System and method for detecting microcalcification activity

Abstract

A system and method for predicting microcalcification activity in a blood vessel, including either an artery or a vein, comprising: (a) measuring patient data including one or more of the following: the presence and / or amount of coronary plaque or visible disease markers in a vascular tissue sample; the presence and / or amount of healthy tissue in the vascular tissue sample; one or more features defining an abnormal hemodynamic environment in the blood vessel; one or more geometric features associated with vascular remodeling and affecting vascular hemodynamics, and / or one or more material properties affecting vascular hemodynamics; and (b) calculating the microcalcification activity in the blood vessel as a function of the measurements obtained in step (a).

Description

[Technical Field]

[0001]

[0001] The present invention generally relates to vascular tissue 18 In the field of estimating / predicting F-NaF incorporation, in particular, 18 Without using F-NaF PET imaging, 18 The estimation / prediction of F-NaF incorporation is described below with reference to this application. However, it should be understood that the present invention is not limited to this particular field of use. [Background technology]

[0002]

[0002] Nothing discussed in this specification regarding background art should ever be considered to be prior art, or to be widely known in the fields of Australia or around the world, or to be part of common general knowledge.

[0003]

[0003] All references, including any patents or patent applications cited herein, are incorporated herein by reference. No reference is considered to constitute prior art. Discussions of references are to state the claims of their authors, and the applicant reserves the right to object to the accuracy and validity of the cited references. Many prior art publications are referenced herein, but it is clearly understood that these references do not constitute any recognition that any of these documents form part of the common general knowledge in the art in Australia or any other country.

[0004]

[0004] This discussion relates in particular to imaging and analysis of microcalcification activity in the coronary arteries that cause coronary heart disease, but the disclosure herein is not limited to the coronary arteries and is readily applicable to the systemic vascular system of a patient, including at least the carotid arteries, cerebral arteries, aorta, peripheral arteries, or any artery or vein of the vascular system.

[0005]

[0005] Coronary artery disease (CHD) is the leading cause of death worldwide. In 2015, CHD affected 110 million people and killed 8.9 million. This figure accounts for 16% of all deaths, making it the most common cause of death globally. Coronary artery disease is also the sole leading cause of death in Australia (12% of all deaths, one death every 27 minutes).

[0006]

[0006] In 2016, the American Heart Association (HCA) reported that 15.5 million people in the United States aged 20 and older had CHD. The reported prevalence increased with age in both women and men.

[0007]

[0007] Approximately 25–30% of patients hospitalized for heart attacks due to chronic hemorrhage (CHD) either die or are readmitted at least once within three years for further clinical events, representing a significant health burden. Recurrent events occur despite the routine use of several proven risk reduction measures, including coronary angiography and revascularization, statins, dual antiplatelet therapy, beta-blockers, ACE inhibitors, and lifestyle advice in hospitalized patients. Novel prophylactic therapies targeting inflammatory processes associated with plaque rupture are being evaluated, but they are costly and may have undesirable side effects. There is a widely recognized unmet need to improve risk stratification to better apply these therapies to only those patients who would benefit most.

[0008]

[0008] When a patient is suspected of having coronary heart disease (CHD), the treating cardiologist typically performs percutaneous coronary intervention (PCI). PCI requires the insertion of a catheter into the heart via the wrist or groin. Under X-ray imaging, a contrast agent is injected, highlighting blood flow and revealing narrowing of the arteries. This part of the procedure is called coronary angiography and can be recorded for subsequent analysis. Next, the cardiologist guides another catheter towards the occlusion and either opens the occlusion with a balloon or places a stent in the occluded area. PCI procedures help alleviate the symptoms of coronary artery disease and reduce damage to the heart after or during a heart attack. The global PCI market was US$10 billion in 2017 and is expected to exceed US$15 billion by 2023.

[0009]

[0009] During coronary angiography and prior to angioplasty (balloon therapy) or stent placement, important information can be obtained regarding the pressure difference along the diseased artery due to occlusion, which helps in deciding whether or not to use a stent. This is called fractional flow reserve (FFR) and measures the overall pressure difference across the coronary artery stenosis (usually due to atherosclerosis) to determine the likelihood that the stenosis will impair oxygen supply to the myocardium (myocardial ischemia). FFR has become the standard treatment for assessing the physiological significance of coronary artery disease (CAD). When FFR is used to guide percutaneous coronary intervention (PCI), clinical outcomes are improved, the number of stents deployed is reduced, and costs are lowered.

[0010]

[0010] However, even in the countries where FFR is most frequently used, FFR is used in less than 10% of PCI procedures, and the number of diagnostic cases is far smaller; therefore, despite these advantages, clinical adoption remains extremely low. This is due to a combination of factors related to practicality, time, and cost. Calculating "virtual" FFR (vFFR) from coronary angiography (CAG) using computational fluid dynamics (CFD) provides the advantages of physiologically guided PCI without the drawbacks that limit invasive techniques.

