeneity index by generating In some embodiments, the gradient or change in radiation density values ​​across the spatial mapping If the value exceeds a certain threshold, the system can be configured to assign a high heterogeneity index. Conversely, in some embodiments, the radiation density throughout the spatial mapping can be If the gradient or change in the intensity values ​​is below a certain threshold, the system assigns a low heterogeneity index. The system can be configured to assign a different value to each of the plurality of sensors.

[0145] In some embodiments, as part of block 208, the system and can be configured to determine the radiodensity of the plaque and / or its composition. For example, high radiodensity values ​​indicate that the plaque is highly calcified or stable. A low radiodensity value indicates low or unstable plaque calcification. Therefore, in some embodiments, the system may The radiodensity of the plaque area exceeding the threshold was determined to indicate stabilized stable plaque. In addition, different areas within the plaque region can be configured to have different levels. The radioactivity may be calcified in the cells, which may result in different radioactivity concentrations. In some embodiments, the system may measure radiodensity values ​​of plaque regions and / or plaque to determine the composition, percentage, or change in radiation concentration values ​​within an area. For example, in some embodiments, the system may be configured to How much or what percentage of plaque is in the low, medium, high, and and / or any other classification of radiation concentration values. Cut.

[0146] Similarly, in some embodiments, as part of block 208, the system and determining a ratio of the radiodensity value of the plaque to the volume of the plaque. For example, large or small areas of the plaque may have high or low radiation. It may be important to evaluate whether the linear density values ​​are being displayed. In an embodiment, the system may provide different radiodensity values ​​as a function or ratio of plaque volume. The method can be configured to determine the percentage composition of the plaque it contains.

[0147] In some embodiments, as part of block 208, the system determining diffusivity and / or assigning diffusivity indices to plaque areas; For example, in some embodiments, the plaque diffusion rate can be Radiodensity values ​​can indicate low plaque diffusivity or stability. It may depend on the concentration value.

[0148] In some embodiments, at block 210, the system determines and and / or derived one or more vascular morphological parameters and / or quantifications. Based on the plaque parameters, one or more plaques identified from medical images are analyzed. Plaque regions can be configured to be classified as stable versus unstable or good versus bad In particular, in some embodiments, the system determines and / or Derived one or more vascular morphological parameters and / or quantified plan It can be configured to generate a weighted measure of the work parameters. In some embodiments, the system comprises one or more vascular morphological parameters and and / or be configured to weight the quantified plaque parameters equally In some embodiments, the system measures one or more vascular morphological parameters. and / or configured to weight the quantified plaque parameters differently. In some embodiments, the system can be configured to: The morphological parameters and / or quantified plaque parameters can be calculated logarithmically, algebraically, and / or may be configured to use other mathematical transformations for weighting. In some embodiments, the system may generate a weighted criterion at block 210. and / or vascular morphological parameters and / or quantified pull Classify one or more plaque regions using only some of the plaque parameters It can be configured as follows.

[0149] In some embodiments, at block 212, the system analyzes and / or determines The method is configured to generate a quantized color mapping based on the specified parameters. For example, in some embodiments, the system may employ any of the analytical techniques described herein. Calcified plaque, non-calcified plaque, benign plaque, malignant plaque, as determined using Generate quantized color mapping of plaques, stable plaques, and / or unstable plaques. and generating a visualization of the analyzed medical image by generating a visualization of the analyzed medical image. In some embodiments, the quantified color mapping may also be used to measure arterial and / or The epicardial fat may also be included, which may also be included by the system, for example, by one or more AI and / or can be determined by utilizing ML algorithms.

[0150] In some embodiments, at block 214, the system may, for example, Based on the analysis, a plaque classification is automatically derived from the In particular, in some embodiments, the system is configured to generate a treatment plan that: Atherosclerosis of a subject based on raw medical images and automated image processing thereof The system may be configured to assess or predict risk of stenosis, stenosis, and / or ischemia. Cut.

[0151] In some embodiments, one or more of the processes described herein in connection with FIG. 2A are The process can be repeated, for example, if medical images of the same subject are taken again at a later time. If so, one or more of the processes described herein may be repeated, and the results of that analysis may be used to can be used for disease tracking and / or other purposes.

[0152] Identification of non-calcified plaques from non-contrast CT images As discussed herein, in some embodiments, the system performs a CT or other medical images to assess the subject, including, for example, the risk of a cardiovascular event. can be configured to be used as input for performing multiple image analysis techniques. In some embodiments, such CT images may include contrast-enhanced CT images. In such cases, for example, analytical techniques described herein may be used to identify or classify plaques. However, in some embodiments, The CT images may include non-contrast CT images, in which case the radiodensity values ​​are low. This, combined with the presence of other low-radiation components such as blood, results in non-calcified Plaques may be more difficult to identify and / or determine. In embodiments, the systems, devices, and methods described herein may be more widely used. A novel method for determining non-calcified plaques from non-contrast CT images may be possible. provide.

[0153] Also, in some embodiments, in addition to analyzing contrast-enhanced CT scans Alternatively, the system can also measure blood flow within the arteries in a non-contrast CT scan. The device can be configured to examine the attenuation density in arteries, which is lower than the attenuation density of blood in which the device is installed. In some embodiments, these "low attenuation" plaques are characterized by blood attenuation density and coronary artery may surround the plaque and / or represent non-calcified plaque of a different material. In some embodiments, these non-calcified plugs may be differentiated from fat. The presence of plaque indicates that the already calcified plaque is stable, worsening, progressing, or disappearing. These developments measurable through these embodiments may provide incremental predictions. The findings may be linked to patient prognosis and may be associated with calcium stabilization (i.e., higher attenuation) The absence of calcified plaques and non-calcified plaques may be associated with a favorable prognosis. Lack of stabilization (i.e., no increase in attenuation density) or significant progression or new Cium formation increases the risk of rapid disease progression, heart attack, or other major adverse cardiovascular events. It may be associated with a poor prognosis, including

[0154] FIG. 2B shows non-calcified and / or reduced calcifications from a medical image such as a non-contrast CT image. 1 is a flow chart illustrating an overview of an example embodiment of a method for determining attenuated plaque. As discussed herein and shown in FIG. 2B, in some embodiments, the system The method may be configured to determine calcification and / or low-attenuation plaque from medical images. In some embodiments, the medical image is of a coronary region of a subject or patient. In some embodiments, the medical images may be computed tomography (CT), dual energy computed tomography (DCT), or other imaging modalities. Computerized tomography (DECT), spectral CT, X-ray, ultrasound, echocardiography, IVU S, MR, OCT, Nuclear Medicine Imaging, PET, SPECT, NIRS, and / or can be obtained using one or more modalities, such as others. In an embodiment, the system may select, in block 202, from, for example, a medical image database 100: It can be configured to access one or more medical images.

[0155] In some embodiments, non-calcified and / or low-attenuation plaque is detected using medical imaging or To determine this from contrast CT images, the system uses a step-by-step strategy, first The method can be configured to identify areas in a medical image that are clearly non-calcified plaque. In some embodiments, the system then performs a more detailed analysis of the remaining areas in the image. analysis can be performed to identify other areas of non-calcified and / or low-attenuating plaque. By utilizing such a compartmentalized or staged approach, some embodiments In this case, the system must apply more complex analysis to every region or pixel of the image. Medically treat non-calcified and / or low-attenuating plaque with a faster turnaround than in other cases. It can be identified or determined from contrast or non-contrast CT images.

[0156] In particular, in some embodiments, at block 224, the system extracts epicardial In some embodiments, the system may be configured to identify fat. All pixels in the image that have a radiodensity value below a certain threshold and / or within a certain range It can be configured to identify epicardial fat by determining the cell or area. The exact predetermined threshold value or range of radiodensity for identifying epicardial fat is a matter of clinical concern. Dependent on the image, scanner type, scanning parameters, and / or other For this reason, in some instances, a normalization device is used to normalize medical images. For example, in some embodiments, the system may be configured to detect a temperature of approximately -100 Haunsfield. Radiation concentrations in the range including Hounsfield units and / or -100 Hounsfield units Pixels of epicardial fat in a medical image or a non-contrast CT image having intensity values, and In particular, in some embodiments, The system is approximately -100 Hounsfield units, approximately -110 Hounsfield units , approximately -120 Hounsfield units, approximately -130 Hounsfield units, approximately -14 0 Hounsfield units, approximately -150 Hounsfield units, approximately -160 Hounsfield units Hounsfield units, approximately -170 Hounsfield units, approximately -180 Hounsfield units , about -190 Hounsfield units, or a lower limit of about -200 Hounsfield units and about 30 Hounsfield units, about 20 Hounsfield units, and about 10 Hounsfield units. Hounsfield units, approximately 0 Hounsfield units, approximately -10 Hounsfield units, approximately -2 0 Hounsfield units, approximately -30 Hounsfield units, approximately -40 Hounsfield units Hounsfield units, approximately -50 Hounsfield units, approximately -60 Hounsfield units, approximately -7 0 Hounsfield units, approximately -80 Hounsfield units, or approximately -90 Hounsfield units A medical image or non-contour image having radiodensity values ​​within a range with a field-wise upper limit. The epicardial fat pixels and / or regions in the last CT image are identified. It is possible.

[0157] In some embodiments, the system uses the identified epicardial fat as the outer boundary of the artery. Identify and / or segment arteries on medical images or non-contrast CT images using For example, the system may first compute cardiac The epicardial fat area is identified and the volume between the epicardial fat is assigned to arteries such as coronary arteries. It can be configured as follows.

[0158] In some embodiments, at block 226, the system may A first set of pixels or regions in the image are identified as non-calcified or low-attenuation plaque. More specifically, in some embodiments, the system The system is composed of pixels or regions with radiation density values ​​below a predetermined threshold or within a predetermined range. By identifying the areas of low attenuation or non-calcified plaque, the first set of For example, a predetermined threshold or a predetermined range can be configured to Low attenuation or non-calcified pixels that cannot be confused with other materials such as blood In particular, some implementations In an embodiment, the system detects peaks having a radioactivity concentration value of less than about 30 Hounsfield units. The first set of hypoattenuating or non-calcified plaques was performed by identifying the cells or areas. In some embodiments, the system can be configured to identify the target. 0 Hounsfield units, approximately 55 Hounsfield units, approximately 50 Hounsfield units, approximately 45 Hounsfield units, approximately 40 Hounsfield units, approximately 35 Hounsfield units field units, approximately 30 Hounsfield units, approximately 25 Hounsfield units, approximately 2 0 Hounsfield units, approximately 15 Hounsfield units, approximately 10 Hounsfield units, a radiation concentration value of about 5 Hounsfield units or less, and / or about 0 Hounsfield unit, approximately 5 Hounsfield units, approximately 10 Hounsfield units , approximately 15 Hounsfield units, approximately 20 Hounsfield units, approximately 25 Hounsfield units and / or have a radioactivity concentration value of about 30 Hounsfield units or greater , by identifying pixels or regions of low attenuation or non-calcified plaque In some embodiments, the system can be configured to identify the set. At block 238, pixels that are within or below this predetermined range of radiation density values ​​or To classify the region as the first set of identified non-calcified or low-attenuating plaques It can be configured.

[0159] In some embodiments, the system may select a low attenuation or non-calcified plug at block 228. Pixels or regions in a medical image, such as within an identified artery, which may or may not represent a line As mentioned above, some In this embodiment, this second set of candidate pixels or regions is used to determine whether they represent plaque. In particular, in some embodiments, The system identifies pixels or regions of the image that have radiological density values ​​within a predetermined range. By doing so, pixels or regions that may be low attenuation or non-calcified plaque can be identified. In some embodiments, the second set of pixels may be configured to identify a second set of pixels. The predetermined range for identifying this second set of cells or regions is approximately 30 Haunsfields. In some embodiments, the ion concentration can be from 100 Hounsfield units to 100 Hounsfield units. The predetermined range for identifying this second set of pixels or regions is approximately 0. Hounsfield unit, 5 Hounsfield unit, 10 Hounsfield unit, 15 Hounsfield unit Hounsfield Unit, 20 Hounsfield Unit, 25 Hounsfield Unit, 30 Hounsfield units, 35 Hounsfield units, 40 Hounsfield units, 45 Hounsfield units, lower limit of 50 Hounsfield units, and / or approximately 5 5 Hounsfield units, 60 Hounsfield units, 65 Hounsfield units , 70 Hounsfield units, 75 Hounsfield units, 80 Hounsfield units, 85 Hounsfield units, 90 Hounsfield units, 95 Hounsfield units 100 Hounsfield units, 110 Hounsfield units, 120 Hounsfield units Hounsfield units, 130 Hounsfield units, 140 Hounsfield units, It may have an upper limit of 150 Hounsfield units.

[0160] In some embodiments, at block 230, the system performs pixel or region identification. The method may be configured to perform a second set of non-uniformity analysis on the second set of pixels. Depending on the range of radioconcentration values ​​used to identify the second set of cells, several In an embodiment, the second set of pixels or regions contains blood and / or plaque. Blood generally exhibits a more homogeneous gradient of radiodensity values ​​compared to plaque. Therefore, in some embodiments, the nucleotides identified as part of the second set may be By analyzing the homogeneity or heterogeneity of the selected pixels or regions, the system It may be possible to distinguish between blood and non-calcified or low-attenuating plaque. In some embodiments, the system is located within or within the geometry or region of the plaque. Generating spatial mapping, such as a three-dimensional histogram, of radiation density values ​​over a given area a heterogeneity index in a second set of regions of pixels identified from the medical image by In some embodiments, the entire spatial mapping may be configured to determine If the gradient or change in radiation concentration values ​​over the Assigning a heterogeneity index and / or configuring classification as plaque Conversely, in some embodiments, the radiation density values ​​across the spatial mapping can be If the slope or change in is below a certain threshold, the system assigns a low heterogeneity index. The device may be configured to classify the sample as blood and / or as blood.

[0161] In some embodiments, at block 240, the system A subset of the second set of regions of the plaque is then identified as non-calcified or reduced plaque. In some embodiments, the blockade may be configured to identify the plaque as a decaying plaque. At block 242, the system analyzes the identified non-calcified or low attenuation plates from block 238. the first set of plaques and the identified non-calcified or low-attenuation plaques from block 240. Therefore, non-contrast Although CT images are used, in some embodiments the system can also detect other substances such as blood. Due to the possibility of overlap, they are more difficult to identify compared with calcified or hyperattenuating plaques. The imaging device can be configured to identify low attenuation or non-calcified plaque, which may be present in the image.

[0162] In some embodiments, the system also detects calcifications or other abnormalities from the medical image at block 232. This process can be configured to determine high-attenuation plaques. or compared with identifying low-attenuation or noncalcified plaques from non-contrast CT images. In particular, in some embodiments, the system may be configured to detect when a predetermined threshold is exceeded. and / or identifying pixels or regions in the image that have radiological density values ​​within a predetermined range. By determining the For example, in some embodiments, The system is approximately 100 Hounsfield units, approximately 150 Hounsfield units, and approximately 200 Hounsfield units, approximately 250 Hounsfield units, approximately 300 Hounsfield units 350 Hounsfield units, approximately 400 Hounsfield units, approximately 450 Hounsfield units, approximately 500 Hounsfield units, approximately 600 Hounsfield units 700 Hounsfield units, approximately 800 Hounsfield units, approximately 900 Hounsfield units, approximately 1000 Hounsfield units, approximately 1100 Hounsfield units 1200 Hounsfield units, approximately 1300 Hounsfield units, Approximately 1400 Hounsfield units, approximately 1500 Hounsfield units, approximately 1600 Ha Hounsfield unit, approximately 1700 Hounsfield unit, approximately 1800 Hounsfield 1900 Hounsfield units, approximately 2000 Hounsfield units, approximately 2500 Hounsfield units, approximately 3000 Hounsfield units, and / or Medical images or non-contrast CT images with radiodensity values ​​above any other minimum threshold Calcification or high attenuation plaque regions or pixels are identified from the It is possible.

[0163] In some embodiments, at block 234, the system selects one or more Can be configured to generate quantized color mappings for multiple identified materials For example, in some embodiments, the system may detect non-calcified or low-attenuation plaque, Calcified or hyperattenuating plaque, total plaque, arteries, epicardial fat, and / or It is possible to assign different colors to different regions associated with different substances, such as In some embodiments, the system may be configured to: Generate visualization of the data and / or present it to healthcare professionals or patients via a GUI In some embodiments, at block 236, the system The plaques were classified into identified non-calcified or low-attenuating plaques, calcified or high-attenuating plaques, and total Based on one or more of the following: plaque, arteries, epicardial fat, and / or other The system can be configured to generate a suggested treatment plan for the disease, for example: In some embodiments, the system is adapted to treat arterial disease, renal artery disease, abdominal atherosclerosis, Generate treatment plans for vascular disease, carotid atherosclerosis, and / or other conditions The medical images analyzed may be configured to provide a medical image of the subject for analysis of such disease. The variance may be taken from any one or more regions of the

[0164] In some embodiments, one or more of the processes described herein in connection with FIG. 2B The process can be repeated, for example, if medical images of the same subject are taken again at a later time. If so, one or more of the processes described herein may be repeated, and the results of that analysis may be used to can be used for disease tracking and / or other purposes.

[0165] Additionally, in some embodiments, the system may perform a DECT or spectral CT scan. , can be configured to identify and / or determine non-calcified plaque. As with the process, in some embodiments the system may be DECT or Spectrum Access CT images and identify epicardial fat on DECT or spectral CT images. and / or segment one or more arteries on DECT images or spectral CT. and then performing a first set of pixel or region reduction or non-calcification pliers in the artery. and / or identify and / or classify as a first set of pixels in the artery. A second set of areas or regions are reduced or non-calcified plaques. However, unlike the techniques described above, e.g. In some embodiments, such as when DECT or spectral CT images are analyzed, The system must then perform a non-uniformity and / or homogeneity analysis of the second set of pixels. The second set of pixels may be configured to identify a subset of the second set of pixels without requiring the first set of pixels to be matched. Instead, in some embodiments, the system may be configured with, for example, DECT or or by utilizing the dual or multispectral aspects of spectral CT imaging. It can be configured to differentiate between blood and low-attenuation or non-calcified plaque directly from the image. In some embodiments, the system performs a first scan of the identified pixel or region. The set of pixels or regions identified as low attenuation or non-calcified plaques The whole set is identified on a medical image by combining a subset of the two sets. In some embodiments, DECT or Spectrum C Even when analyzing T images, the system performs the same steps as described above in connection with block 230. Similarly, the first step of a pixel or region can be performed by performing a heterogeneity or homogeneity analysis. The two sets can be configured for further analysis, e.g., DECT or Spectrum. Even when analyzing total CT images, in some embodiments, blood and / or The distinction between specific areas of low-attenuation or non-calcified plaque may not be complete and / or accurate. It's not necessary.

[0166] Imaging analysis-based risk assessment In some embodiments, the systems, devices, and methods described herein include Vascular events, major adverse cardiovascular events (MACE), rapid plaque progression, and / or uses medical image-based processing to assess a subject's risk for drug non-response. In particular, in some embodiments, the system is configured to utilize, for example, AI and and / or ML algorithms to analyze only non-invasively obtained medical images The subject's health risk can be automatically and / or dynamically assessed within minutes. It can be configured to provide a full image-based analysis report within minutes.

[0167] In particular, in some embodiments, the system may be configured to: Measure the total amount of plaque (and / or the amount of specific types of plaque) in your arteries. In some embodiments, the system can be configured to calculate the patient's malignant lesions within the arteries and / or throughout the entire arterial tract, covering part or all of the arteries In some embodiments, the total amount of plaque can be determined. The stem may be used to treat specific arteries and / or entire arterial areas of a patient, spanning some or all of their arteries. Based on the total amount of plaque in the blood, a particular patient is at risk of a heart attack or other cardiac event. The method can be configured to determine risk factors and / or diagnosis for a person suffering from a disease. Determined from the amount of "malignant" plaque or the relative amount of "malignant" and "benign" plaque Other risk factors that may be present include the rate of disease progression and / or the likelihood of ischemia. In some embodiments, the plaque can be measured by total volume (or cross-sectional imaging). by total vessel volume, total vessel length, or the area of ​​the myocardium facing the vessel. When normalized to the subtended myocardium, it can be measured by relative abundance. Cut.