[0011]

[0011] vFFR can be calculated based on a three-dimensional (3D) reconstruction of coronary artery anatomical structures from coronary CT angiography (imaging) using CFD modeling. In recent years, the FDA has approved the clinical implementation of FFR derived from computational modeling. Optimized methods for determining vFFR (e.g., vFFR derived from 3D-QCA) can yield results in under four minutes or near real-time. While initial results have been promising, the accuracy of vFFR calculations is limited by the accuracy with which the model represents coronary artery and lesion morphology (imaging and reconstruction) as well as physiological parameters (adjustment of boundary conditions) on an individual patient basis. The last major hurdle to a reliable vFFR tool is the application of patient-specific adjustment strategies representing hyperemission flow or myocardial resistance.

[0012]

[0012] In patients with comorbid conditions that are particularly high-risk for cardiac events, a superior imaging system can be used to establish an optimized treatment plan for stent implantation. Recent network meta-analyses have clearly demonstrated the superiority of intravascular ultrasound (IVUS) and / or optical coherence tomography (OCT) over coronary angiography guidance (Buccheri et al., 2017). In particular, angiography is known to have limitations in evaluating vessel size and plaque load, lesion calcium and eccentricity, stent expansion, and geographic errors and complications, so IVUS and OCT are now used to answer questions that arise during routine PCI. The use of OCT is rapidly replacing older technologies such as IVUS due to its 10 times higher image resolution and faster image acquisition time, for example, in Japan, OCT is used in approximately 80% of all PCIs. Therefore, experts believe that OCT analysis will become an important tool and automated image analysis will be urgently needed.

[0013]

[0013] One of the main advantages of using OCT compared to other imaging methods is that it can measure thin capsular fibrous plaque (TCFA), which is the fibrous edge that separates the necrotic core of a plaque from the lumen of the artery. Rupture of a TFCA means that the contents of the necrotic core leak into the bloodstream and cause occlusion downstream. The most dangerous TCFA thickness is less than 65 μm, which can only be measured using OCT. While TCFA thickness is one measure of risk, the unpredictability of coronary artery disease is due to the behavior of unstable and stable plaques, and currently there is no way to assess plaque stability.

[0014]

[0014] In addition to TCFA, many other biomarkers of plaque stability can be visualized and quantified on OCT. Currently, the characteristics of clinical subjects are: (1) Lipid region; (2) Surface calcium; (3) Deep calcium; (4) Plaque-free walls; (5) Thrombus; (6) Macrophages; (7) Microchannels; (8) Cholesterol crystals; and of course, (9) It is a thin-capsule fibrous plaque.

[0015]

[0015] Each of these contributes to the risk of plaque rupture, which can lead to heart attack and potential death. While the importance of these features is recognized, currently they must be manually annotated and quantified on each OCT image (typically around 500 per arterial segment). This is not only extremely time-consuming but also introduces user-to-user variability.

[0016]

[0016] In addition to image-based biomarkers for plaque stability, there is growing evidence suggesting that biomechanical aspects are important for plaque assessment. From a biomechanical standpoint, two forces are typically considered: shear stress and structural stress.

[0017]

[0017] Shear stress is the frictional force acting on the inner walls of blood vessels (i.e., arteries or veins) and plaque due to flowing blood. Computational fluid dynamics (CFD) is the primary method used to calculate the shear stress acting on the inner walls of a patient's arteries or veins. A certain level of shear stress is required for normal physiological function, and low shear stress is a well-established predictor of plaque progression and future clinical events. Currently, there are no commercially available tools to provide clinicians with usable vascular shear stress information.

[0018]

[0018] The structural stresses acting on blood vessels and plaque due to blood pressure also have significant clinical value. When structural stresses exceed the structural strength of the tissue, plaque ruptures. This has been the focus of major research activities for many years, and significant progress has been made. However, as with shear stress, there are currently no commercially available tools that clinicians can use to provide these important data.

[0019]

[0019] At present, there is no method for semi-automatically or automatically analyzing OCT image data across the lumen, or for calculating the important biomechanical forces that destabilize plaques and cause plaque rupture (heart attack) that threatens life. Further, clinicians still need an intravascular imaging and software-based pre-PCI treatment planning tool that can comprehensively select the optimal stent size, length, and placement to minimize further damage to the artery.

[0020]

[0020] The uptake of 18 F-sodium fluoride ( 18 F-NaF) detected by positron emission tomography (PET) has been associated with the characteristics of high-risk plaque coronary arteries and future clinical events (Joshi et al., 2014, 18 F-fluoride positron emission tomography for identification of ruptured and high risk coronary atherosclerotic plaques; a prospective clinical trial. Lancet, 383, 705-13; Lee et al., 2017, Clinical Relevance of (¹⁸)F-Sodium Fluoride Positron-Emission Tomography in Noninvasive Identification of High-Risk Plaque in Patients with Coronary Artery Disease. Circ Cardiovasc Imaging, 10). 18 The areas of 18 F-NaF uptake indicate microcalcification activity in the arterial wall, and these areas will develop into future macrocalcifications. Recently, 18F-Sodium Fluoride Uptake Predicts Outcomes in Patients With Coronary Artery Disease. J Am Coll Cardiol, 75, 3061-74). Kwiecinski et al., they, 18 F-NaF uptake in blood vessels 18 Based on the amount and intensity of F-NaF PET activity, it was converted into an equivalent measure called coronary microcalcification activity (CMA), which represents overall disease activity within blood vessels. Therefore, as an early indicator of future adverse events... 18 The detection, visualization, and quantification of F-NaF uptake have significant clinical relevance. However, this imaging technique is expensive, only available in specialized centers, and requires considerable technical expertise to analyze the images. Furthermore, patients are exposed to additional radiation, and some patients are intolerant of imaging radiotraces.

[0021]

[0021] 18 F-NaF tracers, along with other blood-derived particles, are transported through the bloodstream and bind to early active vascular calcification (Irkle et al., 2015, Identifying active vascular microcalcification by 18 F-sodium fluoride positron emission tomography.Nature Communications,6,7495). 18F-NaF tracers are therefore influenced by hemodynamics (transport to plaque sites) and the distribution of plaque within the coronary arteries. Proliferating / active coronary plaques are thought to be preferential NaF binding sites, triggered by cell death and inflammation, as microcalcification activity occurs (Chen and Dilsizian, 2013, Targeted PET / CT Imaging of Vulnerable Atherosclerotic Plaques: Microcalcification with Sodium Fluoride and Inflammation with Fluorodeoxyglucose. Current Cardiology Reports, 15, 364).

[0022]

[0022] It has been shown that blood supply to the coronary arteries depends on geometric measurements such as the diameter / internal diameter of the vessels, the length of the vessels, and the muscle mass of the myocardium (Zamir et al., 1992, Relation between diameter and flow in major branches of the arch of the aorta. J Biomech, 25, 1303-10; Choy and Kassab, 2008, Scaling of Myocardial Mass to Flow and Morphometry of Coronary Arteries. Journal of Applied Physiology (Bethesda, Md.: 1985), 104, 1281-1286). The propagation of coronary artery plaque alters the local internal diameter and shape of the vessels through remodeling (Libby and Theroux, 2005, Pathophysiology of coronary artery disease. Circulation, 111, 3481-8). This change in shape is often explained by geometrical measures such as area and eccentricity (Hausmann et al., 1994, Lumen and plaque shape in atherosclerotic coronary arteries assessed by in vivo intracoronary ultrasound. Am J Cardiol, 74, 857-63), and is associated with increased structural stress within the plaque (Costopoulos et al., 2017, Plaque Rupture in Coronary Atherosclerosis Is Associated with Increased Plaque Structural Stress. JACC Cardiovasc Imaging, 10, 1472-1483).Plaque characteristics are associated with both high and low endothelial wall shear stress (WSS), which are fluid frictional forces acting on the endothelium (Koskinas et al., 2009, The role of low endothelial shear stress in the conversion of atherosclerotic lesions from stable to unstable plaque. Curr Opin Cardiol, 24, 580-90). The WSS value at a particular location depends on many factors, including blood supply, blood properties (e.g., viscosity), and the inner diameter and lumen shape of the vessel (e.g., eccentricity, curvature (Myers et al., 2001, Factors Influencing Blood Flow Patterns in the Human Right Coronary Artery. Annals of Biomedical Engineering, 29, 109-120)). Low wall shear stress (WSS) stimulates the atherosclerosis phenotype and promotes arterial inflammation, and the expression of adhesion proteins and chemokines works together to capture leukocytes from the bloodstream into the blood vessels (Malek et al., 1999, Hemodynamic shear stress and its role in atherosclerosis. Jama, 282, 2035-42; Lawrence et al., 1987, Effect of flow on polymorphonuclear leukocyte / endothelial cell adhesion. Blood, 70, 1284-90; and Gijsen et al., 2019, Expert recommendations on the assessment of wall shear stress in human coronary arteries: existing methodologies, technical considerations, and clinical applications. European Heart Journal, 40, 3421-3433).Furthermore, low wall shear stress (WSS) is present in the region of recirculation flow and low near-wall velocity, which helps to aggregate blood-derived particles near the endothelium (Gijsen et al., 2019, Expert recommendations on the assessment of wall shear stress in human coronary arteries: existing methodologies, technical considerations, and clinical applications. European Heart Journal, 40, 3421-3433).These hemodynamic mechanisms and associated endothelial dysfunction help explain why plaque progression occurs in areas of low shear stress (Chatzizisis et al., 2008, Prediction of the Localization of High-Risk Coronary Atherosclerotic Plaques on the Basis of Low Endothelial Shear Stress. Circulation, 117, 993-1002; Stone et al., 2012, Prediction of Progression of Coronary Artery Disease and Clinical Outcomes Using Vascular Profiling of Endothelial Shear Stress and Arterial Plaque Characteristics: The PREDICTION Study. Circulation; Kumar et al., 2018, Low Coronary Wall Shear Stress Is Associated with Severe Endothelial Dysfunction in Patients with Nonobstructive Coronary Artery Disease. JACC Cardiovasc Interv,11,207-2080;Yamamoto et al., 2017, Low Endothelial Shear Stress Predicts Evolution to High-Risk Coronary Plaque Phenotype in the Future.Circulation:Cardiovascular Interventions,10,e005455; and Bourantas et al., 2019, Implications of the local hemodynamic forces on the phenotype of coronary plaques.Heart,heartjnl-2018-314086).