[0168] In some embodiments, the coronary imaging data is used to measure atherosclerosis. In some embodiments, this information can include criteria for: The report covers the left and right ventricles, left and right atria, aortic, mitral, tricuspid, and pulmonary valves, aorta, pulmonary artery, and the pulmonary veins, coronary sinuses, and inferior and superior vena cava, epicardial or pericoronary fat , lung density, bone density, pericardial, and other quantitative characterizations of other cardiovascular diseases. As an example, in some embodiments, coronary artery The imaging data may be integrated with the left ventricular mass and the arteries it faces. The left ventricle can be segmented according to its volume and location. This combination of coronary artery information will determine whether a future heart attack will be large or small. As another example, in some embodiments, the coronary artery vascular body may be analyzed to improve prediction of the coronary artery vascular body. The product is a measure of left ventricular mass as a measure of left ventricular hypertrophy, which can commonly be found in hypertensive patients. Increased left ventricular mass (relative or absolute) may be associated with worsening disease. or uncontrolled hypertension. The onset, progression, and / or worsening of atrial fibrillation are related to atrial size, volume, and atrial free wall mass. This may be predicted by the size and thickness of the atria, the function of the atria, and the fat surrounding the atria. In some embodiments, these predictions are made using ML or AI algorithms or other algorithms. May be performed using rhythm types.

[0169] In succession, in some embodiments, atherosclerosis, stenosis, and vascular disease are The algorithms that allow for segmentation of the thoracic and thoracic structures are also used to segment other cardiovascular and thoracic structures. It serves as input to prognostic algorithms as well as enabling the quantification of In some embodiments, the output of a prognostic algorithm, or an image segment, The algorithms that allow for this may be used as inputs to other algorithms, Clinical decision-making may then be guided by predicting future events. By way of example, in some embodiments, atherosclerosis, stenosis, and / or Integrated scoring of vascular morphology identifies patients who may benefit from coronary revascularization, This may identify patients who achieve symptomatic relief and reduced risk of heart attack and death. As another example, in some embodiments, atherosclerosis, stenosis, and blood The integrated scoring of ductal morphology was evaluated in patients receiving lipid-lowering drugs (statins, PCSK-9 inhibitors, iPSCs, and iPSCs). Ethyl cosapentate, and others), Lp(a)-lowering drugs, antithrombotic drugs (clopidogrel, etc.), Benefit from certain types of medications, such as cefotaxime, rivaroxaban, and others In some embodiments, these algorithms may identify individuals who may be The predicted benefit of this study is based on the determination of the type of plaque progression (progression, disappearance) to reduce progression. , or mixed reaction), stabilization with medical therapy, and / or intensive therapy In some embodiments, the imaging data may be normal. There is no plaque now, but there is a high possibility that plaque will form in the future. This may be combined with other data to identify a range of

[0170] In some embodiments, automated or manual co-registration methods can be used to image segmentation. Combined with image-based data, two or more images can be compared over time. In some embodiments, comparison of these images allows for the detection of coronary atherosclerosis, narrowing, and other conditions. This allows for the determination of changes in vessel morphology over time, and is useful for risk prediction. can be used as an input variable to

[0171] In some embodiments, the present invention relates to atherosclerosis, stenosis, and vascular morphology. Coronary imaging data is combined with thoracic and cardiovascular disease measurements, or Without coupling, the coronary vessels are either ischemic or (either at rest or in hyperemic conditions) The algorithm determines whether the patient is indicative of a reduction in blood flow or blood pressure. can be combined.

[0172] In some embodiments, the present invention relates to coronary atherosclerosis, stenosis, and ischemia. The algorithm is implemented by a computer system and / or other can be modified to remove or "seal" the plaque. So, let's compare the results before and after the system removes or seals the plaque to see if any changes have occurred. For example, in some embodiments, the system can determine whether a coronary heart rate has increased. The present invention can be configured to determine whether vascular ischemia has been eliminated by sealing the plaque. Cut.

[0173] In some embodiments, coronary atherosclerosis, stenosis, and / or Characterization of vascular morphology was compared with a population-based cohort of patients undergoing similar scanning. When this is done, it may be possible to correlate a patient's biological age with their vascular age. For example, a 60-year-old patient may be equivalent to an average 70-year-old patient in a population-based cohort. In this case, the patient's vascular age is May be 10 years older than biological age.

[0174] In some embodiments, the risk enabled by the image segmentation prediction algorithm Risk assessment is the probability of illness or death in a person being considered for disability or life insurance. In this scenario, risk assessment can be performed in a more flexible manner than traditional actuarial methods. may replace or augment actual algorithms. stomach.

[0175] In some embodiments, the imaging data may be used to predict heart attack, stroke, death, rapid progression, or other life-threatening conditions. future adverse events such as thrombosis, non-response to medical therapy, no reflow phenomenon, and others. It may be combined with other data to enhance the risk assessment for the In some embodiments, other data may include multi-omics strategies, and algorithms may be used to Sequencing phenotypic data, genotypic data, proteomic data, transcriptomic data omics data, metabolomics data, microbiomics data, and / or activity and lifestyle as measured by a smartphone or similar device; Integrate with style data.

[0176] FIG. 3A shows an overview of an example embodiment of a method for risk assessment based on medical image analysis. 3A is a flowchart illustrating a system according to some embodiments. The system may be configured to access medical images at block 202. In some embodiments, the system may include, in block 204, one or more arteries and and / or configured to identify one or more plaque regions in block 206. Additionally, in some embodiments, the system may include, in block 208, or determining multiple vascular morphology and / or quantified plaque parameters, and / or block 210, determining one or more vascular morphologies and / or or quantified plaque parameters and / or their weighted criteria Block 20 can be configured to classify stable or unstable plaque. 2, 204, 206, 208, and 210, and additional information regarding processes and techniques. Details of can be found in the above description regarding FIG. 2A.

[0177] In some embodiments, the system may be classified, for example, as stable and / or unstable. The plaque area is used to estimate the risk of a cardiovascular event for the subject in block 302. , can be automatically and / or dynamically determined and / or generated. In some embodiments, the system utilizes AI, ML, or other algorithms. Based on the image analysis, block 302 determines whether a cardiovascular event, MACE, or plaque acute This can create a risk of rapid progression and / or non-response to medication.

[0178] In some embodiments, at block 304, the system may Number of vascular morphological parameters, quantified plaque parameters, and / or classification stable vs. unstable plaques, and / or their volumes, ratios, and / or other factors. The values ​​of the coronary artery parameters were compared with one or more previously determined values ​​derived from one or more other subjects. The method may be configured to compare one or more known data sets. The sample includes healthy subjects and / or subjects with various risk levels. One or more vascular morphological parameters derived from medical images taken from other subjects data, quantified plaque parameters, and / or classified stable vs. unstable plaques Lark, and / or its volume, ratio, and / or other values. For example, one or more known data sets of coronary artery values ​​are locally publicly accessible and / or remotely accessible by the system via a network connection The coronary artery values ​​may be stored in a coronary artery values ​​database 306, which may be accessible to the public.

[0179] In some embodiments, at block 308, the system Update the risk of cardiovascular events for subjects based on comparisons to the dataset For example, based on the comparison, the system may be configured to In some embodiments, the system may compare the risk assessment. In some embodiments, the previously generated risk assessment may be maintained even after the , the system generates and / or updates coronary artery values ​​after comparison with a known dataset. and generating a treatment recommendation for the subject based on the risk assessment. can be done.

[0180] In some embodiments, at block 310, the system extracts one or more Further identifying a plurality of other cardiovascular structures and / or one or more associated therewith. The method may be configured to determine one or more parameters. For example, one or more Additional cardiovascular structures include the left ventricle, right ventricle, left atrium, right atrium, aortic valve, mitral valve, tricuspid valve, pulmonary valve, aorta, pulmonary artery, inferior and superior vena cava, epicardial fat, and / or The pericardium may be included.

[0181] In some embodiments, the parameters associated with the left ventricle include size, mass, volume, , shape, eccentricity, surface area, thickness, and / or other. In some embodiments, the parameters associated with the right ventricle include size, mass, volume, shape, , eccentricity, surface area, thickness, and / or others. In the left atrium, the parameters associated with it are size, mass, volume, shape, eccentricity, and surface area. , thickness, pulmonary vein angulation, atrial appendage morphology, and / or others. In some embodiments, the parameters associated with the right atrium include size, mass, volume, shape, This may include eccentricity, surface area, thickness, and / or others.

[0182] Additionally, in some embodiments, the parameters associated with the aortic valve include thickness, volume, , mass, calcification, 3D map of calcification and density, eccentricity of calcification, segmentation by individual valve leaflet In some embodiments, the mitral valve may be associated with The parameters included were thickness, volume, mass, mineralization, and a three-dimensional map of mineralization and density. , eccentricity of calcification, classification by individual valve leaflet, and / or others. In some embodiments, the parameters associated with the tricuspid valve include thickness, volume, mass, calcification, and the like. 3D maps of calcification and density, eccentricity of calcification, classification by individual valve leaflets, and / or Additionally, in some embodiments, a pulmonary valve associated The parameters measured are thickness, volume, mass, mineralization, three-dimensional maps of mineralization and density, This may include eccentricity of calcification, classification by individual leaflet, and / or others.

[0183] In some embodiments, the parameters associated with the aorta include dimensions, volume, diameter, In some embodiments, the area, enlargement, protrusion, and / or other features may be included. ,The parameters associated with the pulmonary arteries are dimension, volume, diameter, area, hypertrophy, protrusion, and In some embodiments, the inferior vena cava and the superior vena cava may be included. The parameters associated with the dimension, volume, diameter, area, hypertrophy, protrusion, and / or It may include others.

[0184] In some embodiments, parameters associated with epicardial fat include volume, density, triglyceride, and erythrocyte sedimentation. In some embodiments, the pericardium and The associated parameters may include thickness, mass, and / or others.

[0185] In some embodiments, at block 312, the system may further include other identified cardiovascular structures. one or more of the parameters, e.g., using the determined parameter or parameters. In some embodiments, other identified cardiac For one or more of the ductal structures, the system may detect normal versus abnormal, increasing or decreasing levels over time. and / or are configured to classify each as being static or dynamic. It can be achieved.

[0186] In some embodiments, at block 314, the system may further include a determined number of other cardiovascular structures. One or more of the parameters obtained were compared with cardiovascular parameters derived from one or more other subjects. may be configured to compare structural parameters to one or more known data sets One or more known data sets of cardiovascular structural parameters can be compared with other cardiovascular structures. The parameter may include any one or more of the parameters described above associated with the structure. In some embodiments, the cardiovascular structural parameters of one or more known data sets are Data are collected from other subjects, including healthy subjects and / or subjects at various risk levels. In some embodiments, the cardiovascular structural parameters can be derived from medical images taken from One or more known data sets of the meter are locally accessible by the system. and / or be remotely accessible by the system via a network connection. The cardiovascular structure values ​​or cardiovascular disease (CVD) database 316 may be stored in the It is possible.

[0187] In some embodiments, at block 318, the system measures one of the cardiovascular structural parameters. A cardiovascular event profile for a subject based on a comparison to one or more known datasets. The system can be configured to update the risk of the system based on the comparison. The system may increase or decrease a previously generated risk assessment. In this case, the system may maintain the previously generated risk assessment even after the comparison.

[0188] In some embodiments, at block 320, the system may include: One or more other plaques identified from vulnerable plaques, arteries, and / or other Quantified color matrix analysis, which can include color coding for cardiovascular structures. In some embodiments, block 322 may be configured to generate a The system generates and / or compares the cardiovascular structural parameters with known data sets. or to generate treatment suggestions for subjects based on updated risk assessments. It can be configured as follows.

[0189] In some embodiments, at block 324, the system extracts one or more Further identifying multiple non-cardiovascular structures and / or one or more associated The medical image may be configured to determine a number of parameters. For example, the medical image may include a field of view, In particular, one or more non-cardiovascular structures may be present within the Cardiovascular structures can include lungs, bones, liver, and / or others.

[0190] In some embodiments, the parameters associated with the non-cardiovascular structure include volume, surface area, , volume to surface area ratio or function, non-uniformity of radiodensity values, radiodensity values, geometric shape ( elliptical, spherical, and / or other), spatial radiation density, spatial scar ng), and / or others. Additionally, in some embodiments, pulmonary The parameters associated with the may include density, scar, and / or other For example, in some embodiments, the system detects low house fluid pressure in certain areas of the lung. In some embodiments, the field unit can be configured to correlate with emphysema. Parameters associated with bones such as the spine and / or ribs include radiodensity, fracture severity, and It can include the presence and / or degree, and / or others. For example, some In some embodiments, the system measures low Hounsfield units in bony regions. In some embodiments, the liver may be associated with osteoporosis. and associated parameters analyzed liver Hounsfield unit density and / or non-alcoholic beverages that can be evaluated by the system by comparing them with It can include density of fatty liver disease.

[0191] In some embodiments, at block 326, the system one or more of the parameters, e.g., using the one or more determined parameters; In some embodiments, the identified non-cardiac structures can be configured to classify For one or more of the structures, the system may detect normal versus abnormal, increasing or decreasing, over time. are configured to classify each as decreasing and / or static or dynamic. It is possible.

[0192] In some embodiments, at block 328, the system One or more parameters were compared with non-cardiovascular parameters derived from one or more other subjects. For comparison with one or more known data sets of structural parameters or non-CVD values One or more of the non-cardiovascular structural parameters or non-CVD values ​​may be used. A number of known data sets are available for any of the above parameters associated with noncardiovascular structures. In some embodiments, one or more Non-cardiovascular structural parameters or non-CVD values ​​of known datasets are obtained from healthy subjects and and / or derived from medical images taken from other subjects, including subjects at various risk levels In some embodiments, non-cardiovascular structural parameters or non-CVD values ​​can be obtained. one or more known data sets are locally accessible by the system; and / or be remotely accessible by the system via a network connection and can be stored in a non-cardiovascular structural value or non-CVD database 330. .

[0193] In some embodiments, at block 332, the system may measure non-cardiovascular structural parameters or Based on comparison to one or more known datasets of CVD or non-CVD values, The risk of a cardiovascular event can be updated for a patient. Based on the comparison, the system may increase or decrease the previously generated risk assessment. In some embodiments, the system may retain the previously generated risk assessment even after the comparison. The value may be maintained.

[0194] In some embodiments, at block 334, the system One or more noncardiac structures, as well as medical images, stable plaque, unstable plaque, and vascular Color coding for the pulse, and / or other cardiovascular structures identified from other can be configured to generate a quantified color map, which may include In some embodiments, at block 336, the system calculates the non-cardiovascular structural parameters or a list generated and / or updated after comparison with a known dataset of non-CVD values. The method may be configured to generate a suggested treatment for the subject based on the assessment. do.

[0195] In some embodiments, one or more of the processes described herein in connection with FIG. 3A are The process can be repeated, for example, if medical images of the same subject are taken again at a later time. If so, one or more of the processes described herein may be repeated, and the results of that analysis may be used to to track the subject's risk assessment based on the imaging process, and / or for other purposes. It is possible.

[0196] Quantification of atherosclerosis In some embodiments, the system may include a computer-aided manufacturing process (CDM) for manufacturing medical imaging systems. Analyze one or more arteries to automatically and / or In some embodiments, the system is configured to dynamically quantify atheroma. It is designed to quantify atherosclerosis as a progression of the underlying disease, while stenosis and / or Prior to the embodiments described herein, manual processing was The process takes a long time and requires a lot of manpower to complete the process, which can take 4-8 hours or more. In contrast, in some embodiments, quantification of the underlying disease is not feasible. ,The system is about 1 minute, about 2 minutes, about 3 minutes, about 4 minutes, about 5 minutes, about 6 minutes, about 7 minutes, about 8 minutes, about 9 minutes, approx. 10 minutes, approx. 11 minutes, approx. 12 minutes, approx. 13 minutes, approx. 14 minutes, approx. 15 minutes, approx. 20 minutes, approx. 2 Atherosclerotic activity in less than 5 minutes, about 30 minutes, about 40 minutes, about 50 minutes, and / or about 60 minutes One or more of the following may be used to segment, identify, and / or quantify atherosclerosis: Medical imaging and / or imaging using multiple AI, ML, and / or other algorithms configured to quantify atherosclerosis based on analysis of CT scans In some embodiments, the system performs a time flow defined by two of the above values. In some embodiments, the method is configured to quantify atherosclerosis. In this mode, the system is configured to calculate stenosis rather than simply visually assess it. This allows users to better understand the overall cardiac atherosclerosis, The calculated results of stenosis are the same when the same medical images are used for analysis. Importantly, the type of atherosclerosis can also be determined by this method. The types of atherosclerosis can be quantified and / or classified by: Dichotomously (calcified vs. non-calcified plaque), sequentially (dense calcified plaque, calcified plaque, fibrous plaque, fibrofatty plaque, necrotic core, or mixed plaque types), or continuously (e.g., by attenuation density on the Hounsfield unit scale). It is possible.

[0197] Figure 3B shows the ability to quantify and / or characterize atherosclerosis based on medical image analysis. 3B is a flowchart illustrating an overview of an example embodiment of a similar method. In some embodiments, the system may measure, in block 202, the C of the coronary artery region of the subject. It can be configured to access medical images such as T-scans. In this embodiment, the system may select one or more arteries and / or The method may be configured to identify one or more plaque regions in block 206. Additionally, in some embodiments, the system may include, in block 208, one or Configured to determine multiple vascular morphology and / or quantified plaque parameters For example, in some embodiments, the system may perform the following steps in block 201: The geometry and / or volume of the plaque and / or vessel region are determined in block 203 In block 205, the ratio or function of the volume to surface area of ​​the plaque area is calculated. The heterogeneity or homogeneity index of the region is calculated in block 207 by comparing the radiodensity of the region of the plaque and and / or the composition by range of radioactivity concentration values, in block 209, and / or the radiodensity to volume ratio of the area of ​​the plaque in block 211. The blocks 202, 204, 206, and 207 may be configured to determine the spreading factor. 8, 201, 203, 205, 207, 209, and 211, and Additional details regarding the technique can be found in the above description regarding FIG. 2A.

[0198] In some embodiments, the system comprises: and / or based on the quantified plaque parameters, in block 340, The present invention can be configured to quantify and / or classify arteriosclerosis. In an embodiment, the system includes a single or multiple vascular morphological parameters and / or quantified plaque parameters It can be configured to generate weighted criteria. For example, in some implementations In this embodiment, the system may measure one or more vascular morphological parameters and / or quantified It can be configured to weight the plaque parameters equally. In embodiments, the system may measure one or more vascular morphological parameters and / or quantification. can be configured to weight differently the plaque parameters In some embodiments, the system comprises one or more vascular morphological parameters and and / or quantified plaque parameters logarithmically, algebraically, and / or differently The weighting may be configured using a mathematical transformation. In block 340, the system uses the weighted criteria to determine and / or Only some of the vascular morphological parameters and / or plaque parameters were quantified. configured to quantify and / or classify atherosclerosis using .

[0199] In some embodiments, the system may include one or more medical images derived from medical images of other subjects. or multiple known vascular morphological parameters and / or quantified plaque parameters. By comparing the data, one or more vascular morphological parameters and / or It is configured to generate weighted measures of quantified plaque parameters. For example, one or more known vascular morphological parameters and / or quantified planar The network parameters are measured in one or more healthy subjects and / or subjects at risk for coronary vascular disease. This can be derived from subjects who are at risk.

[0200] In some embodiments, the system provides a method for determining atherosclerosis based on the quantified atherosclerosis. The subjects' atherosclerosis was classified as high, medium, or low risk. In some embodiments, the system is configured to classify the Quantified atheroma using AI, ML, and / or other algorithms The method is configured to classify the subject's atherosclerosis based on the arteriosclerosis. In some embodiments, the system comprises: a volume-to-surface area analysis of one or more regions of plaque; The ratio, volume, heterogeneity index, and radioactivity concentration can be combined to and / or weighting to classify the subject's atherosclerosis. It is configured as follows.

[0201] In some embodiments, a proton pump with a small volume to surface area ratio or a small absolute volume may be used. LARC can indicate that the plaque is stable. In this embodiment, the system detects a volume-to-surface area ratio of a plaque region that is less than a predetermined threshold value, thereby determining whether the volume-to-surface area ratio of the plaque region is low. The method can be configured to determine whether the blood pressure is indicative of atherosclerosis of the arteries. Thus, in some embodiments, the system may take into account the number and / or surface of the plaques. For example, a larger number of plaques with smaller surfaces can be accommodated. If present, it can be associated with a larger surface area or greater irregularity. This in turn can be associated with a larger surface area to volume ratio. If there are fewer plaques with a thicker surface or greater regularity, the surface area will be smaller. This can be related to a surface area to volume ratio or a larger surface area to volume ratio. Morphologically, high radiodensity values ​​indicate that the plaque is highly calcified or stable. A low radiodensity value indicates a low or unstable plaque. Therefore, in some embodiments, the system may be configured to The radiodensity of the plaque area, which is in excess of the value, indicates low-risk atherosclerosis. In some embodiments, the low non-uniformity or Plaques with high homogeneity can indicate that the plaque is stable. Therefore, in some embodiments, the system detects defects in plaque areas that are below a predetermined threshold. Constructing to determine that uniformity indicates low risk of atherosclerosis. can be done.