[0023]

[0023] We consider the same environment to facilitate the detection of microcalcification activity through the retention, infiltration, and binding of local NaF tracers.

[0024]

[0024] Attempts to clinically use both shear stress and structural stress are currently limited by significant difficulties such as automated image analysis, computation time, and the lack of critical boundary condition data for simulations. Solutions to these problems have not yet been described. Furthermore, 18 Quantitative data on F-NaF uptake (i.e., active microcalcification) shows clinical promise, but is expensive and inaccessible. 18 F-NaF PET hardware, 18 There is a strong need for expertise in nuclear medicine and imaging analysis to access and interpret F-NaF data, and to overcome current requirements regarding patient intolerance to excessive radiation and radiotraces.

[0025]

[0025] The present invention was developed in response to this background. In particular, the present invention aims to overcome or at least improve one or more of the drawbacks of the prior art described above, or to provide consumers with a useful or commercial alternative. [Overview of the project]

[0026]

[0026] The object of the present invention is to overcome or improve at least one of the drawbacks of the prior art or to provide a useful alternative.

[0027]

[0027] One embodiment provides a computer program product for performing the method described herein.

[0028]

[0028] One embodiment provides a non-transitive transport medium for holding computer executable code that causes a processor to perform the methods described herein when executed on a processor.

[0029]

[0029] One embodiment provides a system configured to perform the method described herein.

[0030]

[0030] The present invention relates to the principle of general application in that it provides a method for measuring microcalcification activity in arteries (preferably coronary arteries) using anatomical measurements, imaging measurements, plaque measurements and hemodynamic measurements. In particular, the present invention corresponds to the measurement of target areas and lesions within healthy and / or diseased vascular systems and provides means for identifying / quantifying / distinguishing these conditions. The list of possible inputs and outputs for use in the method is extensive, and microcalcification prediction is a result that can / may be derived from the method.

[0031]

[0031] According to the present invention, the inventors provide a method for measuring microcalcification activity in blood vessels (preferably coronary arteries).

[0032]

[0032] According to a first aspect of the present invention, a method for predicting intravascular microcalcification activity is provided. The blood vessel may include either arteries or veins. The method may include (a) measuring one or more of the following: (a) the presence and / or amount of coronary artery plaque or visible disease markers in a vascular tissue sample; and / or the presence and / or amount of healthy tissue in a vascular tissue sample; and / or one or more features that define an abnormal hemodynamic environment in a blood vessel; and / or one or more geometric features that affect the hemodynamics of a blood vessel in association with vascular remodeling; and / or one or more material properties that affect vascular hemodynamics. The method may further include (b) calculating intravascular microcalcification activity as a function of the measurements obtained in step (a).

[0033]

[0033] According to a particular configuration of the first embodiment, a method is provided for predicting microcalcification activity in a blood vessel, including either an artery or a vein, the method being: (a) A step of measuring one or more of the following: (i) the presence and / or amount of coronary artery plaque or visible disease markers in the vascular tissue sample; and / or (ii) The presence and / or amount of healthy tissue in the vascular tissue sample; and / or (iii) One or more characteristics that define an abnormal hemodynamic environment within a blood vessel; and / or (iv) One or more geometric features associated with vascular remodeling that affect intravascular hemodynamics; and / or (v) The step of measuring one or more material properties that affect vascular hemodynamics; (b) The step of calculating intravascular microcalcification activity as a function of the measurements obtained in step (a) is included.

[0034]

[0034] According to a second aspect of the present invention, a method for predicting intravascular microcalcification activity is provided. The method may include the step of acquiring training data. The training data may consist of general patient data including data on multiple patients and multiple data; and microcalcification activity data (μCA) from multiple patients at one or more anatomical locations. The method fits a multivariate function / model by calculating a function from the input patient data and microcalcification activity data and input training dataset [A Tr B Tr , C Tr , D Tr New data obtained in the same way as...[a new , b new , c new d new ...] may further include the step of estimating or predicting the μCA of the function, wherein the function is: The filename is TIFF0007898507000001.tif6170.

[0035]

[0035] The method evaluates a multivariate model by evaluating a pre-fitted function and obtains a set of estimates of microcalcification activity (μCA) for a new set of function inputs. Est The method may further include the step of obtaining a set of estimates of microcalcification activity (μCA).Est ) is a set of known / corresponding values ​​(μCA) of microcalcification activity data derived from a set of corresponding data collected for the same patient and used to generate the function input. Te The step may further include calculating the error estimate using the error function Ef by comparing it with: TIFF0007898507000002.tif6170

[0036]

[0036] The method may further include a step of checking the error estimates and evaluating the fit of the model.

[0037]

[0037] According to a specific configuration of the second embodiment, a method is provided for predicting intravascular microcalcification activity, the method being: (i) data on multiple patients, and general patient data including multiple data; (ii) A step of obtaining training data consisting of microcalcification activity data (μCA) from multiple patients at one or more anatomical locations; A multivariate function / model is fitted by calculating a function from input patient data and microcalcification activity data, and input training dataset [A Tr B Tr , C Tr , D Tr New data obtained in the same way as...[a new , b new , c new d new A step of estimating or predicting μCA for ....], wherein the function is: TIFF0007898507000003.tif7170, step and; Evaluate multivariate models by evaluating pre-fitted functions and set up estimates of microcalcification activity (μCA) for a new set of function inputs. Est The steps to obtain ) and; Set of estimated values ​​for microcalcification activity (μCA Est) is a set of known / corresponding values ​​(μCA) of microcalcification activity data derived from a set of corresponding data collected for the same patient and used to generate function inputs. Te The step of calculating an error estimate using the error function Ef by comparing it with ), TIFF0007898507000004.tif7170, step and; This includes the step of checking the error estimates and evaluating the fit of the model.

[0038]

[0038] A third aspect of the present invention provides a method for predicting intravascular microcalcification activity. The method may include receiving training data associated with one or more of the following: the presence and / or amount of coronary artery plaque or visible disease markers in a vascular tissue sample; and / or the presence and / or amount of healthy tissue in a vascular tissue sample; and / or one or more features that define an abnormal hemodynamic environment in a blood vessel; and / or one or more geometric features associated with vascular remodeling and affecting intravascular hemodynamics; and / or one or more material properties that affect vascular hemodynamics. The method may further include determining one or more training features based on the training data values. The method may further include determining one or more training labels associated with one or more training features. The method may further include building a predictive model using a computer to determine intravascular microcalcification activity. The step of building a predictive model may include inputting one or more training features and one or more training labels associated with one or more training features into a machine learning algorithm. The steps of building a predictive model may further include: determining a predictive model from a machine learning algorithm to receive new data associated with blood vessels; and determining predictive labels based on the new data.

[0039]

[0039] According to a specific configuration of the third aspect, a method is provided for predicting intravascular microcalcification activity, the method being: (i) the presence and / or amount of coronary artery plaque or visible disease markers in the vascular tissue sample; and / or (ii) The presence and / or amount of healthy tissue in the vascular tissue sample; and / or (iii) One or more characteristics that define an abnormal hemodynamic environment within a blood vessel; and / or (iv) One or more geometric features associated with vascular remodeling that affect intravascular hemodynamics, and / or (v) A step of receiving training data associated with one or more material properties that affect vascular hemodynamics, The steps include determining one or more training features based on training data values; The steps include determining one or more training labels associated with one or more training features; A step of using a computer to construct a predictive model for determining intravascular microcalcification activity, wherein the step of constructing the predictive model is: The steps include inputting one or more training features and one or more training labels associated with those training features into a machine learning algorithm; The process includes the step of building a predictive model, which includes the step of determining a predictive model for receiving new data associated with blood vessels from a machine learning algorithm and determining predictive labels based on the new data.

[0040]

[0040] A fourth aspect of the present invention provides a computer-implemented method for measuring intravascular microcalcification activity. The computer-implemented method may include the step of measuring one or more of the following: (a) the presence and / or amount of coronary artery plaque or visible disease markers in a vascular tissue sample; and / or the presence and / or amount of healthy tissue in a vascular tissue sample; and / or one or more features that define an abnormal hemodynamic environment in a blood vessel; and / or one or more geometric features that affect intravascular hemodynamics in association with vascular remodeling; and / or one or more material properties that affect vascular hemodynamics. The computer-implemented method may further include the step of (b) calculating intravascular microcalcification activity as a function of the measurements obtained in step (a) using a trained machine learning model.

[0041]

[0041] According to a specific configuration of the fourth aspect, a computer-implemented method for measuring intravascular microcalcification activity is provided, the method being: (a) A step of measuring: (i) the presence and / or amount of coronary artery plaque or visible disease markers in the vascular tissue sample; and / or (ii) The presence and / or amount of healthy tissue in the vascular tissue sample; and / or (iii) One or more characteristics that define an abnormal hemodynamic environment within a blood vessel; and / or (iv) One or more geometric features associated with vascular remodeling that affect intravascular hemodynamics, and / or (v) The step of measuring one or more material properties that affect vascular hemodynamics; (b) The step of using a trained machine learning model to calculate intravascular microcalcification activity as a function of the measurements obtained in step (a).

[0042]

[0042] The first machine learning model may include a first training regression model.

[0043]

[0043] The blood vessel may be one or more of the coronary arteries, carotid arteries, cerebral arteries, aorta, peripheral arteries, or veins.

[0044]

[0044] A fifth aspect of the present invention provides information for predicting the uptake of 18F-NAF in a patient's vascular tissue. The method may include the step of using image processing means on patient image data to measure vascular biomarkers indicating the presence and / or amount of visible disease markers in vascular tissue associated with coronary plaque or the progression of cardiovascular disease. The method may further include the step of using a processor to calculate microcalcification activity in vascular tissue as a function of the measured values.