[0202] In some embodiments, at block 342, the system quantified and / or classified the number of coronary artery stenoses based on atherosclerosis In some embodiments, the method is configured to calculate or determine a value calculation or expression. The system uses one or more blood vessels derived from medical images of the subject's coronary artery region. Stenosis using morphological parameters and / or quantified plaque parameters It is configured to calculate

[0203] In some embodiments, at block 344, the system and assessing the risk of ischemia in the subject based on the quantified and / or classified atherosclerosis. In some embodiments, the system is configured to predict coronary heart disease of the subject. One or more vascular morphological parameters and / or or configured to calculate ischemic risk using quantified plaque parameters will be done.

[0204] In some embodiments, the system uses image processing algorithms and techniques to Quantification and / or analysis, both automatically and / or dynamically derived from processed medical images. based on atherosclerosis, stenosis, and / or ischemic risk, and generating a suggested treatment for the subject.

[0205] In some embodiments, one or more of the processes described herein in connection with FIG. 3A are The process can be repeated, for example, if medical images of the same subject are taken again at a later time. If so, one or more of the processes described herein may be repeated, and the results of that analysis may be used to to track quantified atherosclerosis in subjects and / or for other purposes. It can be used.

[0206] Quantification of plaque, stenosis, and / or CAD-RADS score As discussed herein, in some embodiments, the system may be used to interpret medical images. The percentage of stenosis, atherosclerosis, and stenosis as derived from medical images are estimated. Atherosclerosis and / or Coronary Artery Disease - Reporting and Data System (CAD-R) ADS) score. As such, in some embodiments, the system is configured to: and / or by providing comprehensive quantitative analysis that can improve reproducibility. This can improve the reading of the imaging device.

[0207] Figure 3C shows the quantification of stenosis and the generation of CAD-RADS scores based on medical image analysis. 3A is a flowchart illustrating an overview of an example embodiment of a method for making In some embodiments, the system accesses the medical image at block 202. The type of medical image, as well as other information represented by block 202, can be configured to: Additional details regarding this process and technique can be found in the above description regarding FIG. 2A. can.

[0208] In some embodiments, at block 354, the system may use, for example, AI, ML, and and / or other algorithms to identify one or more arteries, plaques, or vein structures in a medical image. The device is configured to identify one or more arteries, plaques, and / or fat. The processes and techniques for identifying the keratinocytes and / or fat are described in blocks 204 and 206. It may include one or more of the same features as described above with respect to In some embodiments, the system may be configured to measure blood flow to, for example, the coronary arteries, carotid arteries, aorta, renal arteries, lower extremity arteries, and / or one or more arteries, including the cerebral arteries, with one or more AIs and and / or ML algorithms to automatically and / or dynamically identify In some embodiments, one or more AIs and / or The ML algorithm applies convolutional neural networks to a set of medical images in which arteries are identified. It can be trained using neural networks (CNNs), which allows for AI and / or ML algorithms will be able to automatically identify arteries directly from medical images. In some embodiments, arteries are identified by size and / or location.

[0209] Additionally, in some embodiments, the system may include, for example, one or more AIs and and / or using ML algorithms to automatically identify one or more plaque regions. and / or dynamically identify one or more plaque regions in a medical image. In some embodiments, one or more AIs and / or Or the ML algorithm can be used to measure a set of medical images in which plaque regions have been identified. It can be trained using a convolutional neural network (CNN), which AI and / or ML algorithms automatically identify plaque areas directly from medical images. In some embodiments, the system may include a medical image. For each coronary artery, the system can be configured to identify the vessel wall and lumen wall. In some embodiments, the system then calculates the volume between the vessel wall and the lumen wall. In some embodiments, the system is configured to determine the The plaques commonly associated with plaque were analyzed with or without normalization using a normalization device. By setting a predetermined threshold or range of radiation density values ​​that are generally considered to be plaque, and identifying plaque regions based on associated radiation density values. can.

[0210] Similarly, in some embodiments, the system may include, for example, one or more AIs and and / or using ML algorithms to automatically and / or or dynamically identify one or more fat regions, such as epicardial fat, in a medical image. In some embodiments, one or more A The I and / or ML algorithms are run against a set of medical images in which fat regions have been identified. It can be trained using a convolutional neural network (CNN), This allows AI and / or ML algorithms to automatically identify fat areas directly from medical images. In some embodiments, the system may, for example, Radiation densities commonly associated with fat were measured with or without normalization using a chair. By setting a predetermined threshold or range of intensity values, radiation commonly associated with fat can be detected. The method may be configured to identify fatty regions based on radiation density values.

[0211] In some embodiments, the system may include, at block 208, It can be configured to determine plaque status and / or quantified plaque parameters. For example, in some embodiments, the system may include, in block 201, and / or the geometry and / or volume of the region of the blood vessel, in block 203, The volume to surface area ratio or function of the area of ​​the plaque is calculated in block 205 as a function of the heterogeneity of the area of ​​the plaque. Alternatively, the uniformity index may be calculated in block 207 by measuring the radiodensity of the area of ​​the plaque, and / or The composition is determined by the range of radiodensity values, and in block 209, the radiodensity of the plaque region is calculated. Determine the ratio of the density to the volume and / or the diffusivity of the area of ​​the plaque in block 211. Blocks 208, 201, 203, 205, 207, Additional details regarding the processes and techniques represented by 209 and 211 are provided in relation to Figure 2A. This can be found in the above description.

[0212] In some embodiments, at block 358, the system may One or more vascular morphological parameters and / or quantified parameters derived from the images Calculate or calculate a numerical representation of coronary artery stenosis based on the plaque parameters In some embodiments, the system is configured to determine from the raw medical image. Determined and / or derived one or more vascular morphological parameters and / or can be configured to generate weighted criteria for quantified plaque parameters For example, in some embodiments, the system may include one or more vascular The morphological and / or quantified plaque parameters were weighted equally. In some embodiments, the system may be configured to include one or more Differentially weighted vascular morphological parameters and / or quantified plaque parameters In some embodiments, the system may be configured to find one or more or multiple vascular morphological parameters and / or quantified plaque parameters. Configure weighting numerically, algebraically, and / or using other mathematical transformations. In some embodiments, the system may perform weighted using established criteria and / or vascular morphological parameters and / or quantified It is configured to calculate stenosis using only some of the plaque parameters. In some embodiments, the system may be configured to calculate stenosis on a vessel-by-vessel or region-by-region basis. It can be configured as follows.

[0213] In some embodiments, based on the calculated stenosis, the system performs the step of block 360 This is designed to determine the CAD-RADS score, which is also important for preventing irreproducible results. CAD-RAD based on a physician's visual or general evaluation of medical images, which may result in This is in contrast to existing methods for determining S. However, some of the methods described herein In this embodiment, the system performs image processing based on automatic and / or dynamic image processing of raw medical images. Based on this, we aim to generate a reproducible and / or objective calculated CAD-RADS score. It can be configured as follows.

[0214] In some embodiments, at block 362, the system One or more quantified plaque parameters derived from the images and / or The system may be configured to determine the presence or risk of ischemia based on vascular morphological parameters. For example, in some embodiments, the system may perform weighted or unweighted by combining one or more of the above parameters first, or Some or all of these parameters can be used individually to determine the presence or risk of ischemia. In some embodiments, the system may be configured to determine quantified stenosis, one or more quantified plaque parameters and / or blood One or more of the vascular morphology parameters may be measured, for example, in healthy subjects and / or cardiac subjects. known risk factors derived from medical images of other subjects, including subjects at risk for vascular events Comparison with a database of such parameters can determine the presence of ischemic risk. In some embodiments, the system can be configured to: It can be configured to calculate the presence or risk of ischemia by region.

[0215] In some embodiments, at block 364, the system determining one or more quantified parameters of fat for one or more fat regions; For example, in some embodiments, the system may be configured to Listed in connection with locks 208, 201, 203, 205, 207, 209, and 211 The methods discussed herein for deriving quantified parameters of plaque, such as those In particular, some In an embodiment, the system determines the volume, geometry, and / or shape of one or more fat regions in a medical image. determining one or more parameters of the fat, including shape, radiodensity, and / or other The present invention can be configured to determine the

[0216] In some embodiments, at block 366, the system determines whether a cardiovascular disease event occurs in the subject. or generating a risk assessment of the event. In this state, the generated risk assessment provides a risk score that indicates the subject's risk of coronary artery disease. In some embodiments, the system may include one or more vascular morphologies. Parameter, one or more quantified plaque parameters, one or more Quantified fat parameters, calculated stenosis, ischemic risk, CAD-RADS score Risk assessments can be generated based on the risk assessment, risk assessment, and / or other analyses. In some embodiments, the system measures one or more vascular morphological parameters of the subject, One or more quantified plaque parameters, one or more quantified Fat parameters, calculated stenosis, ischemic risk, and / or CAD-RADS score For example, some implementations can be configured to generate weighted criteria for the In an embodiment, the system is configured to equally weight one or more of the above parameters. In some embodiments, the system can be configured to One or more can be configured to be weighted differently. In an embodiment, the system may calculate one or more of these parameters logarithmically, algebraically, or and / or may be configured to weight using another mathematical transformation. In some embodiments, the system uses weighted criteria at block 366. and / or using only some of these parameters to assess the coronary heart rate of the subject. The method is configured to generate a risk assessment for a cardiac disease or cardiovascular event.

[0217] In some embodiments, the system may use the above parameters with or without weighting. By combining one or more of these parameters, or some of these parameters or all individually to prevent coronary artery disease or cardiovascular events in subjects In some embodiments, the system may be configured to generate a risk assessment of The system may measure one or more vascular morphological parameters, one or more quantified plaque parameters, one or more quantified fat parameters, calculated stenosis, ischemic risk, and / or CAD-RADS score, e.g., in healthy subjects from medical images of other subjects, including those at risk for cardiovascular events By comparing with a database of known such parameters derived from coronary artery It can be configured to generate a risk assessment of a disease or cardiovascular event.

[0218] Furthermore, in some embodiments, the system may further include a step of: parameters, quantified plaque parameters of one or more plaque regions quantified coronary artery stenosis, presence or risk of ischemia determined, and / or based on one or more of the determined set of quantified fat parameters, CAD-RADS qualifiers can be configured to be generated automatically and / or dynamically. In particular, in some embodiments, the system may be configured to perform, for example, CAD-RADS As defined and used by the one or more of the subjects, including one or more of the following: Configured to automatically and / or dynamically generate applicable CAD-RADS qualifiers for For example, N can indicate that the test is non-diagnostic, S can indicate that the test is stenotic, and G can indicate the presence of a coronary artery bypass graft, V can indicate the presence of a coronary artery bypass graft can indicate the presence of vulnerable plaque, for example exhibiting low radiodensity values.

[0219] In some embodiments, the system uses image processing to derive the image from the raw medical image. a generated risk assessment of coronary artery disease, one or more vascular morphological parameters, One or more quantified plaque parameters, one or more quantified calculated fat parameters, calculated stenosis, risk of ischemia, CAD-RADS score, and and / or generate treatment suggestions for subjects based on CAD-RADS modifiers It can be configured as follows.

[0220] In some embodiments, one or more of the processes described herein in connection with FIG. 3B The process can be repeated, for example, if medical images of the same subject are taken again at a later time. If so, one or more of the processes described herein may be repeated, and the results of that analysis may be used to quantified plaque, calculated stenosis, CAD-RADS score, and / or The study included modifiers derived from medical images, determined ischemic risk, and quantified fat parameters. data, coronary artery disease risk assessments generated for subjects, and / or other purposes. can be used to

[0221] Disease Tracking In some embodiments, the systems, methods, and devices described herein are The progression and / or regression of arterial and / or plaque-based diseases, such as arterial disease For example, in some embodiments, the system can be configured to: Multiple medical images obtained at different times using one or more of the techniques discussed herein Automatically and / or dynamically analyze images and derive different parameters from them Comparison of the results can be used to track disease progression and / or resolution. Therefore, in some embodiments, the system provides a non-subjective evaluation method. Invasive raw medical images can be used as input to provide automated disease tracking tools. Cut.

[0222] In particular, in some embodiments, the system may be configured to detect whether plaque stabilization or deterioration is occurring. It can be configured to utilize a four-category system that determines what is happening to the subject. For example, in some embodiments, these categories include: (1) "plaque" (2) "mixed reaction - calcium predominant" or "non-acute" (3) "mixed reaction - non-calcium dominant" or "non-rapid non- (4) "calcium-dominant mixed reaction," or (5) "plaque disappearance."

[0223] In some embodiments, in the case of "plaque progression" or "rapid plaque progression," In some embodiments, the total or relative volume of the mixture increases. In the case of a "calcium-dominant" or "non-rapid calcium-dominant mixed reaction," the plaque volume remains relatively constant. Remains or does not increase to the threshold level for "rapid plaque progression" but calcifies There is an overall progression of plaque and an overall disappearance of non-calcified plaque. In the case of "mixed reaction - non-calcium dominant" or "non-rapid non-calcium dominant mixed reaction," In this case, plaque volume remains relatively constant or the overall progression of non-calcified plaque and total disappearance of calcified plaque. In some embodiments, "plaque disappearance" In this case, the total or relative volume of plaque is reduced.

[0224] In some embodiments, these four categories are, for example, higher density versus lower density categories. Calcium plaques (e.g., >1000 Hounsfield units vs. <1000 Hounsfield units) field-based) and / or calcium-dominated and expanded to more specifically categorize the mixed response into predominantly non-calcified plaque. For example, in the case of a mixed reaction with predominantly non-calcified plaque, further characterizes the necrotic core, fibrolipidic plaque, and / or fibrous plaque as non-calcified It can be included as a separate category within the overall umbrella of plaque. Plaques are classified into low-density calcified plaques, medium-density calcified plaques, and high-density calcified plaques. can be categorized as

[0225] FIG. 3D is a flow diagram illustrating an overview of an example embodiment of a method for disease tracking based on medical image analysis. For example, in some embodiments, the system may be configured to measure non-invasively obtained By analyzing one or more medical images, it is possible to detect atherosclerosis, stenosis, Plaque-borne diseases, such as coronary artery disease associated with ischemia and / or other The device may be configured to track the progression and / or resolution of a disease or symptom of the patient. do.

[0226] As shown in FIG. 3D, in some embodiments, the system may: A first set of plaque parameters derived from medical images of the subject at a first time point. In some embodiments, the medical image is configured to access a medical image The database 100 can store, for example, CT, non-contrast CT, contrast the above, including CT, MR, DECT, spectral CT, and / or others In some embodiments, the subject may have any of the types of medical images described above. The medical images of the subject's coronary artery area, coronary arteries, carotid arteries, renal arteries, abdominal aorta, cerebral arteries, In some embodiments, the plaque-like patch may be a plaque-like patch. The set of parameters is in blocks 208, 201, 203, 205, 207, 209, and and / or any of the quantified plaque parameters described above in relation to 211 The plaque parameters may be stored in a database 370. .

[0227] In some embodiments, the system may include a system for generating a medical image previously derived from the medical image and / or Alternatively, the plaque parameters stored in the plaque parameter database 370 may be used. In some embodiments, the first set of data can be directly accessed. The plaque parameter database 370 is locally accessible, and / or or can be remotely accessible by the system via a network connection In some embodiments, the system derives a plan from medical images taken from a first time point. Configure the first set of work parameters to be dynamically and / or automatically derived It is possible.

[0228] In some embodiments, at block 374, the system performs a first step of the plaque parameter a medical image set of a subject that can be obtained from the subject at a time later than the medical image set from which the medical image set of a subject was derived; In some embodiments, the second medical image may be configured to access the second medical image of the patient. Medical images can be stored in a medical image database 100, e.g., CT, non- Contrast CT, contrast-enhanced CT, MR, DECT, spectral CT, and / or It may include any of the types of medical images mentioned above, including others.

[0229] In some embodiments, at block 376, the system receives the second time point taken from the second time point. From the two medical images, a second set of plaque parameters is dynamically and / or automatically calculated. In some embodiments, the plaque parameter The second set includes blocks 208, 201, 203, 205, 207, 209, and and / or include any of the quantified plaque parameters described above in relation to 211 In some embodiments, the system may include derived or determined The second set of plaque parameters is stored in a plaque parameter database 370. It can be configured to store

[0230] In some embodiments, at block 378, the system The first set was derived from the images taken at a later time point, and the second set was derived from medical images taken at a later time point. Configured to analyze changes in one or more plaque parameters between two sets of For example, in some embodiments, the system may comprise, for example, one or The radiodensity, volume, geometry, location, volume-to-surface ratio, or is a function, heterogeneity index, radioconcentration composition, radioconcentration composition as a function of volume, radioconcentration the degree-to-volume ratio, the diffusivity, any combination or relationship thereof, and / or Other quantified plaque parameters can be compared between the two scans, such as In some embodiments, the system may include one or more pullers. Spatial mapping or three-dimensional histogram of radiation density values ​​across the geometry of the area. Determine heterogeneity indices for one or more plaque regions by generating a plaque profile. In some embodiments, the system may be configured to, for example, measure serum bioavailability. Markers, genetics, omics, transcriptomics, microbiomics, and and / or metabolomics, to analyze changes in one or more non-image-based metrics. It is configured to analyze

[0231] In some embodiments, the system provides a method for determining whether a plaque is stable or unstable. and determining changes in plaque composition between the two scans. In some embodiments, the system may further include a system for detecting high radiodensity or stable plaques versus low radiodensity plaques. Determine the change in the degree or percentage of vulnerable plaque between the two scans In some embodiments, the system is configured to: It can be configured to track changes in radiodense plaque between two scans. In some embodiments, the system can identify high radiodense plaques by dividing the high radiodense plaques into more than 1000 halves. Low radiodensity plaques are defined as having less than 1000 Houghfield units. It can be configured to define it as having field units.

[0232] In some embodiments, at block 380, the system generates a signal derived from two or more scans. Comparison of one or more parameters extracted and / or serum biomarkers , genetics, omics, transcriptomics, microbiomics, and / or Based on changes in one or more non-image-based metrics, such as metabolomics, Plaque progression or clearance, and / or any other relevant measurements, symptoms, or assessments For example, some experiments have been performed to determine the presence or absence of a specific disease. In an embodiment, the system may be configured to measure the progression and / or disappearance of plaque in general, atherosclerosis, configured to determine the risk or presence of hypertension, stenosis, ischemia, and / or other Furthermore, in some embodiments, the system may generate a medical image derived from two medical images. Based on the quantified or calculated stenosis, such as The S-score can be configured to be generated automatically and / or dynamically. Further details regarding the generation of RADS scores are described herein in connection with FIG. 3C. In some embodiments, the system determines the subject's CAD-RADS score. In some embodiments, the system may be configured to determine progression or disappearance. The system measures plaque parameters individually and / or in combination with one or more of them. The numbers can be combined as weighted criteria and configured for comparison. For example, in some embodiments, the system may analyze plaque parameters uniformly, as well as differently. weighted logarithmically, algebraically, and / or using other mathematical transformations, In some embodiments, the system may be configured to: · It can be configured to use only some or all of the parameters.

[0233] In some embodiments, the plaque progression status as determined by the system is Rapid progression of calcium-dominated, non-rapid mixed calcium-dominated, non-rapid non-calcium-dominated, or The results can include one of four categories, including plaque disappearance or plaque disappearance. In one embodiment, the system detects a subject's atheroma volume increase percentage exceeding 1% per year. In this case, the plaque progression state is classified as rapid plaque progression. In an embodiment, the system is configured to detect a subject's atheroma volume increase percentage of less than 1% per year. and plaque progression is considered when calcified plaque represents more than 50% of the total new plaque formation. The proposed method is designed to classify the state of the reaction as a non-rapid calcium-dominated mixed reaction. In an embodiment, the system detects a subject's atheroma volume increase percentage of less than 1% per year. If non-calcified plaque represents more than 50% of the total new plaque formation, plaque progression is considered. The method is designed to classify the condition as a non-rapid non-calcium dominated mixed reaction. In an embodiment, the system may be configured to: The method is configured to classify the plaque progression status as plaque disappearance.

[0234] In some embodiments, at block 382, ​​the system For example, in some embodiments, The system is based on the comparison of one or more parameters derived from two or more scans. The progression or disappearance of plaques determined based on the Suggested to a subject based on relevant measurements, symptoms, assessments, or related disorders It can be configured to generate a treatment plan.

[0235] In some embodiments, one or more of the processes described herein in connection with FIG. 3D For example, one or more of the processes described herein can be repeated. The analysis can be repeated and the results can be used for serial tracking of plaque-based disease and / or can be used for other purposes.