[0045]

[0045] According to a particular configuration of the fifth aspect, a method is provided for providing information for predicting the uptake of 18F-NAF in a patient's vascular tissue, the method comprising: using image processing means on patient image data to measure the presence and / or amount of visible disease markers in the vascular tissue associated with coronary plaque or the progression of cardiovascular disease; and using a processor to calculate microcalcification activity in the vascular tissue as a function of the measured values.

[0046]

[0046] According to a sixth aspect of the present invention, a computer system is provided comprising at least one processor and at least one memory device for storing patient data. The stored patient data may be related to the presence and / or amount of coronary artery plaque or visible disease markers in a vascular tissue sample; and / or the presence and / or amount of healthy tissue in a vascular tissue sample; and / or one or more features that define an abnormal hemodynamic environment in a blood vessel; and / or one or more geometric features associated with vascular remodeling and affecting hemodynamics in a blood vessel; and / or one or more material properties that affect vascular hemodynamics. The at least one processor may be configured to use a trained machine learning model to calculate microcalcification activity in a blood vessel as a function of patient data.

[0047]

[0047] According to a particular configuration of the sixth aspect, a computer system is provided, the computer system is: At least one processor; At least one memory device: (i) the presence and / or amount of coronary artery plaque or visible disease markers in the vascular tissue sample; and / or (ii) The presence and / or amount of healthy tissue in the vascular tissue sample; and / or (iii) One or more characteristics that define an abnormal hemodynamic environment within a blood vessel; and / or (iv) One or more geometric features associated with vascular remodeling that affect intravascular hemodynamics; and / or (v) A memory device that stores patient data relating to one or more material properties that affect vascular hemodynamics, At least one processor is configured to use a trained machine learning model to calculate intravascular microcalcification activity as a function of patient data.

[0048]

[0048] Any one of the above embodiments of the method may include the step of measuring microcalcification activity in any target blood vessel, including coronary arteries, carotid arteries, cerebral arteries, aorta, peripheral arteries, or veins.

[0049]

[0049] According to a further aspect of the present invention, a method is provided for predicting intravascular microcalcification activity, the method being: The step of obtaining training data (Tr), wherein the training data (Tr) is: General patient data [A] includes data on multiple patients and multiple data that may further include image data and / or biomechanical data at one or more anatomical locations. Tr B Tr , C Tr , D Tr ...], and, The process consists of steps comprising microcalcification activity data (μCA) from multiple patients at one or more anatomical locations, Input patient training data and input training dataset A Tr B Tr , C Tr , D Tr ...new data a obtained using the same method new , b new , c new d new ...a step of fitting a multivariate function / model by calculating a function from microcalcification activity data that can newly estimate / predict μCA for ..., wherein the function is The file is TIFF0007898507000005.tif6170, and the steps are as follows: Evaluate multivariate models by evaluating a pre-fitted function f, and train the set [A Te B Te , C Te , D Te ...] Microcalcification activity (μCA) for a new set of function inputs, which is a new set of general patient test data (Te) that was not included in the previous set. Est A step of obtaining a set of estimates of ), The file is TIFF0007898507000006.tif6170, and the steps are as follows: The step of calculating an error estimate using an error function Ef by comparing a set of estimated values ​​(Est) of microcalcification activity (μCAEst) with a set of known / corresponding values ​​of microcalcification activity data (μCATe) derived from a set of corresponding data collected for the same patient and used to generate function inputs [ATe, BTe, CTe, DTe...], The file is TIFF0007898507000007.tif7170, and the steps are as follows: The process includes a step of checking the error estimate and evaluating the fit of the model. If the error estimate meets a set of desired criteria, such as the required accuracy, precision, and sensitivity to input data, where the error is small and the results are statistically significant, the model is considered fit for the purpose and may be used to predict microcalcification activity.

[0050]

[0050] According to a further aspect of the present invention, a non-temporary computer-readable medium is provided which stores computer program instructions for measuring microcalcification activity in blood vessels (preferably coronary arteries), wherein, when executed by a processor, the computer program instructions are sent to the processor: (a) A step of measuring, (i) the presence and amount of plaque or visible disease markers in the vascular tissue sample; (ii) The presence and / or amount of healthy tissue in the vascular tissue sample; (iii) One or more characteristics that define an abnormal hemodynamic environment within a blood vessel; (iv) One or more geometric features associated with vascular remodeling and affecting intravascular hemodynamics; and / or (v) A step of measuring one or more of the material properties that affect vascular hemodynamics, (b) The procedure includes the step of calculating the intravascular microcalcification activity as a function of the measurements obtained in step (a).