[0236] Determining the cause of calcium score changes In some embodiments, the systems, methods, and devices disclosed herein include Possible causes of an increased calcium score can be determined, analyzed, and / or reported. It can be configured to generate a notification only for high calcium scores or their increase. So, what does it mean to represent any particular cause, whether positive or negative? Rather, in general, various high calcium scores or increases in calcium levels are associated with various There may be a variety of possible causes, for example, in some cases a high calcium score or The increase indicates significant heart disease and / or an increased risk of heart attack in the patient. In some cases, a high or increasing calcium score may be an indicator of It may be an indicator that the patient is performing an increased amount of exercise (exercise is (This is because it can transform fatty plaques in arteries.) In some cases, A low or increased calcium score indicates the conversion of fatty plaque to calcium. Unfortunately, blood tests can be an indicator that a patient is beginning a statin treatment regimen. Using only the above, which of the reasons is the possible cause of the increased calcium score? In some embodiments, it is not possible to determine whether one or more of the methods described herein are used. By utilizing multiple techniques, the system can detect high or increasing calcium scores. The system can be configured to determine the cause of the increase.

[0237] More specifically, in some embodiments, the system is configured to detect fatty deposit material plaque lesions. The patient's arterial walls were monitored to monitor their transformation into near-calcified plaque deposits. This can be configured to track a particular segment in the to help determine the cause of the increased calcium score, such as one or more of the following: Additionally, in some embodiments, the system may be configured to detect one or more of the calcified plaques. determines and analyzes the location, size, shape, diffusivity, and / or attenuated radioactivity concentration of multiple regions and / or can be used to determine the cause of calcium score increases. As a non-limiting example, if calcium plaque density increases, this may indicate a need for treatment or may represent plaque stabilization due to lifestyle, but new calcium plaque If a cloud forms where it was not previously present (especially where the damping density is low), this can lead to a stable In some embodiments, the adverse findings described herein may represent a progression of the disease rather than progression. One or more of the processes and techniques described may be used in conjunction with non-contrast CT scans (ECG ECG-gated coronary calcium score or non-ECG-gated chest CT), as well as contrast It may also be applied to weighted CT scans (such as coronary CT angiograms).

[0238] As another non-limiting example, CT scan image acquisition parameters may be adjusted to track calcium changes over time. As an example, conventional coronary artery catheters can be modified to improve understanding of the mechanism of coronary artery disease. Calcium imaging was performed with a slice thickness of 2.5-3.0 mm and 130 Hz. This is done using detection voxels / pixels per field or more. An alternative is the slice thickness. Those performing "thin" slice imaging such as 0.5 mm, as well as those with a thickness of less than 130 mm Low density that may be missed by any 130 Hounsfield unit threshold All calcium levels exceeding a certain threshold (e.g., 100) can be identified. It may be to detect the Hounsfield unit density.

[0239] Figure 3E shows the relationship between calcium stimuli, whether increased or decreased, based on medical image analysis. 1 is a flowchart illustrating an overview of an example embodiment of a method for determining the cause of a change in a core.

[0240] As shown in FIG. 3E, in some embodiments, the system may: Subject's first calcium score and / or first set of plaque parameters First, calcium scores and / or The first set of plaque parameters is obtained from the subject's medical images and / or In some embodiments, the clinical benefit of a medical device may be derived from a blood test at one time point. The images can be stored in a medical image database 100, e.g., CT, non-contrast CT, contrast-enhanced CT, MR, DECT, spectral CT, and / or other The medical image data may include any of the types of medical images described above, including others. In this embodiment, the medical image of the subject is displayed on the coronary artery region, coronary arteries, carotid arteries, renal arteries, abdominal major arteries, and In some embodiments, the arteries may include the cerebral arteries, the lower limbs, and / or the upper limbs. The plaque parameters are set in blocks 208, 201, 203, 205, 20 7, 209, and / or 211, as described above, and the quantified plaque parameters The plaque parameter database 370 may contain any of the following data: It is possible.

[0241] In some embodiments, the system includes a calcium score database 398 and and / or a plaque parameter database 370, respectively. Direct access to the first set of calcium scores and / or plaque parameters The information may be configured to be stored and / or retrieved. In this state, the plaque parameter database 370 and / or calcium score The database 298 may be locally accessible and / or over a network connection. In some embodiments, the system may be remotely accessible. The system may acquire a medical image and / or blood test of the subject taken from a first time point. , a first set of plaque parameters and / or calcium scores, and and / or may be configured to be derived automatically.

[0242] In some embodiments, at block 386, the system performs a first step of the plaque parameter After the first calcium score and / or medical image was derived, a set of A second calcium score for the subject and / or a second calcium score that can be obtained from the subject at a time point The second medical image may be configured to be accessed. In this state, a second calcium score is obtained from a second medical image taken of the subject at a second time point. and / or can be derived from a second blood test. The second calcium score can be stored in the calcium score database 398. In some embodiments, the medical images are stored in a medical image database 100. For example, CT, non-contrast CT, contrast-enhanced CT, MR, DEC Any of the medical imaging types mentioned above, including CT, spectral CT, and / or others It may include:

[0243] In some embodiments, at block 388, the system generates a first calcium score. The calcium score is compared to the second calcium score and the change in calcium score is determined. However, as mentioned above, this alone generally does not It does not provide insight into the causes of any changes in the system score. In some embodiments, a statistically significant change in calcium score between the two readings was observed. If not, for example, if there is a difference but it is below a predetermined threshold, the system In some embodiments, the analysis of the score change can be configured to terminate. , for example, if there is a statistically significant change in calcium score between the two readings. If the difference exceeds a predetermined threshold, the system can be configured to continue the analysis. can be done.

[0244] In particular, in some embodiments, at block 390, the system A second set of plaque parameters is dynamically and / or automatically calculated from the second medical image. In some embodiments, the plaque parasite can be dynamically detected. The second set of meters is comprised of blocks 208, 201, 203, 205, 207, 209, and / or any of the quantified plaque parameters described above in relation to 211 In some embodiments, the system may include a derived or determined The second set of plaque parameters was stored in the plaque parameter database 3. It can be configured to store up to 70

[0245] In some embodiments, at block 392, the system The first set was derived from the images taken at a later time point, and the second set was derived from medical images taken at a later time point. Configured to analyze changes in one or more plaque parameters between two sets of For example, in some embodiments, the system may comprise, for example, one or is a region of a plurality of plaques and / or one or more regions surrounding the plaques, Radiation concentration, volume, geometry, location, volume-to-surface ratio or function, heterogeneity index, Radiation concentration composition, radiation concentration composition as a function of volume, radiation concentration to volume ratio, diffusivity, Any combination or relationship thereof, and / or otherwise, is quantified. Plaque parameters can be configured to be compared between the two scans. In some embodiments, the system comprises a system for measuring the overall geometry of one or more plaque regions. by generating a spatial mapping or three-dimensional histogram of radiation density values ​​over a and determining a heterogeneity index for one or more plaque regions. In some embodiments, the system can be configured to analyze, for example, serum biomarkers, genetics, omics, ics, transcriptomics, microbiomics, and / or metabolomics configured to analyze changes in one or more non-image-based metrics, such as .

[0246] In some embodiments, the system provides a method for determining whether a plaque is stable or unstable. and determining changes in plaque composition between the two scans. In some embodiments, the system may further include a system for detecting high radiodensity or stable plaques versus low radiodensity plaques. Determine the change in the degree or percentage of vulnerable plaque between the two scans In some embodiments, the system is configured to: It can be configured to track changes in radiodense plaque between two scans. In some embodiments, the system can identify high radiodense plaques by dividing the high radiodense plaques into more than 1000 halves. Low radiodensity plaques are defined as having less than 1000 Houghfield units. It can be configured to define it as having field units.

[0247] In some embodiments, the system measures plaque parameters individually and / or Or combine one or more of them as weighted criteria and compare them. For example, in some embodiments, the system may be configured to · Parameters can be scaled uniformly, unequally, logarithmically, algebraically, and / or mathematically In some embodiments, the system may be configured to use a transformation to weight the signal. The system can be configured to utilize only some or all of the quantified plaque parameters. It can be achieved.

[0248] In some embodiments, at block 394, the system may Based on a comparison of one or more plaque parameters, whether combined or weighted Based on this, it can be configured to characterize changes in calcium scores in a subject. In some embodiments, the system may be configured to provide a positive, neutral, or negative For example, it can be configured to characterize changes in calcium scores. In some embodiments, by comparison of one or more plaque parameters, Overall, plaque stabilization was observed without any new plaque formation. or high radiation concentration values, the system A change in score can be reported as positive. In contrast, one or more By comparing the plaque parameters, for example, new unstable lesions with low radiodensity values ​​can be identified. The formation of a plaque area resulted in the formation of a plaque-free area in the entire subject without the formation of any new plaque. If the plaque becomes unstable, the calcium A change in score can be reported as negative. The stem may be any of the stems described herein, including those discussed in connection with Figures 3A, 3B, 3C, and 3D. Among the follow-up plaque quantification and / or plaque-based disease analysis discussed in this paper: , can be configured to utilize any or all of the techniques.

[0249] By way of non-limiting example, in some embodiments, the system may detect one or more Determining and comparing the change in the ratio between the volume and radiodensity of multiple plaque regions. Based on this, it can be configured to characterize the cause of changes in calcium scores. Similarly, in some embodiments, the system may include one or more Based on the determination and comparison of changes in diffusivity and / or radiodensity of the plaque region For example, it can be configured to characterize the cause of changes in calcium scores. For example, if the radiodensity of the plaque area is increased, the system will calculate the calcium score. A change or increase in the level of the signal can be characterized as positive. In some embodiments, the system generates one or more new images that were not present in the first image. If a plaque area is identified in the second image, the system will record a change in calcium score. Some implementations can be configured to characterize the conversion as negative. In this configuration, the system is configured to treat one or more plaque regions with a volume-to-surface area ratio of two skin If the system determines that the calcium score has decreased between scans, it will mark the change in calcium score as positive. In some embodiments, the The system may, for example, generate and / or analyze a spatial mapping of radiation concentration values. The heterogeneity or heterogeneity index of the plaque area decreased between the two scans. If the system determines that a change in calcium score is positive, It can be configured to determine sex.

[0250] In some embodiments, the system uses AI, ML, and / or other algorithms. Based on one or more plaque parameters derived from medical images, This is configured to characterize changes in calcium scores. In an embodiment, the system uses CNN and / or calcium scores and Use a dataset of known medical images in which plaque parameters have been identified to be combined. It can be configured to utilize AI and / or ML algorithms that are trained using In some embodiments, the system may include a database of calcium concentrations. Changes in calcium scores by accessing a known dataset of scores For example, the known data set can be configured to characterize other data sets in the past. Changes in calcium scores and / or medical images in subjects and / or The data set can include plaque parameters derived from the In this embodiment, the system may perform per vessel, per segment, per plaque, and / or characterize changes in calcium scores on a subject-by-subject basis and / or The system can be configured to determine the cause of the change.

[0251] In some embodiments, at block 396, the system For example, in some embodiments, The stem is based on the change in the subject's calcium score and / or its characterization. It can be configured to generate a suggested treatment plan for the subject.

[0252] In some embodiments, one or more of the processes described herein in connection with FIG. 3E are For example, one or more of the processes described herein can be repeated. The results of the analysis can be repeated to continuously track changes in the subject's calcium score. The compounds may be used for identification and / or characterization, and / or other purposes.

[0253] Prognosis of cardiovascular events In some embodiments, the systems, devices, and methods described herein Based on one or more of the medical image-based analysis techniques described in the specification, For example, in some embodiments, The system will provide cardiac support to patients based on the amount of malignant plaque buildup in their arteries. It is configured to determine whether or not there is a risk of a vascular event. Vascular events include heart attack, stroke, or death, as well as disease progression and / or ischemia. Clinical major cardiovascular events may be included.

[0254] In some embodiments, the system comprises: based on the ratio of the total surface area and / or volume of some or all of the patient's arterial vessels to In some embodiments, the risk of a cardiovascular event can be identified. If a certain threshold is exceeded, the system will identify specific risk factors and / or Alternatively, it may be configured to output a number and / or a level. In one embodiment, the system measures the volume of a patient's arteries compared to the total volume of some or all of the arterial vessels. Absolute amount or volume of malignant plaque accumulation in blood vessels, or percentage of accumulation or volume The method is configured to determine whether the patient is at risk for a cardiovascular event based on the In some embodiments, the system detects changes in blood chemistry or biomarkers from a patient's blood chemistry or biomarker test. Based on the results of the study, it can be determined whether a patient is at risk for a cardiovascular event, e.g. to determine whether blood chemistry or biomarker tests exceed certain threshold levels In some embodiments, the system is configured to: Receive as input and / or patient blood samples from the database system Configured to access fluid chemistry or biomarker test data. In this embodiment, the system may include a system for detecting plaque, vessel morphology, and / or stenosis-related movements. In addition to pulse information, the mass of the opposing left ventricle, the volume and size of the body cavity, valve morphology, blood vessels ( e.g., aorta, pulmonary artery) morphology, fat, and / or lung and / or bone health It is also designed to utilize input from other imaging data related to the non-coronary cardiovascular system, such as In some embodiments, the system can generate a risk profile using the output risk factors. For example, the system can generate treatment plan suggestions for soft malignant prostate cancer. To convert the plaque into a hard plaque that is safer and more stable for the patient, The method may be configured to output a treatment plan involving the administration of cholesterol-lowering drugs such as acetaminophen. Generally, hard, calcified plaques are at risk of rupturing at the border with the arterial blood vessels. This may significantly reduce the chance of blood clots forming in the arteries. The patient's risk of heart attack or other cardiac events may be reduced.

[0255] FIG. 4A shows a cardiac vascular assessment based on and / or derived from medical image analysis. 1 is a flow chart illustrating an overview of one embodiment of a method for prognosing a vascular event.

[0256] As shown in FIG. 4A, in some embodiments, the system may, in block 202: CT scans of the subject's coronary artery region, which may be stored in a medical image database 100. In addition, some embodiments may be configured to access medical images, such as In this embodiment, the system may include, in block 204, one or more arteries and / or blocks. The detector 206 can be configured to identify one or more plaque regions. Additionally, in some embodiments, the system may include, in block 208, one or more blood Configured to determine vessel morphology and / or quantified plaque parameters For example, in some embodiments, the system can the geometry and / or volume of the area, the volume-to-surface area ratio or function of the plaque area , heterogeneity or homogeneity index of the plaque area, radiodensity of the plaque area, and / or or its composition by range of radiodensity values, the radiodensity to volume ratio of the area of ​​the plaque, and / or can be configured to determine the diffusivity of the region of the plaque. Additionally, in some embodiments, at block 210, the system determines from the raw medical image: one or more determined and / or derived vascular morphological parameters and / or Based on the quantified plaque parameters, one or more plaque regions are identified as stable. Block 202 can be configured to classify the signal as stable versus unstable or good versus bad. Additional details regarding the processes and techniques represented in 204, 206, 208, and 210 Details can be found in the description above regarding Figure 2A.

[0257] In some embodiments, the system performs a malignant plaque vs. malignant plaque analysis at block 412. More specifically, some embodiments are configured to generate a ratio of blood vessels in which the blood vessels appear. In this system, the total surface area of ​​blood vessels identified on medical images is compared with the malignant potential within those vessels. or the surface area of ​​all regions of vulnerable plaque. Based on the above, in some embodiments, the system detects malignant plaque in a particular blood vessel. Generate a ratio of the total surface area to the surface area of ​​the entire blood vessel or a portion thereof shown in the medical image. Similarly, in some embodiments, the system may be configured to The total volume of the vessels identified on the image and the total volume of malignant or unstable plaque within those vessels Based on the above, some In an embodiment, the system calculates the volume of all malignant plaques in a particular blood vessel and the volume of malignant plaques shown in the medical image. The device can be configured to generate a ratio of the volume of the entire blood vessel or a portion thereof to the volume of the entire blood vessel.

[0258] In some embodiments, at block 414, the system further comprises: Determine the absolute total volume and / or surface area of ​​all malignant or vulnerable plaques Also, in some embodiments, at block 416, the system may Absolute detection of all plaques, including benign and malignant plaques, identified in the imaging Further, in some embodiments, block 418 is configured to determine a total volume relative to the total volume. The system will then monitor the results from the patient's blood chemistry and / or biomarker tests. access or obtain other non-imaging test results; Further, in some embodiments, at block 422, The system accesses one or more non-coronary cardiovascular medical images and / or can be configured to analyze it.

[0259] In some embodiments, at block 420, the system may measure the surface area or volume, malignancy, Absolute total plaque volume, absolute total plaque volume, blood chemistry and / or biomarkers Test results and / or analysis of one or more non-coronary cardiovascular medical images One or more of the resulting ratios of malignant plaque to vessels, regardless of whether they are due to Analyze the effects of one or more of these parameters, individually and / or in combination. Either of these may be configured to determine whether a predetermined threshold has been exceeded. For example, in some embodiments, the system may be used in healthy subjects and / or subjects with cardiovascular events. by comparing the results with one or more baseline values ​​for subjects at risk for the disease. One or more of the parameters can be configured to be analyzed individually. In some embodiments, the system may apply the combined or weighted criteria to a healthy One or more baseline values ​​for the subject and / or subjects at risk for a cardiovascular event By comparing with one or more of the above parameters, a weighted In some embodiments, the method may be configured to analyze a combination of criteria, etc. The system may be configured to weight one or more of these parameters equally. In some embodiments, the system may be configured to measure one or more of these parameters. can be configured to weight the multiple differently. In this case, the system may scale one or more of these parameters logarithmically, algebraically, and The weighting can be configured using other mathematical transformations and / or other methods. In some embodiments, the system may use only some of the above parameters, individually and in combination. , and / or can be configured to be utilized as part of a weighted criterion. .

[0260] In some embodiments, at block 424, the system may monitor a cardiovascular event for the subject. In particular, in some embodiments, the system is configured to generate a prognosis for the patient. surface area or volume, absolute total volume of malignant plaque, absolute total volume of plaque, blood chemistry and / or biomarker test results, and / or one or more non-coronary Whether it is based on the analysis of arterial and cardiovascular medical images, the difference between malignant plaque and vascular generating a prognosis for a cardiovascular event based on one or more of the results of the analysis of the generated ratios; In some embodiments, the system is configured to: or other algorithms to generate a prognosis. In an embodiment, the generated prognosis may be a risk score or risk assessment for a cardiovascular event for the subject. In some embodiments, the cardiovascular event includes atherosclerosis risk assessment. , stenosis, ischemia, heart attack, and / or other can.

[0261] In some embodiments, at block 426, the system For example, in some embodiments, The stem is based on the change in the subject's calcium score and / or its characterization. The system can be configured to generate a suggested treatment plan for the subject. In embodiments, the generated treatment plan may include statin use, lifestyle changes, and / or Or it may involve surgery.

[0262] In some embodiments, one or more of the processes described herein in connection with FIG. 4A are For example, one or more of the processes described herein can be repeated. The results of the analysis can be used to further prognose and / or assess the cardiovascular events of the subject. Or it can be used for other purposes.

[0263] Patient-specific stent determination In some embodiments, the systems, methods, and devices described herein are One or more guidelines regarding patient-specific stent and / or implantation selection or guidance In particular, one or more parameters may be used to determine and / or generate the In some embodiments, the systems disclosed herein are based on, for example, AI, ML, and specific patient data based on the processing of medical imaging data using algorithms and / or other algorithms The type, length, diameter, gauge, strength, and / or any other stent required for It can be used to dynamically and automatically determine any stent parameters. .

[0264] In some embodiments, if a stent that is too large is implanted, the arterial wall may stretch and This may result in excessive thinning, potential rupture, undesirable high flow rates, or other problems. Therefore, one or more patient-specific stent parametrizations are optimally suited to specific arterial areas. By determining the metric, the system can improve the patient's risk of complications and / or insurance risk. On the other hand, if a stent that is too small is implanted, it may cause damage to the arterial wall. may not fully advance and open, resulting in too little blood flow or other problems.

[0265] In some embodiments, the system dynamically identifies the extent of stenosis in the artery; Dynamically determining the appropriate diameter for the identified area of ​​the artery and / or The system is configured to automatically select a stent from a selection of available stents. In this embodiment, the selected stent is implanted and then placed in the proper arterial straight line to determine the extent of the artery. In some embodiments, the proper movement The diameter of the vessel is equal to or substantially equal to the diameter that would be natural in the absence of stenosis. In some embodiments, the system identifies the selected stent. The system can be configured to dynamically generate patient-specific surgical plans for implantation in selected arterial areas. For example, the system can determine whether an arterial branch is near an identified arterial region. Insert two guidewires to address the bifurcation and / or insert a second stent. Generate a patient-specific surgical plan to determine the location of the constrained insertion of the catheter into the bifurcation It can be configured as follows.

[0266] Figure 4B shows how to determine patient-specific stent parameters based on medical image analysis. 1 is a flowchart illustrating an overview of an example embodiment of the present invention.

[0267] As shown in FIG. 4B, in some embodiments, the system may, in block 202: It can be configured to access medical images, such as CT scans of the subject's coronary artery area. Additionally, in some embodiments, the system may include one or more Identifying a number of arteries and / or one or more plaque regions in block 206 Additionally, in some embodiments, the system may be configured to 208, one or more vascular morphology and / or quantified plaque parameters For example, in some embodiments, the system In block 201, the geometry and / or shape of the plaque and / or vessel area is determined. The volume is calculated in block 203 by calculating the ratio or function of the volume to surface area of ​​the plaque area in block 204. At block 205, a heterogeneity or homogeneity index of the plaque region is calculated, and at block 207, a plaque The radioactivity concentration of the area and / or its composition by the range of radioactivity concentration values, At 209, the radiodensity to volume ratio of the area of ​​the plaque is calculated, and / or at block 21 1, the diffusivity of the region of the plaque can be determined. , 204, 206, 208, 201, 203, 205, 207, 209, and 211 Additional details regarding the processes and techniques depicted can be found in the above description regarding FIG. 2A. It is possible.

[0268] In some embodiments, at block 440, the system analyzes the medical image to determine the diameter , curvature, vessel morphology, vessel wall, lumen wall, and / or other In some embodiments, the system may be configured to determine the vessel parameters. A system may be a single system, such as that shown in a medical image, with a stenosis in a specific area along a blood vessel. or a plurality of vascular parameters are determined or derived from the medical image. In some embodiments, the system may include one or more stenoses that are not present. For example, some embodiments may be configured to determine a number of vascular parameters. In this state, the system graphically and / or hypothetically removes stenosis or plaque from the blood vessel. to determine the diameter, curvature, and / or other characteristics of the vessel if no stenosis was present. The system can be configured to:

[0269] In some embodiments, at block 442, the system determines whether the stent is to be implanted in the subject. Determine whether or not a treatment is recommended and, if so, provide a treatment specific to the patient based on medical analysis. determining one or more recommended parameters of a desired stent; For example, in some embodiments, the system may If one of the following parameters is present: In some embodiments, the system may be configured to analyze one or more , and can be configured to utilize AI, ML, and / or other algorithms. In some embodiments, the system may calculate one or more of the above parameters by: configured to be analyzed individually, in combination, and / or as weighted criteria In some embodiments, one or more of these parameters derived from medical images or more, either individually or in combination, in subjects implanted with stents and One derived or collected from other subjects, including non-embedded subjects Alternatively, the patient may be compared to multiple reference values. Based on the determined parameters of the stent, the system selects a suitable stent that meets those parameters. Determine the selection of existing stents and / or select stents derived from medical images. Generate manufacturing instructions for manufacturing patient-specific stents with the patient parameters. In some embodiments, the system may be configured to: Recommend a stent diameter that is smaller than or substantially equal to the diameter of the artery in question. It can be configured as follows.

[0270] In some embodiments, at block 444, the system determines a medical image based on the analyzed medical image. can be configured to generate a recommended surgical plan for stent implantation using For example, in some embodiments, the system may determine whether bifurcations exist based on medical images. and / or provide guidewires and / or The system can be configured to generate guidelines for positioning the stent. Therefore, in some embodiments, the system may be used for medical image analysis of plaque and / or other Configured to generate detailed surgical plans specific to a particular patient based on parameters It is possible.

[0271] In some embodiments, at block 446, the system may or a plurality of medical images. In some embodiments, at block 448, the system analyzes the accessed medical images to , can be configured to perform post-implant analysis. For example, in some embodiments After the stent is implanted, the system performs the steps discussed herein in connection with block 208. one or more vascular morphology and / or plaque parameters, including any of Based on the above analysis, in some embodiments, The system may further provide, for example, recommendations for the use of statins or other medications, lifestyle changes, etc. In some embodiments, such as stent implantation, further surgery or stent implantation, and / or other A suggested treatment for the condition can be generated.

[0272] In some embodiments, one or more of the processes described herein in connection with FIG. 4B For example, one or more of the processes described herein can be repeated. The results of the analysis can be used to determine the need for further patient-specific stents for the patient. Use to determine the quality and / or parameters, and / or other purposes. can be done.

[0273] Patient-specific reporting In some embodiments, the system comprises a processor that processes the raw CT scan data. The system is configured to dynamically generate patient-specific reports based on analysis of the processed data. In some embodiments, patient-specific reports are dynamically generated based on the processed data. In some embodiments, the selection of specific phrases from a database and / or Reports are dynamically generated based on combinations of specific words, terms, and / or The phrases are modified to be specific to the patient and their identified medical problem. In some embodiments, the system processes image scanning data and / or Dynamically selecting one or more images from the system-generated image views described herein The selected image or images may be used in the analysis of the processed data. The data is dynamically inserted into the report to generate a patient-specific report based on the data.

[0274] In some embodiments, the system may include a selected one of the following for insertion into a patient-specific report: or configured to dynamically annotate a plurality of images, the annotations being patient-specific, and / or performed by the devices, methods, and systems disclosed herein. The annotation is based on data processing, e.g., prominent malignant plaque buildup along arteries. One should include markings or other indicators to show which position it is in. Or annotating multiple images.

[0275] In some embodiments, the system may perform a diagnostic test based on past and / or current medical data. For example, in some embodiments, the system may be configured to dynamically generate reports based on the is constructed to show how a patient's cardiovascular health has changed over time. In some embodiments, the system may monitor the cardiovascular health of the patient, as well as and / or to specifically describe how cardiovascular disease changes in the patient's body. Configured to dynamically generate phrases and / or select phrases from a database will be done.

[0276] In some embodiments, the system may include a method for determining how cardiovascular disease progresses over time in a patient. For example, showing past and present images juxtaposed against each other to show how things have changed, and For example, the system allows users to visualize the past and present by showing a past image superimposed on the current image. to allow you to move, fade or toggle between current images in the medical report. Insert one from your previous and / or current medical scan Alternatively, the apparatus may be configured to dynamically select a plurality of medical images.

[0277] In some embodiments, the patient-specific report includes specific images, videos, animations, etc. of the report. Features include: augmented reality (AR), virtual reality (VR), and / or user interaction with the In some embodiments, the system may also include an interactive report that allows for or specific vascular and / or vascular disease that may contain or be suspected of containing vascular disease requiring further analysis. Dynamically generated illustrations or drawings of the patient's arterial vessels to highlight or highlight portions of the vessels. In some embodiments, the image is dynamically inserted into a patient-specific report. The generated patient-specific report uses AR and / or VR to show the vessel wall to the user. It is configured to:

[0278] In some embodiments, the system is a system that is capable of performing the methods, systems, and devices disclosed herein. Use the device to dynamically generate any ratio and / or dynamically generated data In some embodiments, the dynamically generated report is configured to be inserted into the report. In some embodiments, dynamically generated reports include radiology reports. To enable you to compile the data, use an editable application such as Microsoft Word®. In some embodiments, the dynamically generated report is in the form of a document that can be accessed by a PACS (picture archiving system). The images are stored in a medical record (EMR) or other electronic medical record (EMR) system.

[0279] In some embodiments, the system is useful for any patient to improve literacy. data from imaging to accurately convey information in a way that is better understood by the patient into infographics in visual or visual format, with or without audio. In some embodiments, the system is configured to convert and / or translate the text. This method of improving is to reduce lower risks to higher literacy and higher risks to lower literacy. In some embodiments, this is coupled to a severity classification tool that defines the severity of the condition. These reporting outputs may be patient-derived and / or patient-specific. In this case, actual patient imaging data (e.g., from a patient CT) is used to derive the findings. To further illustrate this, graphics from the patient's CT and / or drawings from the CT are used. In some embodiments, actual patient imaging data, graphics, Graphic data and / or drawing data are not from the patient, but are explanatory graphics (e.g., fatty plastics) that can help consumers better understand It can be combined with other videos (videos related to the work).

[0280] In some embodiments, these patient reports include information about heart disease, such as diabetes or high blood pressure. Applications that allow tracking disease over time in relation to risk factor control In some embodiments, the app and / or user The interface allows you to follow blood glucose and blood pressure over time, and / or correlate changes in images over time in a manner that enhances risk prediction. can be done.

[0281] In some embodiments, the system generates processed data from the raw CT data. Based on the data, patient-specific video reports can be generated. In some embodiments, the system provides imaging findings, associated automated computational diagnoses, and and / or prognostic algorithms to automatically and dynamically change content. It can be programmed to create a personalized video viewing experience for the user. In some embodiments, the viewing method is configured to: Contrary to previous reports, this is through a visual experience that may be in the form of a regular 2D image, and / or Or through a mixed reality video experience using AR or VR. In both 2D and mixed reality, personalized video experiences interact with patients. to predict patient outcomes such as risk of heart attack, rate of disease progression, and / or ischemia. It is possible.

[0282] In some embodiments, the system may incorporate actual CT image data from the patient. Video reports containing both cartoon images and / or animations along with audio content In some embodiments, the dynamically generated The video medical report may use a voice synthesizer or pre-made audio content for playback during the video report. Select phrases, terms, and / or other terms from the database so that you can In some embodiments, the content is dynamically narrated. The resulting imaging medical report may be configured to include any of the images disclosed herein. In some embodiments, the dynamically generated imaging medical report may include a method for detecting cardiovascular disease in a patient's body. Previous medical scanning and / or Select one or more medical images from the current medical scan to be inserted into the video medical report. For example, in some embodiments, the report may be configured to: It is possible to show past and present images juxtaposed next to each other. In some cases, the report may show a previous image superimposed on the current image, thereby allowing the user to toggle or move or fade between the previous and current images. In some embodiments, the dynamically generated video medical report may include a Showing actual medical images, such as CT scans, followed by illustrations or cartoons of the actual medical images image (partially or completely illustrated or cartoon image) that allows the patient's arteries to be In some embodiments, dynamic The generated video medical report will use AR and / or VR to show the vessel walls to the user. It is configured as follows.

[0283] FIG. 5A illustrates a method for generating a medical report regarding patient characteristics based on medical image analysis. 5A is a flowchart illustrating an overview of an example embodiment. In this embodiment, the system is configured to access medical images at block 202. In some embodiments, the medical images are stored in a medical image database 100. The type of medical image, as well as other processes represented by block 202, can be stored. Additional details regarding the processes and techniques can be found in the above description regarding FIG. 2A.

[0284] In some embodiments, at block 354, the system may use, for example, AI, ML, and and / or other algorithms to identify one or more arteries, plaques, or vein structures in a medical image. The medical image type and block type are configured to identify blood vessels, blood vessels, and / or blood vessels. Additional details regarding other processes and techniques represented in block 354 are provided above with respect to FIG. 3C. This can be found in the above description.

[0285] In some embodiments, at block 208, the system detects one or more vascular morphologies. and / or can be configured to determine quantified plaque parameters For example, in some embodiments, the system may include, in block 201, and / or the geometry and / or volume of the blood vessel area, in block 203, of the plaque. The volume to surface area ratio or function of the region is used to measure the heterogeneity or The uniformity index is calculated in block 207 based on the radiodensity and / or radioactivity of the area of ​​the plaque. The composition is determined by the range of radiodensity values ​​in block 209. and / or determining the diffusivity of the area of ​​the plaque in block 211. Blocks 208, 201, 203, 205, 207, and 208 can be configured to Additional details regarding the processes and techniques represented by 09 and 211 are provided in the section regarding Figure 2A. This can be found in the above description.

[0286] In some embodiments, at block 508, the system sclerosis, risk of ischemia, risk of cardiovascular events or disease, and / or other The system can be configured to determine and / or quantify the including, but not limited to, those described above in connection with blocks 358 and 366 to utilize any of the techniques and / or algorithms described herein. It can be configured.

[0287] In some embodiments, at block 510, the system Use the analysis results to generate annotated medical images and / or quantized color maps For example, in some embodiments, the system may be configured to include one or more or multiple arteries, plaque, fat, benign plaque, malignant plaque, vascular morphology, and / or The method may be configured to generate a quantization map that indicates the quantization level, or other values.

[0288] In some embodiments, at block 512, the system may, for example, use previously obtained pairs Determine the progression of a patient's plaque and / or disease based on analysis of the patient's medical images In some embodiments, the system may be configured to 380 and / or those described in connection with FIG. 3D , Any of the algorithms or techniques described herein relating to disease tracking may be utilized. It can be configured as follows.

[0289] In some embodiments, at block 514, the system detects plaque and / or disease. configured to generate a suggested treatment plan for the patient based on the determined progression of the disease. In some embodiments, the system may be implemented generally as in blocks 382 and 383. and / or disease tracking, including but not limited to those described in connection with FIG. 3D. and utilizing any of the algorithms or techniques described herein in connection with therapy generation. It can be configured so that

[0290] In some embodiments, at block 516, the system generates a patient-specific report. A patient-specific report can be configured to include one or more medical images of the patient. It may contain images and / or derived graphics. For example, In some embodiments, the patient report may include one or more annotated medical images and / or In some embodiments, the patient-specific report may include a quantized color map. The report may include one or more vascular morphologies and / or quantified features derived from medical images. In some embodiments, patient-specific information may include plaque parameters. The report included quantified stenosis, atherosclerosis, ischemia, cardiovascular events, or disease. risk of disease, CAD-RADS score, and / or progression or follow-up of any of the above In some embodiments, the patient-specific report may include a trace of statins, lifestyle changes, or other factors. This may include suggested treatments such as style changes and / or surgery.

[0291] In some embodiments, the system is applicable to generate patient-specific reports. One or more phrases, particularly phrases that can be used for and / or access to, and use of, graphics, video, audio files, and / or other and / or configured to retrieve them from the patient report database 500. In generating the patient-specific report, in some embodiments, the system may: one or more of the above and / or derived from medical images of the patient Compare the parameters to one or more parameters previously derived from other patients. For example, in some embodiments, the system may be configured to One or more quantified plaque parameters derived from medical images, as well as One or more criteria derived from medical images of the patient or other patients in the same age group Comparison with quantified plaque parameters can be configured. In some embodiments, the system may select phrases, characterizations, graphics, Video, audio files and / or other information, for example to identify similar previous cases Therefore, it can be configured to determine whether to include it in a patient-specific report. In embodiments, the system utilizes AI and / or ML algorithms to provide patient-specific In some embodiments, the patient-specific The report may include written, AR, VR, video, and / or audio components. It can be done.

[0292] 5B to 5I show medical reports on patient characteristics generated based on medical image analysis. In particular, FIG. 5B illustrates an example of a patient-specific report. Showing the page.

[0293] 5C-5I show portions of an example patient-specific report. In this case, the patient-specific reports generated by the system are part of these illustrated parts. As shown in Figures 5C-5I, some embodiments may include only or all of the following: In this case, patient-specific reports are given, e.g., right coronary artery (RCA), right posterior descending artery (R-PDA) , right posterior lateral branch (R-PLB), left great artery (LM) and left anterior descending (LAD) artery, first pair Diagonal (D1) artery, second diagonal (D2) artery, circumflex (Cx) artery, first obtuse marginal branch (OM1), One or more of the following: 2 obtuse marginal branches (OM2), intermediate branches (RI), and / or others In some embodiments, the report includes visualization of the artery and / or portions thereof. For each artery, the system may, for example, provide a proximal portion, a middle portion, and / or a configured to generate a linear image of a simple trace along the length of the vessel, such as in the distal portion. will be done.

[0294] In some embodiments, the patient-specific report generated by the system includes information about intravascular The study included quantified measures of various plaque and / or vessel morphology-related parameters. In some embodiments, for each or a portion of the arteries included in the report, The system is generated and / or derived from patient medical images and measures total plaque volume, low density, and or total volume of non-calcified plaque, total value of non-calcified plaque, and / or total volume of calcified plaque Quantified measures of total larval volume are configured for inclusion in patient-specific reports. In some embodiments, the system may include a systolic pressure sensor for each or a portion of the arteries included in the report. The system may be generated and / or derived from medical images of a patient, e.g., the maximum percent stenosis in an artery. Include quantified measures of stenosis severity, such as percentage of In some embodiments, each of the arteries included in the patient-specific report is configured to In whole or in part, the system generates and / or derives from medical images of the patient; Quantified measures of vascular remodeling, such as the maximum remodeling index, can be used to provide patient-specific It is configured for inclusion in the report.

[0295] Visualization / GUI Atherosclerosis in and on the walls of arteries, which can restrict blood flow Disease, accumulation of fat, cholesterol and other substances (e.g., plaque). Atherosclerosis is considered a heart problem. Although it is often the case that arteries are involved in the pulmonary circulation, it can affect arteries anywhere in the body. This is due in part to imperfect imaging data, aberrations (e.g., For example, due to patient movement) and differences in plaque manifestation in different patients can affect coronary heart rate. It can be difficult to determine information about intravascular plaque. Neither the calculated information derived from the CT scan nor the visual inspection of the CT images alone can provide a clearer picture of the patient's condition. The present disclosure does not provide sufficient information to determine the condition present in the coronary arteries. The information in the section can be determined from the CT images using an automatic or semi-automatic process. For example, a machine learning process that has been trained on thousands of CT scans determining the information depicted in the CT image and / or using an analyst Inspect and improve the results of the machine learning process and use the example user interface described herein. The face can provide the determined information to another analyst or a physician. The information determined from this is very useful in assessing the patient's coronary artery condition, but it requires extensive experience. Visual analysis of the coronary arteries by trained physicians, combined with information determined from on-hand CT images, provides a clear picture of the patient's condition. As shown herein, implementation of the system allows for a more comprehensive assessment of the patient's coronary arteries. The embodiments are directed to the detection of vessel lumens, vessel walls, plaques, and stenoses in and around coronary vessels. This system facilitates analysis and visualization of blood vessels, for example, from a CT scan of a patient's blood vessels. Multiplanar forma- tion is based on a set of computed tomography (CT) images generated by View vessels in axial, sagittal, and coronal views, including mats, cross-sectional views, and 3D views of the coronary artery tree. CT images are a key component of the communication and management of medical imaging information and related data. It can be a Digital Imaging and Communications in Medicine (DICOM) image, a standard that CT image, or CT scan, as used herein, refers to a computer-controlled scan. It is a broad term that refers to pictures of internal structures made by scanners, such as X-ray beams. However, other radiation sources and / or imaging It is recognized that the system may also generate a set of CT-like images. Use of the term "CT image" in this document refers to a "CT image" of internal body structures, unless otherwise indicated. having any type of imaging source that creates a set of images depicting a "slice" The term "user imager" as used herein may refer to any type of imaging system. One key aspect of the interface is the precise correlation of displayed images and information from the CT images. The CT image displayed on the user interface (i.e., the "panel") The position in the image is displayed by the system so that the same position is displayed simultaneously in different images. Precisely correlated. Coordinates of coronary vessels can be measured simultaneously, e.g., two, three, four, five, or is displayed simultaneously on six images, allowing the practitioner to examine a specific location of a coronary vessel in one image, By allowing the other two to six images to show the exact same position correspondingly, This provides a great deal of insight into the vascular symptoms and allows the practitioner / analyst to understand the information presented. Quickly and easily visually integrate information to provide a comprehensive and accurate understanding of the coronary condition being examined. It becomes possible to obtain a solution.

[0296] Advantageously, the present disclosure provides for more useful and accurate analysis of CT images and data, allowing users to Interact with, analyze, and / or compute images and data in a more analytically useful way. This allows the analysis to be performed in a more useful way, for example to detect symptoms that require attention. A graphical user interface allows a user to interact with the processes described herein. , and define the relationship between different information and images of the coronary arteries, visualization of which is otherwise difficult. In one example, a portion of a coronary artery can be imaged using a CMPR image, an SMPR image, and By simultaneously displaying cross-sectional images, it is possible to obtain images that would otherwise be unperceivable using fewer images. provides analysts with insight into plaque or stenosis associated with coronary arteries, which may be Similarly, a portion of the coronary artery can be applied to CMPR, SMPR, and cross-sectional images. In addition, axial, sagittal, and coronal views allow for visualization of coronary artery disease that would otherwise be difficult to visualize. This can provide the analyst with more information that would otherwise be imperceptible using fewer images of the pulse. In various embodiments, the system or an analyst interacting with the system may determine any of the information described or exemplified herein, as well as a coronary artery in a set of CT images A set of CT images associated with the stenosis and plaque of a segment of a vascular Other information related to the attached coronary artery / vessel ("arterial information") (e.g., from another external source, e.g. from the analyst), as well as the identification and location of coronary vessels in a set of CT images. The information shown is stored in the system and displayed in various panels and reports in the user interface. The present disclosure provides a method for detecting coronary arteries and features associated with coronary arteries in a patient. This disclosure also provides a method for analyzing selected portions of coronary artery data, allowing for easier and faster analysis. Enables faster analysis of coronary artery data by providing rapid and accurate access Without the use of the systems and methods of the present disclosure, rapid CT imaging and coronary artery information is unavailable. Rapid selection, display, and analysis can be cumbersome and inefficient, and analysts may be reluctant to This can lead to missing important information in the analysis of the coronary arteries, which can affect the patient's condition. This may lead to an inaccurate assessment of the condition.