[0051]

[0051] According to a further aspect of the present invention, a non-temporary computer-readable medium is provided which stores computer program instructions for measuring microcalcification activity in blood vessels (preferably coronary arteries), wherein, when executed by a processor, the computer program instructions are sent to the processor: [A Tr B Tr , C Tr , D Tr General patient data such as, ..., The steps include obtaining training data consisting of microcalcification activity data (μCA) from multiple patients at one or more anatomical locations, A step of fitting a multivariate function / model by calculating a function from input patient data and microcalcification activity data that can estimate / predict μCA of new data acquired in the same way as input training data, wherein the function is: The file is TIFF0007898507000008.tif7170, and the steps are as follows: A set of estimates of microcalcification activity for a new set of function inputs (μCA), which is a new set of common patient examination data not included in the training set. Est The step of evaluating a multivariate model by evaluating a pre-fitted function f in order to obtain [A Te B Te , C Te , D Te ...] includes data relating to multiple patients and multiple data which may further include image data and / or biomechanical data at one or more anatomical locations, The file is TIFF0007898507000009.tif6170, and the steps are as follows: Using the error function Ef, a set of estimates of microcalcification activity (μCA) Est ) to (μCA Te The step of calculating an error estimate by comparing it with a set of known / corresponding values ​​of ), The file is TIFF0007898507000010.tif7170, and the steps are as follows: The process includes the steps of checking the error estimates and evaluating the fit of the model. If the error estimates meet a desired set of criteria, such as the required accuracy, precision, and sensitivity to the input data, the model is considered fit for the purpose and may be used to predict microcalcification activity.

[0052]

[0052] According to a further aspect of the present invention, a non-temporary computer-readable medium is provided which stores computer program instructions for measuring microcalcification activity in a patient's artery, and when the computer program instructions are executed by a processor, the processor: The steps include receiving a multivariate function / model that includes a function calculated from a training model of input patient data and microcalcification activity CA data that can estimate / predict μCA, The steps include receiving general patient data of a patient that matches the input patient data of the training model, The value of microcalcification activity (μCA) in the patient's arteries.Est The process involves the steps of calculating ) and performing the steps including .

[0053]

[0053] Any one of the above embodiments may further include one or more of the following features in any combination.

[0054]

[0054] The method may include the step of measuring microcalcification activity in any target blood vessel, including coronary arteries, carotid arteries, cerebral arteries, aorta, peripheral arteries, or veins.

[0055]

[0055] Patient data and / or training data may include, but are not limited to, biomarker data relating to one or more features of a clinical subject, including lipid regions; surface calcium; deep calcium; plaque-free walls; thrombi; macrophages; microchannels; cholesterol crystals; or thin-capsulated fibrous plaque associated with one or more blood vessels of the patient.

[0056]

[0056] Patient data and / or training data may include one or more image data, including but not limited to OCT, angiography, computed tomography (CT); CT angiography image data. The image data may refer to a common reference frame or a common coordinate system. The image data may be converted to a common reference frame. The image data may provide a complete representation of the imaged patient's arterial tree. The representation may be a two-dimensional and / or three-dimensional image representation.

[0057]

[0057] The method may include interpolation of image data between image frames and / or between anatomical landmarks.

[0058]

[0058] The method may include the step of performing a structural simulation at any location of the object along the imaged blood vessel. The image data may be segmented by the user to identify different regions of plaque and the vessel wall within the imaged blood vessel.

[0059]

[0059] The method may include a step of estimating biomaterial properties based on the tissue stiffness ratio. The tissue stiffness ratio may be based on biomaterial properties similar to those of other areas of the patient's cardiovascular system.

[0060]

[0060] The method may include, but is not limited to, steps of providing measurements of vascular condition, including: intraluminal shear stress; plaque structural stress; plaque feature analysis; microcalcification activity; virtual stent placement; vascular wall feature analysis; thin cap measurement; multimodal imaging; vascular branching; coronary flow reserve ratio; rapid time frame; and VR virtualization.

[0061]

[0061] Microcalcification activity in blood vessels, such as arteries or veins, including coronary arteries, may be measured using positron emission tomography (PET). In this method, any set of measurements may be fitted to a model (via regression or machine learning techniques) to obtain precise microcalcification activity results.

[0062]

[0062] The presence and / or amount of vascular plaque may be measured based on well-established geometric disease markers from intravascular optical coherence tomography (OCT) images, specifically, the presence of lipids, calcium and macrophages (bright spots) within the plaque. For example, mean lipid arc [°], mean calcium arc [°], and mean bright spot measurements may be obtained. Additional geometric measurements indicating disease are related to the diameter, area, volume, thickness, twist and eccentricity of the vessel, as well as all combinations of these measurements. Similarly, these measurements may be obtained by other imaging techniques common in clinical practice.

[0063]

[0063] The presence and / or amount of healthy tissue may be measured based on the measurement of the amount of visible healthy arterial wall using intravascular OCT imaging, for example, plaque-free wall (PFW) is inversely correlated with disease. For example, a measurement of the mean arc [°] of plaque-free wall may be obtained. Similarly, this measurement may be obtained by any other imaging method typical in the clinical setting.

[0064]

[0064] In this method, measurements of abnormal hemodynamic environments, such as the retention of blood-derived particles or abnormal WSS, may be estimated using computational fluid dynamics (CFD) simulations or other methods that can directly estimate wall shear stress (WSS) via imaging techniques. For example, by measuring low shear region (LSA): low WSS region [%] or high shear region (HSA): high WSS region [%] or mean WSS [Pa]. Additional hemodynamic metrics may include, but are not limited to, the oscillatory shear index (OSI), relative residence time (RRT), low oscillatory shear (LOS), endothelial activation potential (ECAP), velocity-derived field function (e.g., vorticity), pressure drop, or any gradient of the aforementioned metrics (e.g., gradient of WSS).