[0297] In various embodiments, the system may be configured to: Automatically (e.g., during the pre-processing step of a set of CT images associated with a patient, learning algorithms), or interactively (e.g., by providing at least some input to the user). The patient's coronary arteries can be identified (by receiving the signal from the user). In some embodiments, the processing of the raw CT scan data includes processing the patient's body to determine and / or identify the presence and / or absence of specific arterial vessels within the This may include analyzing CT data to identify specific arteries as a naturally occurring phenomenon. While certain arteries may exist in a particular patient, such particular arteries may not exist in other patients. In some embodiments, the system detects in the scan data The system can be configured to identify and label the arterial vessels that are detected. The system allows users to click on the labels of identified arteries in the patient's body. This allows the patient to see the blood vessels in the electronic representation of the arteries present in the patient's body. In some embodiments, the imaging system may be configured to allow for arterial enhancement. The system can then process the CT scan data in 10-15 minutes or less. The system is configured to analyze the arteries and display various views of the arteries present in the patient's body. In particular, by way of example, stenosis without considering benign or malignant plaque or any other factors. Performing a visual assessment of the CT to identify the lesions alone can take anywhere from 15 minutes to 20 minutes depending on skill level. It may take more than an hour and may be significantly There may be a wide variability.

[0298] Some systems allow analysts to view CT images associated with patients. However, it is possible to obtain all the necessary images in real time or near real time, with patient-specific coronary heart rate monitoring. 3-D arterial tree view of the vein, multiple SMPR views, and cross-sectional, axial, and sagittal views There is no ability to display corresponding CT and / or coronal views. This provides unparalleled visibility of a patient's coronary arteries, and It can be constructed into all representations, and the analyst or practitioner would not simply know without these images. This allows us to perceive features and information that we might not otherwise be able to perceive. User interface configured to show all, as well as information related to the displayed coronary vessels The interface allows the analyst or practitioner to combine their own experience with the information provided by the system. and can be used to better identify arterial conditions, which can then inform treatment for the patient. In addition, it can be determined by the system and used by the user interface. Information displayed by the interface that cannot be perceived by the analyst or practitioner is are presented in a way that makes them easy to understand and quick to adopt. Knowledge of the actual radiation concentration value of the LARK is determined by the analyst simply looking at the CT image. It does not guarantee that the system will find a complete analysis of all plaque. It can be shown.

[0299] Generally, arterial vessels are curved in nature. Therefore, the system can be used to The blood vessels can be straightened to form a substantially linear arterial profile, and several In some embodiments, this is referred to as a linear multiplanar reconstruction (MPR) image. In this mode, the system displays a dashboard view showing multiple arterial vessels in a linear multiplanar reconstruction. In some embodiments, the linear representation of the arterial vessel is configured to include a longitudinal axis ( In some embodiments, the system The system allows the user to inspect the vessel wall from various views and angles, allowing the user to configured to allow 360° rotation about the longitudinal axis of the linear arterial vessel. In some embodiments, the system may be configured to reduce blood flow, rather than just narrowing the vessel diameter. It is also configured to exhibit properties of the inner and / or outer tube walls themselves. The system may be configured to display multiple arterial vessels in multiple linear views, e.g., SMPR views. It can be achieved.

[0300] In some embodiments, the system may include a 3D image of the arterial vessel to better illustrate the curvature of the arterial vessel to the user. In some embodiments, the arterial vessels may be configured to show a perspective view of the arterial vessels. In some embodiments, the perspective view is referred to as a curved multiplanar reconstruction. In some embodiments, the CT images include CT images of the liver and blood vessels, for example in the form of arterial cartograms. The view does not show the heart tissue to better highlight the heart vessels, but has been modified to show the arterial vessels. In some embodiments, the system includes a CT image of the patient, the CT image being differently aligned with the patient's arteries. The perspective view may be configured to allow the user to rotate the view to view from different perspectives. In some embodiments, the system may measure the transverse axis (or width or The cross-section along the longitudinal axis can be configured to show a cross-sectional image of the arterial vessel along the short axis. In contrast to the image, in some embodiments, the system derives arterial blood pressure from a cross-sectional image across the transverse axis. Viewing the vessel allows the user to see stenosis, or narrowing of the vessel wall, more clearly It can be made into.

[0301] In some embodiments, the system may include a cartoon image, an illustrated image, or a cartoon image. The arterial blood vessels are displayed in various ways. In this embodiment, the system may be configured to provide a solid or gradient representation of a particular arterial vessel or a segment of a particular arterial vessel. Ray scaling can be used to identify the incidence of cardiovascular events in specific arteries or arterial compartments. For example, the system may display a first arterial vessel as Yellow indicates a moderate risk of a cardiovascular event in the first artery. The second artery is displayed in red to highlight the risk of a cardiovascular event occurring in the second artery. In some embodiments, the system may be configured to indicate a high risk. , to better understand the specified risks associated with arterial vessels or arterial vessel compartments. , allowing the user to interact with various arterial vessels and / or segments of arterial vessels. In some embodiments, the system may be configured to allow the user to monitor the patient's movements. It is possible to switch from an illustration image of the pulse to a CT image.

[0302] In some embodiments, the system may include all or some of the various figures described herein. can be configured to display all of the above in a single dashboard view. For example, the system , the linear view can be configured to be displayed along with the perspective view. can be configured to display a linear diagram along with the illustrative image.

[0303] In some embodiments, the processed CT image data allows the system to The patient's various arteries can be displayed to the user using the recorded data. As described above, the system can be used to generate a linear representation of a patient's multiple arterial vessels. , can be configured to utilize processed CT data. The linear view displays the patient's arteries in a line that mimics a substantially straight line. In morphology, linear diagram generation involves stretching an image of one or more naturally occurring curved arterial vessels. In some embodiments, the system utilizes such processed data. allows the user to rotate the displayed linear view of the artery in a 360° rotatable manner. In some embodiments, the processed CT image data can be The data allows visualization and comparison of arterial morphology over time, i.e., throughout the cardiac cycle. Arterial dilation, or lack thereof, indicates healthy arteries versus diseased arteries that are unable to dilate. In some embodiments, arterial flow may be measured by simply examining a single time point. A predictive algorithm can be used to determine whether or not a given volume can be expanded.

[0304] As mentioned above, aspects of the system can aid in visualizing a patient's coronary arteries. In some embodiments, the system allows the user to interact with the data of a particular patient and to dynamically generate visualization interfaces for analyzing the data. It can be configured to utilize processed data from processed CT scans. The system is capable of displaying multiple arteries associated with the patient's heart. The CT scan is constructed to display multiple arteries in a substantially linear fashion, even though arteries are not linear inside the patient. In some embodiments, the system visualizes different areas of the artery. Allows the user to scroll up and down or left and right along the length of the artery to In some embodiments, the system may be configured to allow a user to The user can rotate the artery 360° to allow different parts of the artery to be viewed at different angles. The device may be configured to allow the device to

[0305] Advantageously, the system marks ranges where the amount of plaque accumulation exceeds a threshold level. In some embodiments, the system may be configured to include or generate The system may be configured to allow the user to target specific areas of the artery for further examination. The system can associate a vein with an artery at a specific point along its length. The user marks one or more arteries to display the underlying data. It can be configured to allow the user to click on the selected area. In one embodiment, the system may be configured to generate a cartoon rendition of the patient's arteries. In some embodiments, the cartoon or computer-generated representation of the artery may include identifying the artery of the patient. A color coding scheme can be included to highlight areas of interest for further user inspection. In some embodiments, the system uses red or any other graphical representation. , producing cartoons or computer-generated images of arteries for further analysis by the user. In some embodiments, the system can be configured to represent arteries. Store, according to the labeling scheme, a cartoon representation and a 3D representation of the artery described above. If desired, the user can label the coronary vessels. The scheme can be changed or refined, and the preferred labels are stored and the coronary arteries labeled. It may also be used to

[0306] In some embodiments, the system identifies areas of the artery where ischemia is likely to be found. In some embodiments, the system may be configured to determine whether a malicious plugin is present. The present invention can be configured to identify the extent of plaque present. In this state, the system measures the range of shades and / or grayscale levels within the arteries. By determining whether a threshold level is exceeded, malignant plaque areas are identified. In one example, the system may be configured to detect when the image of the plaque area is black or substantially The imaging device can be configured to identify areas of plaque, typically black or dark gray. In one example, the system may be configured to measure the plaque area by designating it as white or light gray in color within the artery. and can be configured to identify areas of "benign" plaque.

[0307] In some embodiments, the system may identify portions of arterial vessels at high risk of cardiac events. and / or the pattern of plaque accumulation along the vessel wall. In some embodiments, the system is further configured to: display information to the user and / or the outline drawn by the AI ​​algorithm Specifying the part or outline identified by the user if the user believes the specification is inappropriate In some embodiments, the system is configured to provide editing tools to modify The software features an editing tool called "Snap-to-Lumen" that allows users to quickly create a specific section of a vessel. Select the area of ​​interest by drawing a box around it and selecting the snap-to-lumen option. Select an area and the system will more closely follow the boundaries of the vessel wall and / or plaque buildup The system automatically redraws the outline so that it can detect edges, but is not limited to that. In some embodiments, the AI ​​algorithm uses image processing techniques that are not used in medical imaging. The image data is not processed with perfect accuracy and therefore takes time to complete the analysis of the medical image data. In some embodiments, final user editing of the medical image data is required. This allows for faster processing of medical image data than would be possible using AI algorithms alone. Medical image data processing becomes possible.

[0308] In some embodiments, the system replicates images from higher resolution imaging. As an example, in CT, partial volume artifacts from calcium This is a known artifact of CT, resulting in overestimation of calcium volume and arterial This results in stenosis. In some embodiments, CT is used to train and evaluate arterial appearance against Arterial appearance may be replicated to resemble IVUS or OCT. In this way, coronary artery calcium artifacts are de-bloomed. Improve the accuracy of CT images.

[0309] In some embodiments, the system may include a blood vessel from a start segment to an end segment, and / or A graphical user interface that displays the vessel's tapering along the vessel length. It is configured to provide a graphical user interface. Many examples of panels that can be used are illustrated and described with reference to Figures 6A-9N. In some embodiments, a portion, panel, button, or user interface The information displayed in the interface may differ from that described herein and illustrated in the drawings. For example, the user can select different views of arteries from the user interface. Users may have preferences for placing the image in different parts of the image.

[0310] In some embodiments, the graphical user interface may include a graphical user interface for displaying a stenosis of a blood vessel. Or to show stenosis, the displayed blood vessel image is enhanced with a plot derived from AI algorithm analysis. In some embodiments, the system is configured to annotate the image with graphically stored data. The user interface system displays color markings or Annotate with other markings to identify areas of high risk or for further analysis, areas of moderate risk, The system may be configured to show high-risk and / or low-risk areas. The local user interface system displays red markers at specific ranges along the vessel length. Marked areas of prominent malignant lipid plaque should be annotated with markings or other graphic markings. It can be configured to indicate the presence of blockage and / or stenosis. In embodiments, annotated markings along the vessel length may include stenosis, biochemical tests, biomarkers, and car testing, AI algorithm analysis of medical imaging data, and / or other In some embodiments, the method is based on one or more variables, including but not limited to: The graphical user interface system visualizes atherosclerosis in angiograms. In some embodiments, the graphical user interface is configured to annotate the image with clinical features. The interface system is configured to annotate vascular images with ischemic images. In some embodiments, the graphical user interface includes a graphical user interface for displaying blood vessels and annotations. The user can rotate the vessel 180 degrees or 180 degrees to view the plaque accumulation image from different angles. The device is configured to allow for 360 degree rotation. From this view, the user can Stent length and diameter can be determined manually, and some implementations In morphology, the system analyzes medical image information to determine the recommended stent length and diameter. A graphical user interface that determines which stent is proposed to be implanted to allow the user to see how the stent addresses the stenosis within the identified area of ​​the vessel. In some embodiments, the systems, methods, and systems disclosed herein are configured as shown in the figure. The law and the device are designed to affect the subject, whether the subject is a human or other mammal. It may be applied to other areas of the body and / or other vessels and / or organs.

[0311] [Example] One of the primary uses of such systems is in the treatment of blood vessels, such as, but not limited to, coronary vessels. The purpose of the present invention may be to determine the presence of plaque in the ducts. The type of plaque may be determined by the user's For improved readability, the visualization can be based on Hounsfield unit density. Embodiments of the system also provide both vessel and lesion level analysis of segmented coronary arteries. This provides quantification of variables related to stenosis and plaque composition in the vascular system.

[0312] In some embodiments, the system assesses coronary artery disease (CAD) or suspected CAD. Coronary computed tomography angiography (CCTA) in patients undergoing coronary artery Determine the presence and extent of arterial plaque (i.e., atherosclerosis) and stenosis It provides trained physicians with an interactive tool to review and analyze cardiac CT data. Web-based software applications intended for use by medical professionals This system is configured as a post-processing system for CT images acquired using a CT scanner. The system provides tools and systems for characterizing, measuring, and visualizing coronary artery features. and generating a user interface that provides the functionality.

[0313] System embodiment features include, for example, centerline and lumen / vessel extraction, plaque detection, Composition overlay, user identification of stenosis, real-time calculated vessel statistics (vessel length , lesion length, vessel volume, lumen volume, plaque volume (non-calcified, calcified, low-density non-calcified plaque) Lark, and total), maximum remodeling index, and area / diameter stenosis ratio (e.g. , percentage), two-dimensional (2D) visualization of multiplanar reformatted vessels and cross-sectional images. Interactive three-dimensional (3D) rendering of the coronary artery tree, compared to the actual vessels appearing in the CT image. Responsive animated arterial tree visualization and user-modifiable semi-automatic vessel segmentation , as well as user identification of stents and chronic total occlusions (CTOs).

[0314] In one embodiment, the system is configured to: etyof Cardiovascular Computed Tomography ) using 18 coronary artery segments within the coronary vascular tree. Arterial segment labels include:

[0315] pRCA - proximal right coronary artery

[0316] mRCA - middle right coronary artery

[0317] dRCA - distal right coronary artery

[0318] R-PDA-Right posterior descending artery

[0319] LM - left aorta

[0320] pLAD - proximal left descending artery

[0321] mLAD - middle left anterior descending artery

[0322] dLAD - distal left anterior descending artery

[0323] D1 - 1st diagonal

[0324] D2 - 2nd diagonal

[0325] pCx - proximal left circumflex artery

[0326] OM1 - First blunt edge

[0327] LCx-distal left rotation

[0328] OM2-2nd obtuse edge

[0329] L-PDA-left posterior descending artery

[0330] R-PLB-Right posterolateral branch

[0331] RI-intermediate branch artery

[0332] L-PLB-left posterior wall branch

[0333] Other embodiments may include more or fewer coronary artery segment labels. The coronary artery segments present in each patient are classified as either right or left dominant. Some segments are present only when the right coronary artery is dominant, and some segments are Only present when the left coronary artery is dominant. Therefore, in many, if not all, cases, No patient will have all 18 segments. The system is compatible with most known variants. Consider an example.

[0334] In one example of system implementation, a CT scan is processed by the system and the resulting The collected data is compared with ground truth results generated by expert readers. Pearson correlation coefficients and brand correlations between system results and expert reader results were The de Altman agreement is shown in the table below. [Table 1]

[0335] 6A-9N show one embodiment of the system's user interface, panel ,Graphics ,Tools ,Examples ,of ,CT ,image ,representations, ,as ,well ,as ,a ,set ,of ,CT ,images ,shown ,in ,the ... In various embodiments, the user can: The interface is flexible and has panels, images, graphic representations of CT images, and can be configured to show various configurations of properties, structures, and statistics. For example: Based on analyst preference. The system provides multiple menus and It has navigation tools, keyboard and mouse shortcuts, and also the patient's It can be used to navigate through a set of CT images and associated images and information. can.

[0336] FIG. 6A can be generated and displayed on a CT image analysis system described herein; Multiple panels that can show various corresponding views of the patient's arteries and information about the arteries 6 shows an example of a user interface 600. The user interface 600 shown in FIG. 6A is a diagram illustrating the development of a method for analyzing a patient's coronary arteries. A starting point can be the "Study Page" (or Study Page 6) herein. In some embodiments, the study page may be used by, for example, an analyst. can be placed in different locations on the user interface 600 based on user preferences. Various examples of the user interface 600 may include a number of panels. A particular panel among the possible panels that may be displayed (e.g., based on user input) You can choose to display it.

[0337] The example study page 600 shown in Figure 6A is a 3D coronary vascular study based on CT images. The arterial tree 602 includes a raw (3D) representation of the coronary vessels identified in the CT image. The first panel 601 (circled " While processing the CT images, the system determines the extent of the coronary vessels. The arterial tree is generated by defining structures that are not part of the coronary vasculature (e.g., the heart). tissue and other tissues surrounding the coronary vessels) are not included in the arterial tree 602. 6A does not include cardiac tissue between the branches (blood vessels) 603 of the arterial tree 602. , allowing visualization of all parts of the arterial tree 602 without obstruction by cardiac tissue. become.

[0338] The example on Study Page 600 also demonstrates at least one linear multiplanar reconstruction (SMPR) ) a second panel 604 ( SMPR images include the vascular images in a specific rotational orientation. Multiple SMPR images are displayed in the second panel 604, each image being a different For example, at any 1° or 0.5° angle. In this example, the second Panel 604 is shown in elevation at relative rotations of 0°, 22.5°, 45°, and 67.5°. As shown, the image includes four straight multi-planar vessels 604a-d, and the rotation is In some embodiments, the rotation of each image is different, e.g., at different relative rotation intervals. The user interface accepts input from the user. 6 shows a rotation tool 605 configured to receive and rotate the SMPR image (e.g., 1 degree This can be used to adjust the blood vessels shown in the SMPR image. One or more graphics representing the lumen of a blood vessel may also be displayed. Graphics, graphics representing vessel walls, and / or graphics representing plaque is.

[0339] This study page 600 example also shows the CT images in a set of patient CT images. A third panel 606 is configured to show a cross-sectional image of a blood vessel 606a generated based on the (also indicated by a circled "1c"). The cross-sectional image includes the blood vessels shown in the SMPR image. The cross-sectional image also shows the difference in the blood vessels in the SMPR image (e.g., pointing device). The user interface corresponds to the position indicated by the user (using a , selection of a specific location along the coronary vessel in the second panel 604 , allows the relevant CT image to be The third panel 606 is configured to display the cross-sectional image. 07 is displayed in the second panel 604, and the third panel 606 shows the extent of plaque in the blood vessel. Indicates the degree.

[0340] This example study page 600 also includes anatomical plan views of selected coronary vessels. The fourth panel 608 is included. In this embodiment, the study page 600 includes an axial 3D image 608a (also indicated by a circled "3a"), coronal image 608b (also indicated by a circled " 3b), and sagittal view 608c (also indicated by a circled "3c"). Axial views are cross-sectional or "top" views. Coronal views are frontal views. The sagittal view is a lateral view. The user interface displays the sagittal view of the selected coronary vessel. For example, the image corresponding to a coronary vessel (e.g., For example, a selected image at a position on one of the SMPR images in the second panel 604 This is an image of the coronary blood vessels.

[0341] Figure 6B shows various corresponding diagrams of a patient's arteries that can be generated and displayed on the system. A study page (user interface) with multiple panels that can be displayed ) 600. In this example, the user interface 600 is a 3D The arterial tree is shown in the first panel 601, and cross-sectional images are shown in the third panel 606. and a sagittal view is displayed in the fourth panel 608. The second panel 604 shown in FIG. Instead, the user interface 600 displays a curved, multi-planar view of the selected coronary vessel. The fifth panel 609 shows a reconstructed (CMPR) angiogram. In this example, two CMPR images can be displayed. CMPR images are generated, with the first CMPR image 609a at 0° and the second CMPR image 609b at 9°. CMPR images are displayed at various relative rotations, e.g., from 0° to 259.5°. The coronary vessels shown in the CMPR image correspond to the selected vessel. and corresponds to the vessel displayed in the other panel. A location on the vessel is selected in one panel. and (e.g., CMPR image), and images of other panels (e.g., cross-sectional, axial, sagittal, and The system automatically updates the coronal and venous views to show the vessels at the selected location on each view. This significantly improves the information presented to the user and increases the efficiency of the analysis. Improve.

[0342] Figures 6C, 6D, and 6E show the characteristics of the multiplanar reconstruction (MPR) vascular image in the second panel. The image shows the specific details and functionality associated with this image. After verifying the accuracy of the coronary artery tree segmentation in 602, we proceed to interact with the MPR images. where individual vessel segments (vessel wall, lumen, etc.) can be edited. In the SMPR and CMPR images, the arrow icon 60 shown in Figures 6C and 6D By using the 5, the vessel can be rotated incrementally (e.g., 22.5°). Alternatively, by using the rotate command 610 as shown in FIG. 6E, The vessel can be rotated 360 degrees in one degree increments. The vessel can also be rotated through the user interface. On interface 600, press the COMMAND or CTRL button and left-click the mouse. +You can rotate it by dragging it.

[0343] FIG. 6F shows the first panel, which allows the user to view and modify vessel labels. Further information is shown in a three-dimensional (3D) rendering of the coronary artery tree 602 in 601. FIG. 6G shows the coronary artery tree 602, an axial view 608a, a sagittal view 608b, and a coronary view 608c. Image 608c shows the shortcut commands. The user can rotate the arterial tree and view the resulting image using the user interface shown in Figure 6G. Zoom in and out on the 3D rendering using the commands selected in the By clicking on the vessel currently being examined, you can It turns yellow, indicating that it is a blood vessel. In this image, the user can right-click on the name of the blood vessel and select to open a panel 611 configured to receive input from the user to rename the vessel. The panel 601 also allows you to rename or delete a vessel. Contains a control that can be activated to turn the displayed label "on" or "off." Figure 6H further illustrates DIC in three anatomical planes: axial, coronal, and sagittal. Figure 6I shows a panel 608 of the user interface for viewing OM images. , panel 606 showing a cross-sectional image of a blood vessel. Scroll, zoom in / out, and pan commands can also be used on these images.

[0344] 6J and 6K illustrate the toolbar 612 and menus of the user interface 600. Figure 6J shows specific aspects of functionality in new navigation. 6 illustrates a toolbar of the user interface to navigate. , including buttons 612a, 612b, etc. for each blood vessel displayed on the screen. The interface 600 displays buttons 612a-n to provide various information to the user. In one example, when a vessel is selected, a corresponding button, e.g. Button 612c is highlighted (e.g., displayed in yellow). A dark grey button indicates that the vessel is available for analysis. The black button 612d indicates that the vessel is not anatomically present or has too many artifacts. This means that the data could not be analyzed by the software. A button 612e that appears grayed out indicates that the vessel has been inspected.

[0345] Figure 6K shows the expanded menu for viewing all available series for inspection and analysis. 6 shows a diagram of a user interface 600 including: If vessel segments are provided for analysis from different image series, the user interface The source is configured to receive user input to select the desired series for analysis. In the example, the user inspects the sequence of interest by selecting one of the radio buttons 613. A radio button can be selected for testing and an input indicating the sequence can be received. The color changes from gray to purple. In one embodiment, the software defaults to the highest diagnostic quality setting. Two series are selected for analysis, but all series are available for testing. ,determine whether the series selected by the system are of diagnostic quality required for analysis. Clinical judgment can be used to select different series for analysis as desired. The sequences selected by the system are optimized by prioritizing diagnostic-quality images. The system will improve workflow. The system will allow users to inspect all sequences and The selection of quality images is not interchangeable in the study. Send any line shown in 6K and select a vascular cell by hovering the mouse over the line. The user can then select the "Analyze" button 614 as shown in Figure 6L. Cut.

[0346] FIG. 6M illustrates a user interface for adding new blood vessels onto an image, according to one embodiment. 6 shows a panel that can be displayed on the screen 600. Adding new blood vessels to the image To add a vessel, the user interface 600 includes a “+ Add Vessel” button on the toolbar 612. The user interface can receive user input via buttons. The "Create Mode" 615 button appears on the fourth panel 608 on the axial, coronal, and sagittal views. Then scroll and click the left mouse button to select multiple dots (for example, You can add blood vessels to the image by creating new When new vessels were added, they were identified as new vessels in MPR, cross-sectional, and 3D arterial images. The user interface will indicate that the vessel has been added. The system is then configured to receive a "Done" command. To use the tools to segment the vessels, click "Analyze" on the toolbar and The interface displays the proposed segmentation for inspection and modification. The name of the vessel can be created by selecting "New" in the 3D artery tree in the first panel 601. 611, thereby activating the name panel 611 and entering the name of the vessel in panel 61 1 and then stores the new vessel and its name. If the software cannot identify a vessel that has been added by the user, The user can adjust the center line to return to the straight vascular line connecting the added green dots. The user interface popup menu 611 is in standard format. This allows for rapid and consistent identification and naming of new blood vessels according to the protocol.

[0347] FIG. 7A shows how machine learning algorithms are used to process CT scans, and then an analyst analyzes the CT Scanning, and the findings resulting from processing the information generated by machine learning algorithms Editing toolbar 71 containing editing tools that allow the user to modify and improve accuracy 4 shows an example of a user interface. In some embodiments, the user interface may include Includes editing tools that can be used to modify and improve accuracy. In the Editing Tools section, edit tools are located on the left side of the user interface, as shown in Figure 7A. Below is a list and description of the available editing tools. By hovering over the tool, the name of each tool will be displayed. You can click on these tools to If the tool is gray, it is stopped. If the software identifies any of these characteristics in a vessel, it launches a tool The annotation is already on the image when you click Edit. The editing tools on the toolbar are one or more of the following tools: The lumen wall 701, the snap-together vessel wall 702, the vessel wall 70 3, snap-to-lumen wall 704, segment 705, stenosis 706, plaque Burley 707, Central Line 708, Chronic Total Occlusion (CTO) 709, Stent 710, Exclusion 711, tracker 712, and distance 713. The user interface 600 Receive user selection of each tool icon (shown in the table below and in Figure 7A) Each of these tools can be launched by configuring the Edit Tool Description below. It is configured to provide the functionality described in the table. [Table 2]

[0348] Figures 7B and 7C illustrate the specific functionality of the Tracker Tool. The control 712 displays various panels of the user interface 600, such as the SMPR image. , CMPR, cross-sectional, axial, coronal, sagittal, and 3D arterial tree views. It orients the images and allows the user to correlate them. The Tracker icon is selected on the Edit toolbar. The Tracker tool 712 is launched. When this occurs, the user interface displays a line 616 (e.g., For example, a red line) is generated and displayed. The system then displays the corresponding ( The first panel 601 generates a 3D arterial tree (red) disk 617, which is then attached to the line 6 16 and the corresponding position. The system will display the corresponding The fourth panel generates a (red) dot that corresponds to the axial, sagittal, and coronal images. The line 616, the disk 617, and the dot The points 618 are all position indicators that refer to the same position in different images, thereby By scrolling either tracker up or down, you can see the position indicators of the other images. The same movement of the mouse is effected. The user interface 600 also displays a position indicator. A cross-sectional image corresponding to the position indicated by the data is displayed on panel 606.

[0349] 7D and 7E show the vessel and vascular The specific functionality of the lumen wall tool 701 and the vessel wall tool 702 is shown. 03 has been previously determined for blood vessels (e.g., using machine learning processes on CT images). ), lumen and vessel wall (herein referred to as contour, boundary, These tools are configured to modify the output or Used by the system to determine the measurements displayed. By interacting with the contours generated by the system, the user can refine the contour location. The accuracy of the contours and any measurements derived from them can be improved. These tools are available in SMPR and cross-sectional images. The tools are located in the Edit toolbar. The vessels and lumen icons 701, 703 are activated by selecting them on the The wall 619 is graphically indicated in a certain color (e.g., yellow) in the MPR image and the cross-sectional image. The lumen wall 629 is shown in a different color (e.g., purple) In one embodiment, the user interface The face is configured to refine the contour through user interaction. For example, To refine the image, the user can move a pointing device (e.g., mouse, star) over the outline. highlight the contour, click the desired vessel or lumen wall contour, and You can drag the indicated trace to a different position to set new boundaries. The Interface 600 automatically updates any changes to these tracings. The system is configured to store the data in a circular manner in real time or near real time. Recalculate any measurements derived from changes in contours. Also, recalculate the contours of a single panel of a single statue. Any changes made in will be displayed correspondingly in the other images / panels.

[0350] Figure 7F shows the luminal wall / snap-to-vascular tools 701, 702 and the vascular wall / snap-to-vascular tools. can be used to activate the tip-to-lumen wall tools 703, 704, respectively. The user interface 600 includes a lumen wall button 701 and a snap-to-vascular Wall button 702 (left), as well as vessel wall button 703 and snap-to lumen wall button The user interface provides these tools. , correct the previously determined lumen and vessel wall contours. The tool is useful for easily and quickly closing the gap between the lumen and the vessel wall contour, i.e. The lumen contour trace and the vessel contour trace are moved to be the same or substantially the same. The user interface 600 is used to reduce interactive editing time. , the user positions the pointing device over the tool, thereby snapping the tool. When the toolbar button appears, it is configured to launch these tools. For example, the lumen wall When you align the button 701, the snap-to-vessel button 702 is to the right of the lumen wall button. The luminal wall button 704 appears on the side and fits over the vascular wall button 703. appears next to the Vessel Wall button 703. The button is selected to activate the desired tool. Referring to Figure G, the pointing device is clicked at a first point 620, Use this to drag along the intended portion of the vessel and edit it to a second point 621. The desired range 622 appears, indicating where the tool will operate. Once the end of the line is drawn, you can deselect it to fasten the lumen and vessel wall together. circle.

[0351] Figure 7H shows the marking of boundaries between individual coronary artery segments on the MPR. Allows for a second panel that can be displayed while using the segment tool 705 The user interface 600 includes a segment tool 602. When 705 is selected, a line (e.g., lines 623, 624) is drawn on the blood vessel in the SMPR image. The lines are configured to appear on the vascular image in panel 602 of FIG. The names are displayed as icons adjacent to each line 623, 624. 625, 626. To edit the name of the segment, use the name shown in FIG. 7I. Use panel 611 to click on icons 625, 626 and labels as appropriate. Segments can also be erased, for example by selecting the trash can icon. Lines 623, 624 can be moved up and down to define segments of interest. If there is no segment, the user can add a new segment using the Add Segment button. and use the labeling functions in the Segment Labeling pop-up menu 611. and labeling can be performed.

[0352] 7J-7M illustrate the use of the stenosis tool 706 on the user interface 600. For example, Figure 7L shows an example of a 3D model based on user-edited lumen and vessel wall contours. The figure shows the stenosis button, which can be used to drop a stenosis marker. Figure 7M shows the stenosis marker on the segment in a curved multiplanar angiogram (CMPR). The second panel 604 shows a marker marking the extent of stenosis in a blood vessel. The stenosis tool 706 allows the user to indicate the stenosis. In one embodiment, the stenosis tool can be used to mark the extent of stenosis in a blood vessel. The set of five markers is used to be defined.

[0353] R1: Proximal normal slice closest to stenosis / lesion

[0354] P: Abnormal slice most proximal to stenosis / lesion

[0355] O: slice with maximum occlusion

[0356] D: Abnormal slice most distal to the stenosis / lesion

[0357] R2: Distal normal slice closest to stenosis / lesion

[0358] In one embodiment, two techniques for adding stenosis markers to multiplanar images (linear and curved) are used: After selecting the stenosis tool 706, the stenosis button shown in FIG. 7K or FIG. 7L can be You can add stenoses by activating the (i) Click on the Stenosis "+" button (Figure 7K) to drop a stenosis marker; (ii) A series of five evenly spaced yellow lines appears on the blood vessels, and the user can (iii) the markers must be edited to the applicable position; You can move the five marks by clicking inside the highlighted ranges and dragging them up or down. (iv) Move all the cars at the same time, and (v) click on individual yellow lines or tags to move them up or down. (v) to remove the stenosis, use the red Click the trash can icon. The stenosis is calculated based on the user-edited lumen and vessel wall contours. To drop the disease marker,

number

[0359] Figure 7N uses the plaque overlay tool 707 in the user interface 7N shows an example of a panel that can be displayed while "Plaque" refers to low-density non-calcified plaque (LD-NCP) 701, non-calcified Calcified plaque (CP) 633 or non-calcified plaque (NCP) 632 You can also create a plaque overlay by selecting the plaque overlay tool 707 in the Edit toolbar. Once started, the Plaque Overlay Tool 707 will SM of the second panel 604 with plaque range based on Hull Unit (HU) density PR image, cross section of SMPR, and cross section image of third panel 606 (see, e.g., Figure 7R) In addition, a legend opens in the cross-sectional image, allowing you to easily identify plaque and The type corresponds to the color of the plaque overlay as shown in Figures 7O and 7Q. The user can click on the “Edit Threshold” button located in the upper right corner of the cross-sectional image as shown in FIG. 7P. For three different types of plaque, click the "olds" button. A different HU range can be selected. In one embodiment, the initial plaque threshold for the value The initial settings are shown in the table below. [Table 3]

[0360] The initial value can be set, if desired, using, for example, the Plaque Threshold interface shown in FIG. 7Q. Although initial values ​​are provided, the user must use their clinical judgment to The user can select different plaque thresholds based on the first threshold shown in Figure 7R. The cross-sectional view in panel 606 of FIG. 3 can be used to further examine the area of ​​interest. Also, the selected plaque threshold can be set by clicking the This can be seen in the vascular statistics panel.

[0361] The centerline tool 708 allows the user to adjust the center of the lumen. Quantification of the lumen and vessel wall, as well as plaque, if present, by changing the center point The centerline tool 708 can be used to change the centerline of a selected object on the user interface 600. A line 635 (e.g., a yellow line) appears in the CMPR image 609, A point 634 (e.g., a yellow point) appears in the cross-sectional image of the third panel 606. The center line is the line / You can adjust the points as needed by clicking and dragging them. Any changes in the R view are reflected in the cross-sectional view and vice versa. The interface 600 provides several ways to extend the centerline of an existing vessel. For example, The user can extend the centerline as follows: (1) in the axial, coronal, or Or right-click on the outlined vessel dot 634 on the sagittal image (see Figure 7U) and select 2) Select "Extend from Beginning" or "Extend from End" (see Figure 7U) to view the blood vessels. Jump to the beginning or end of the (3) (green) dot to extend the vessel ( (See Figure 7V), (4) When finished, select the (blue) check mark button, To abort the extension, select the (red) "x" button (see Figure 7V for an example). The interface then extends the vessel according to the changes made by the user. Then, manually edit the lumen and vessel wall in the SMPR or cross-sectional image (see Figure 7W for an example). The user interface may not be able to identify the vessel segments being added by the user. If not, the system returns to a straight blood vessel line connecting the dots added by the user. The line can be adjusted.

[0362] The user interface 600 also displays a portion of an artery that has a chronic total occlusion (CTO). , or chronic total occlusion, which identifies sections of the artery that have 100% stenosis and no detectable blood flow. A CTO tool 709 is provided. Since it is likely to contain a large amount of thrombus, Plaques are not included in the overall plaque quantification. To activate, click CT on the Edit toolbar 612. To add a CTO, click Tools 709. Click the TO "+" button. As shown in Figure 7X, a portion of the CTO vessel is shown. Two lines (markers) 636, 637 appear in the MPR image of the second panel 604. The degree of CTO can be adjusted by moving the car 636, 637. If a TO exists, you can reactivate the CTO "+" button in the user interface. Additional CTOs can be added by adding new ones. CTOs can also be deleted as needed. The location of the CTO is stored. In addition, the portion of the vessel that is within the specified CTO can be is not included in the overall plaque calculation, and determination of plaque quantification is necessary after CTO is identified. It will be recalculated accordingly.

[0363] The user interface 600 also indicates where the stent is located within the vessel. A stent tool 710 is provided. The stent tool is accessible from the stent toolbar 612. The tool is activated by user selection of tool 710. To add a stent, the user selects Click the "+" button provided in the interface. Two lines 638, 6 39 (e.g., purple lines) appear in the MPR image as shown in FIG. 7Y, with individual lines 638 , 639 and move them up and down along the vessel to the end of the stent. By doing so, the lines 638 and 639 can be moved to indicate the extent of the stent. Overlap with the CT (or CTO / exclusion / stenosis) markers is displayed in the user interface. Disallowed by 00. Stents can also be erased.

[0364] The user interface 600 can also be used to measure motion, contrast, misalignment, or other Constructed to indicate portions of vessels to be excluded from analysis due to blurring caused by , an exclusion tool 711 is provided. By excluding low quality images, the unexcluded portion of the blood vessel is This improves the overall quality of the analysis results for . To exclude the top or bottom portions of the vessel, Activate the Segment tool 705 and Exclusion tool 711 on the Edit toolbar 612 Figure 7Z shows the use of the exclusion tool to exclude a portion from the apex of a blood vessel. A shows the use of the exclude tool to exclude the bottom portion of a vessel. The marker acts as an exclusion marker for the apical portion of the vessel. The enclosed area is excluded from all statistical calculations of the vessel. Markers can be excluded by dragging them to the bottom of the desired exclusion range. The excluded range is highlighted. Alternatively, drag the "end" marker to the top of the desired excluded range. The excluded range is highlighted and the user can explain the reason for the exclusion. New exclusions can be entered into the interface (see Figure 7AC). To add a new element to a list, activate the Exclude tool 711 on the Edit toolbar 612. button. A user interface pop-up will appear with the reason for the exclusion. A window will appear (Figure 7AC) where you can enter the reason and refer to the exclusion ranges shown. Two markers 640, 641 appear in the MPR as shown in FIG. 7AB. Clicking inside the highlighted area moves both markers simultaneously. The user can click and drag the lines 640, 641 to move the individual The user interface 600 allows the exclusion marker line to be moved. 640, 641 (and previously defined features) and exclude lines 640, 641 and any previous CTO, stent, or stenosis-containing vessel. The user interface 600 also prohibits overlapping with the specified Configured to clear exclusions.

[0365] 7AD-7AG, the user interface 600 also includes an image provides a distance tool 713, which is used to measure the distance between two points on A drag-and-drop ruler that captures precise measurements. The tool works in MPR, cross-sectional, axial, coronal, and sagittal views. , click the distance tool 713 on the editing toolbar 612. Then, click The line 642 and the measurement value 643 are displayed in the user interface. It appears on the image displayed on 600. Right-click on the distance line 642 or the measurement value 643 , by selecting the “Delete Distance” button 644 on the user interface 600 (See Figure 7AF.) Figure 7AD shows the results of a straight multiplanar vessel (SMPR). Figure 7AE shows an example of measuring the distance of a curved multiplanar vessel (CMPR). FIG. 7AF shows an example of measuring the distance 642 of a cross-section of a blood vessel. FIG. 7AG shows an example of measuring distance 642 in an axial image of a patient's anatomy. An example of this is shown below.

[0366] An example of the vascular statistics panel of the user interface 600 is shown in Figures 7AH-7AK. FIG. 7AH illustrates the vascular statistics panel 646 (or "Task") shown in FIG. You can choose to display the panel's user interface 60 7AJ shows the "Vessel Statistics" portion 645 of the 0 (e.g., button). A specific function in the Vascular Statistics tab that allows the user to click through to details of Figure 7AK also shows the possibility of using a stencil to toggle between vessels. For example, the user can select the vascular panel shown in FIG. 7A-I. The panel can be hidden by clicking the "X" in the figure. As shown in J, at the per-vessel and per-lesion (if present) level.

[0367] If more than one lesion is marked by the user, the user must click the details of each lesion. To view the statistics for each vessel, the user can click on the You can toggle between the vessels in the vessel panel.

[0368] General information regarding length and volume is provided for blood vessels and lesions (if present). Vascular Statistics Panel 6 with plaque and stenosis information at per vessel and per lesion level The user can exclude the data to be taken into account in the calculation by using the exclusion tool. You may want to remove unwanted artifacts from the image. The table below shows the artifacts that are present in blood vessels, lesions, Specific statistics available for plaque and stenosis are shown. [Table 4] [Table 5] [Table 6] [Table 7]

[0369] See, for example, low-density non-calcified plaque, non-calcified plaque, and calcified plaque. This allows the system to define the parameters that are used and displayed in various parts of the user interface 600. The quantitative variable is the Hounsfield unit (HU). The field unit scale is a quantitative scale that describes radiation and characterizes radiative attenuation. It is often used in reference to CT scans as a method of determining what a given finding represents. Hounsfield unit measurements are provided with reference to a quantitative scale. Examples of Hounsfield unit measurements for specific substances are shown in the table below. [Table 8]

[0370] In one embodiment, stenosis, atherosclerosis, and CAD-RADS are further described. The information the system determines about the user interface, as shown in Figure 8A. Included on the 600 panel of 800. By default, CAD-RADS score is unselected. may be used, requiring the user to manually select the score on the CAD-RADS page. By hovering over the "#" icon, the user interface 600 Provides more information about the output obtained. To see more details about the CAD-RADS output, click Click on the "View Details" button located on the right, which will take you to the available details page. In one embodiment, the centerpiece page of the user interface 600 Center the view and perform SCCT coronary artery segmentation as shown in panel 802 of Figure 8C. The coronary artery tree 805 ("Cartoon") is divided into segments 805a to 805r based on the There is a non-patient-specific rendition of the “arterial tree” (805). All analyzed vessels have their own intravascular The maximum diameter stenosis is displayed in color according to legend 806. The greyed out segments / vessels in 805, e.g., segments 805q and 805r, are Those that were not available anatomically or were not analyzed by the system (all sections (The segment may not be present in all patients.) As shown in Figures 8B and 8C , for example, by using the user interface 600 selection buttons of panel 801 By clicking on the upper area (RCA, LM+LAD, etc.), you can You can see the information for each segment, or you can see the segments in the cartoon coronary artery tree 805. Alternatively, the members 805a to 805r may be selected.

[0371] Stenosis atherosclerosis displayed on the user interface of panel 807 The data updates accordingly as different segments are selected, as shown in Figure 8D. 8E shows an example of a portion of a summary panel 807 for each area of ​​the user interface. Figure 8F also shows the location of the blood vessel along the indicated location (e.g., along the SMPR visualization). the position indicated by the pointing device when moved), An example of a portion of panel 807 showing the SMPR and associated statistics for selected vessels is shown. That is, the user interface 600 displays the SMPR visualization in panel 809, and the user interface is displayed, for example via a pointing device A popup panel that displays information when location information along the vessel is received from the user. At 810, a plaque detail and a stenosis detail are provided. Total occlusion (CT) and / or presence of a stent is demonstrated at the vessel segment level For example, Figure 8G shows the presence of a stent in the D1 segment. Figure 8H shows It indicates the presence of CTO in the mRCA segment. The abnormalities can be displayed under the coronary artery tree as shown in Figure 8I. You can easily identify the anomalies by, for example, hovering your pointing device over the "Details" button. If the plaque threshold is changed in the analysis, the Alerts you in the user interface or in generated reports that the changes have been made. If anomalies exist, the associated The isolated coronary vessel segment 805 appears separated from the aorta. For example, as shown in panel 811 of Figure 8K, a textual summary of the analysis also It can be displayed under the tree.

[0372] Figure 9A shows a summary of the atherosclerosis information based on the analysis. 9 illustrates an atherosclerosis panel 900 that can be displayed on the interface. Figure 9B shows a summary of atherosclerosis information on a segment-by-segment basis. 1 illustrates a vessel selection panel that can be used to select vessels as shown. The top section of the atherosclerosis panel 900 is a patient-specific If the user selects a segment with calcified plaque in panel 901, or the "segment with non-calcified plaque" in panel 902. , the segment names with applicable plaques are displayed. Under patient-specific data, The user can select each vessel by clicking one of the vessel buttons, shown in Figure 9B. and atherosclerosis data by segment may be accessed.

[0373] Figure 9C shows the atherosclerosis determined by the system on a segment-by-segment basis. A panel 90 can be generated and displayed on the user interface showing the disease information. 3. Presence of positive remodeling, the highest remodeling index, and The presence of low-density non-calcified plaque was confirmed for each segment in panel 903 shown in Figure 9C. For example, plaque data may be displayed below on a segment-by-segment basis. The plaque composition volume can be displayed segment by segment in panel 903 shown in FIG. 9C. It is possible.

[0374] Figure 9D displays on the user interface, including patient-specific data on stenosis. The upper section of the stenosis panel 904 shows the patient-specific data. Hover the pointing device over the number as shown in Figure 9E. By doing so, you can view more details about each count. The blood vessels involved are shown in the table below. [Table 9]

[0375] In one embodiment, as shown in FIG. 9F, a bar graph 906 of percentage diameter stenosis can be generated and displayed in panel 905 of the user interface. The bar graph 906 of the maximum diameter stenosis rate of each segment displays the maximum diameter stenosis rate of each segment. If marked on the segment, indicate 100% diameter stenosis. If a stenosis is marked on the segment, the maximum output is displayed by default. ,Users can click on each stenosis bar to see the details of the stenosis and Small stenoses (if present) can be investigated. The user can also Drag the gray button in the center of the SMPR image of the blood vessel to select each section. Scroll the screen to view the luminal diameter and % diameter stenosis rate for each cross section at any selected position. do.

[0376] FIG. 9H shows the location of one or more stenoses marked on the SMPR based on the analysis. The figure shows a panel showing categories. Color can be used to enhance the displayed information. In the example, LM stenoses with a diameter stenosis of ≥ 50% are marked in red. The maximum percentage for each segment, as shown in panel 907 of the interface As shown in Figure 9J, the diameter narrowing rate is plotted by using the pointing device. By "hovering" over the cross-sectional representation of the vessel, the reference minimum lumen diameter and lumen diameter can be displayed. If a segment was not analyzed or does not exist anatomically, the segment The segment is grayed out and displays "Not Analyzed." If the segment was analyzed but no stenosis was detected, If not searched, the value will show "N / A".

[0377] Figure 9K is panel 9 of the user interface showing CADS-RADS score selection. 08. The CAD-RADS Panel, "Coronary Artery Disease - Reporting and Data Systems" System (CAD-RADS), SCCT, ACR, and NASCI Expert Consensus Document: View the definition of CAD-RADS as defined by the ACC Approved The user has complete control over the selection of the CAD-RADS score. In one embodiment, the score is Not suggested by the system. In another embodiment, a CAD-RADS score is suggested. When a CAD-RADS score is selected on this page, the score is Displayed both in the user interface panel and on the full text report page. Once the CAD-RADS score is selected, the user is given the option to select modifiers and symptoms. Once a representation is selected, interpretation, further cardiac testing, and management guidelines are provided. , for example, as shown in panel 909 shown in Figure 9L. These guidelines can be displayed to the user on the Advice and Data System (CAD-RADS), SCCT, ACR, and NASCI Replicates guidelines found in the Expert Consensus Document: Endorsed by the ACC. do.

[0378] Figures 9M and 9N can be generated and displayed in the user interface panels. Figure 9M shows a table that can be used to generate and / or include in a report. Figure 9N shows the quantitative plaque output. In the quantitative table, the user can view the quantitative segmental stenosis and Quantitative Stenosis and Vascular Output Tables (Figure 9M) contains information about the arteries and segments evaluated. The sum of each vessel area The information may be, for example, length, vessel volume, lumen volume, total plaque volume, The maximum percent diameter stenosis, maximum area stenosis, and maximum remodeling index may be included. The Target Plaque Output Table (Figure 9N) contains information about the arteries and segments that were evaluated. The information may include, for example, total plaque volume, total calcified plaque volume, non-calcified plaque volume, The volume of the plaque may include low-density non-calcified plaque volume, low-density non-calcified plaque volume, and total non-calcified plaque volume. Users can also download quantitative output PDF or CSV files with full text reporting. The full text report covers atherosclerosis, stenosis, and The user can select the report type and the CAD-RADS criteria as desired. If the user chooses to edit the report, the report will be Do not automatically update DS selection.

[0379] FIG. 10 is a flow diagram illustrating a process 1000 for analyzing and displaying CT images and corresponding information. At block 1005, the process 1000 generates computer-executable instructions. A set of CT images of the patient's coronary vessels, vessel labels, and stenosis, plaque, and a set of CT images containing information on the location of coronary vessel segments and associated arterial information; All steps of the process can be implemented, for example, in the system implementation described in FIG. In some embodiments, this can be implemented by the system embodiments described herein. For example, one or more non-transitory computer storage media in communication with one or more non-transitory computer storage media. A computer hardware processor generates one or more non-transient computer programs. In various embodiments, the method includes: The user interface displays various views (e.g., S) related to the CT image of the patient's coronary arteries. One or more of the images (MPR, CMPR, cross-sectional, axial, sagittal, coronal, etc.) Graphical representation of coronary arteries, extracted or revised by machine learning algorithms or human analysts The features being corrected (e.g., vessel wall, lumen, central line, stenosis, plaque, etc.) are listed by the system, by the analyst, or by the analyst interacting with the system (e.g. Displays information related to the CT image that has been determined by the The device may include one or more sections or panels configured to In one embodiment, the user interface panels may include those described herein, and The user may arrange the points differently from those illustrated in the corresponding drawings. On a touch screen using a display device or the user's finger, In one embodiment, the user interface includes: By determining the selection of buttons / icons / parts of the user interface, In one embodiment, the user interface is capable of receiving user input. Input can be received at defined fields of the interface.

[0380] At block 1010, the process 1000 performs a CT image-based, Contains a three-dimensional (3D) representation of the coronary vessels, depicting the defined coronary vessels, and segment labels. Generate a first panel containing an arterial tree that does not contain cardiac tissue between the branches of the arterial tree, depicting An example of such an arterial tree 602 is shown below. , shown in panel 601 of FIG. 6A. In various embodiments, panel 601 is 6. The user interface 600 may be positioned at locations other than those shown.

[0381] At block 1015, the process 1000 selects the coronary vessels in the arterial tree of the first panel. For example, the first input may be received from a panel 601. Receiving by the user interface 600 of the vessels in the arterial tree 602 of At block 1020, in response to the first input, the process 1000 At least one linear multiplanar planar (SMPR) image of at least a portion of the coronary vessels is shown. A second panel can be generated and displayed in the user interface. The SMPR image is displayed in panel 604 of Figure 6A.

[0382] At block 1025, the process 1000 generates a third image showing a cross-sectional image of the selected coronary vessel. A panel can be generated and displayed in the user interface, and cross-sectional images can be selected. It is generated using one of a set of coronary CT images. Each location along the PR view is associated with one of the CT images in the set. thereby allowing selection of a specific location along the coronary vessel for at least one SMPR image. The associated CT image is then displayed in the cross-sectional view in the third panel. can be displayed in panel 606 as shown in FIG. 6A. , the process 1000 performs a CT scan along a selected coronary artery in at least one SMPR image. A second input to the user interface indicating the first position can be received. In one example, a user may use a pointing device to select an SMP At block 1030, the process 10 00 is associated with a cross-sectional image of a third panel, panel 606, in response to a second input. Display the associated CT scan. That is, the cross-sectional image corresponding to the first input is displayed in the SM. The PR image is replaced with a cross-sectional image corresponding to the second input.

[0383] Normalization Device In some instances, the pharmaceutical compositions that have been treated and / or analyzed as described throughout this specification The images used can be normalized using a normalization device, which is discussed further in this section. As will be described in detail, the normalization device serves as a basis for normalizing medical images. and placing the medical image in the field of view to provide an image of a known substance that can be The device may include multiple samples of known substances. The device normalizes the image to patient tissue and / or other material (e.g., plaque) within the image. Allows direct in-image comparison with known materials in the device.

[0384] As briefly mentioned above, in some instances, medical imaging scanners Images with different scalable radiological densities may be created for the same object. For example, the type of medical imaging scanner or device used, as well as the Scan parameters and / or conditions for the specific day and / or time the scan was performed As a result, if two different scans of the same subject are taken, Even if the image is taken in a different way, the resulting medical image may be brighter and / or darker. This can reduce the accuracy of any analytical results processed from the image. Taking such differences into account, in some embodiments, one or more known compounds of the known substance are The normalization device with the sample can be scanned with the subject, resulting in The resulting image of one or more known elements is translated, transformed, or and / or can be used as a reference for normalization.

[0385] Normalization of the medical images being analyzed can be beneficial for several reasons. For example, can be captured under a wide variety of conditions, all of which contribute to the resulting medical In the example where the medical imaging device comprises a CT scanner, a number of different Variables can affect the resulting image. For example, variable image acquisition parameters are Variable image acquisition parameters can affect the resulting image, among others: Kilovoltage (kV), kilovoltage peak (kVp), milliamperes (mA), or gated In some embodiments, the method may include one or more of the following: Triggering methods include, among others, predictive axial triggering, retrospective ECG helical triggering, These parameters include gating, and high-speed pitch helical. Varying either of these results in different results, even when the same subject is scanned. There may be slight differences in the medical images obtained.

[0386] In addition, the type of reconstruction used to prepare the image after scanning can affect the quality of medical images. Examples of types of reconstruction include iterative reconstruction, non-iterative reconstruction, This can include machine learning-based reconstruction, as well as other types of physics-based reconstruction. 11A-11D show different images reconstructed using different reconstruction techniques. In particular, FIG. 11A shows a CT image reconstructed using filtered backprojection; 11B shows the same CT image reconstructed using iterative reconstruction. The two images look slightly different. A normalization device, described below, can be used to normalize the two. The method used to help account for these differences by providing a method for normalizing FIG. 11C shows a CT image reconstructed by using iterative reconstruction. , and FIG. 11D shows the same image reconstructed using machine learning. It is understood that images contain small differences, and the normalization device described herein advantageously , it can be useful to normalize the image to take into account the difference between the two.

[0387] As another example, various types of image capture technologies are used to capture medical images. In the example where the medical imaging device comprises a CT scanner, such image capture The technologies include, among others, dual source scanners, single source scanners, dual Al energy, monochromatic energy, spectral CT, photon counting, and different detector materials As mentioned above, images captured using different parameters may be Even scans of the same subject may appear slightly different. In addition to scanners, other types of medical imaging devices may also be used to capture medical images. These include, for example, x-ray, ultrasound, echocardiography, and intravascular ultrasound (IVUS). VUS), MR imaging, optical coherence tomography (OCT), nuclear medicine imaging PET, single photon emission computed tomography (SPECT) , or near-field infrared spectroscopy (NIRS). Therefore, images captured by these different imaging devices are referred to herein as To facilitate image normalization so that it can be used in the described methods and systems. This can be done.

[0388] In addition, new types of medical imaging techniques are currently being developed: normalization devices The use of the methods and systems described herein may be used to This will enable use with future medical imaging technologies. The use of different or emerging medical imaging technologies may also result in slight differences between images. This may be necessary.

[0389] There may be differences in medical images that can be taken into account using a normalization device. Another factor that may be involved is the use of different contrast agents during medical imaging. Several agents currently exist and others are in development. Regardless of the type of contrast agent used, and even in cases where no contrast agent is used, Normalization can be facilitated.

[0390] These slight differences can be significant in some cases, especially when the analysis of images is performed under different conditions. Artificial intelligence or machine learning algorithms trained or developed using captured medical images When implemented by algorithms, this can adversely affect the analysis of the image. In embodiments, the methods and systems for analyzing medical images described throughout this application include: This may involve the use of artificial intelligence and / or machine learning algorithms. The rhythms can be trained using medical images. In some embodiments, these The medical images used to train the algorithm are normalized images. A normalization device may be included so that the normalization device is trained based on the normalization device. By including the device in subsequent images and normalizing those images, the mechanics Using a learning algorithm, the images captured under a wide variety of parameters, including those mentioned above, are The collected medical images can be analyzed.

[0391] In some embodiments, the normalization devices described herein are different from conventional phantoms. In some cases, conventional phantoms are used to allow the CT machine to accurately measure the appropriate shape. These conventional phantoms can be used periodically to verify that the In some cases, the calibration of the CT machine can be verified. Use the system before each scan, weekly, monthly, yearly, or after CT machine maintenance, as appropriate. However, in particular, conventional phantoms , the resulting medical images across different machines, different parameters, different patients, etc. Does not provide a normalization function that allows normalization of the image.

[0392] In some embodiments, the normalization devices described herein provide this functionality. The normalization device can be used to measure the CT data or various machine types. and / or other medical imaging data generated for normalization across different patients. It allows for normalization of data, e.g., data produced by different manufacturers Different CT devices produce different color and / or gray-scale images In another example, some CT scanning devices can As scanning devices become older, or CT scanning devices are used or based on the environmental conditions surrounding the device during scanning. Different shades and / or grayscale images can be created. , different shades and / or gray scale levels depending on the patient's tissue type, etc. may appear differently in medical image scan data. Data normalization is a common problem when processing CT scan data or other medical imaging data. Various machines or the same machine used at different times and / or across different patients To ensure consistency across various machine-generated datasets , can be important. In some embodiments, the scanning device changes over time. Since the patient may be different and / or scan to scan, the normalization device It should be used every time a medical imaging scan is performed. The normalized device is designed to adapt to the AI ​​algorithms used to analyze patients' medical imaging data. To norm...

Claims

1. 1. A computer-implemented method for tracking plaque progression in a subject using medical image analysis, comprising: accessing, by a computer system, a first medical image of the subject's coronary artery region that is non-invasively obtained; identifying, by the computer system, one or more coronary arteries in the first medical image; segmenting, by the computer system, one or more coronary arteries; normalizing, by the computer system, the first medical image based on image parameters within the first medical image using a normalization algorithm; identifying, by the computer system, one or more plaque regions within the segmented coronary artery; determining, by the computer system, a first set of quantified plaque parameters for one or more regions of the plaque; accessing, by the computer system, a second medical image of the subject's coronary artery region obtained at a later time; and normalizing, by the computer system, the second medical image based on image parameters within the second medical image using a normalization algorithm; determining, by the computer system, a second set of quantified plaque parameters for one or more regions of plaque in the second medical image; generating, by the computer system, a plaque progression assessment by comparing the first set and the second set of quantified plaque parameters; The computer-implemented method, wherein the computer system comprises a processor and a memory.

2. 2. The computer-implemented method of claim 1, wherein the quantified plaque parameters include at least one of plaque volume, plaque surface area, plaque radiodensity, plaque composition, plaque heterogeneity index, or plaque diffusivity.

3. Normalizing the first medical image and the second medical image includes: Identifying image parameters of a known material within a normalization device; and adjusting pixel values ​​in the medical image based on the identified image parameters.

4. generating a quantized color map of the coronary artery and plaque regions; 10. The computer-implemented method of claim 1, further comprising: displaying the quantized color map in a graphical user interface.

5. The computer-implemented method of claim 4 , wherein the quantized color map uses different colors to represent stable and unstable plaque.

6. Generating a plaque progression assessment calculating a change in one or more quantified plaque parameters between the first medical image and the second medical image; and classifying the progression of the plaque as one of regression, stabilization, or progression based on the calculated change.

7. The computer-implemented method of claim 6 , further comprising generating a treatment plan for the subject based on the classification of plaque progression.

8. 1. A system for normalizing medical images for plaque analysis, comprising: a non-transitory computer-readable medium storing instructions; a processor configured to execute instructions; accessing a first medical image of a coronary artery region of a subject obtained non-invasively; identifying one or more coronary arteries within the first medical image; Segmenting one or more coronary arteries; Identifying image parameters within the first medical image; normalizing the first medical image based on the identified image parameters using a normalization algorithm; Identifying one or more plaque regions within the segmented coronary artery; The system determines a first set of quantified plaque parameters for one or more plaque regions based on the normalized first medical image.

9. 9. The system of claim 8, wherein the quantified plaque parameters include at least one of plaque volume, plaque surface area, plaque radiodensity, plaque composition, plaque heterogeneity index, or plaque diffusivity.

10. Normalizing the first medical image includes: Identifying image parameters of known materials within the normalization device; The system of claim 8 , further comprising adjusting pixel values ​​in the first medical image based on the identified image parameters.

11. The processor further comprises: generating quantized color maps of coronary artery and plaque regions; 10. The system of claim 8, further configured to display the quantized color map in a graphical user interface.

12. The system of claim 11 , wherein the quantized color map uses different colors to represent stable and unstable plaque.

13. The processor further comprises: accessing a second medical image of the subject's coronary artery region obtained at a later time; normalizing the second medical image based on image parameters within the second medical image using a normalization algorithm; determining a second set of quantified plaque parameters for one or more regions of plaque in the second medical image; The system of claim 8 , configured to generate a plaque progression assessment by comparing the first set and the second set of quantified plaque parameters.

14. Generating a plaque progression assessment calculating a change in one or more quantified plaque parameters between the first medical image and the second medical image; and classifying the progression of the plaque as one of regression, stabilization, or progression based on the calculated change.

15. 1. A non-transitory computer-readable medium configured to store instructions that, when executed by a processor, cause the processor to perform operations for analyzing plaque in a normalized medical image, the instructions comprising: accessing a first medical image of a coronary artery region of a subject; identifying one or more coronary arteries within the first medical image; normalizing the first medical image based on image parameters within the first medical image using a normalization algorithm; Identifying one or more plaque regions within a coronary artery; determining a first set of quantified plaque parameters for one or more plaque regions; A non-transitory computer-readable medium that generates a plaque assessment based on the first set of quantified plaque parameters.

16. 16. The non-transitory computer-readable medium of claim 15, wherein the quantified plaque parameters include at least one of plaque volume, plaque surface area, plaque radiometric density, plaque composition, plaque heterogeneity index, or plaque diffusivity.

17. Normalizing the first medical image includes: Identifying image parameters of a known material within a normalization device; and adjusting pixel values ​​in the first medical image based on the identified image parameters.

18. The operation further comprises: generating a quantized color map of the coronary artery and plaque regions; and displaying the quantized color map in a graphical user interface.

19. 20. The non-transitory computer-readable medium of claim 18, wherein the quantized color map uses different colors to represent stable and unstable plaque.

20. The operation further comprises: accessing a second medical image of the subject's coronary artery region obtained at a later time; and normalizing the second medical image based on image parameters within the second medical image using a normalization algorithm; determining a second set of quantified plaque parameters for one or more regions of plaque in the second medical image; and generating a plaque progression assessment by comparing the first set and the second set of quantified plaque parameters.

Images