[0065]

[0065] Measurements of geometric features associated with vascular remodeling and hemodynamic effects may be obtained from intravascular OCT images (circumferential and eccentric) and computed tomography angiography (CCTA). For example, by measuring mean circumference [mm] (using OCT), mean eccentricity (using OCT), arterial wall / layer thickness, and / or ventricular muscle mass [g] (using CT).

[0066]

[0066] Material properties that affect hemodynamics, such as % hematocrit values, may be measured during routine blood sampling and may also be used to adjust the viscosity model used to calculate WSS in CFD.

[0067]

[0067] The method may enable the evaluation of treatment options based on one or more target measurement criteria.

[0068]

[0068] In this method, the imaging diagnostic methods used to obtain the measurements of this method may include one or more of the following: computed tomography (CT); magnetic resonance imaging (MRI); ultrasound; intravenous ultrasonography (IVUS); optical coherence tomography (OCT); single-photon emission computed tomography (SPECT), PET, or NaF PET.

[0069]

[0069] The method may include a fitting process for a multivariate function, such as parametric regression or nonparametric regression. A portion of the training data may be saved as validation data during the fitting process. The validation data may be used to estimate the prediction error of the model selection. Nonparametric regression may include methods such as kernel regression and machine learning support vector machines. Parametric fitting may include a step of using a parametric machine learning algorithm or a conventional optimization method to find the minimum value of the objective function (e.g., "sum of squared errors"). For nonlinear functions, a specific example suitable for use in the above method may be a direct search method of multidimensional unconstrained minimization, such as the Nelder-Mead simplex method. Parametric optimization may utilize commonly used functional forms related to biological relationships, such as allometric scaling functions.

[0070]

[0070] Additional purposes, advantages and novel features are described below or will become apparent to those skilled in the art by examining the drawings and the following detailed descriptions of some non-limiting embodiments.

[0071]

[0071] Notwithstanding any other forms that may be within the scope of the present invention, preferred embodiments / multiple embodiments of the present invention will be described by reference to the accompanying drawings, merely as examples. [Brief explanation of the drawing]

[0072] [Figure 1] Figure 1 outlines a machine learning system and methodology for predicting plaque stability in order to provide a clinical decision support software application. [Figure 2] Figure 2 shows the training and testing process of the method of the present invention. [Figure 3] Figure 3 shows a graphical representation of the measured values ​​for vascular tortuosity. [Figure 4]Figure 4 shows the region of endothelial shear stress in coronary artery segments below a specific threshold, expressed in Pascals. [Figure 5] Figure 5 shows a graphical representation of the arc / angle measurements obtained from the OCT image. [Figure 6] Figure 6 shows the region of endothelial shear stress in coronary artery segments below a specific threshold, in Pascals, and the corresponding 18F-NaF TBR within the segment. [Figure 7] Figure 7 shows a graph of the correlation between microcalcification training data and model output data obtained according to the method disclosed herein. [Figure 8] Figure 8 shows the correlation between microcalcification test data and model output data obtained according to the method disclosed herein. [Figure 9] Figure 9 shows the optimized fit for the maximum TBR using all the measurements in Table 1. [Figure 10] Figure 10 shows the optimized fit for the maximum TBR using a subset of the measured values ​​(top); and the average relative contribution of these five measured values ​​to the model approximation (bottom). [Figure 11] Figure 11 shows the optimized fit for the maximum TBR using a subset of categorical measurements obtained from intravascular OCT images (top); and the mean relative contribution of OCT measurements to the model approximation (bottom). [Figure 12] Figure 12 shows an example of an overfitted neural network model, including a two-layer feedforward network with sigmoid latent neurons and linear output neurons. [Figure 13] Figure 13 shows a block diagram illustrating an example computer system that can implement one embodiment of System 100. [Modes for carrying out the invention]

[0073]

[0072] Note that in the following description, the same or identical reference numerals in different embodiments indicate the same or identical features.

[0074]

[0073] The present invention is based on the discovery that any set of measurements can be fitted to a model via regression or machine learning techniques to obtain precise microcalcification activity results, which are typically measured using NaF PET. The systems and methods disclosed herein describe an unexpected realization of correlating sodium fluoride (NaF) uptake with features related to plaque anatomical structure, hemodynamic environment, etc., through the use of an AI modeling method from patient image data that uses AI directly on patient image data to identify and reconstruct anatomical structures, and the AI ​​modeling method is used to extract derived data for use in regression models to determine the microcalcification activity of the patient's arteries.

[0075]

[0074] Despite the significant clinical promise of determining microcalcification activity, obtaining measurements from current sodium fluoride-PET methods is costly, requires additional preparation and acquisition time, complicates the images, and is not widely available. Therefore, sodium fluoride-PET is unlikely to reach routine clinical use. The systems and methods disclosed herein describe a framework for creating AI and regression models configured to provide the ability to determine information about microcalcification activity from non-sodium fluoride-PET related data in a manner not previously considered or implemented. The systems and methods disclosed herein describe a solution to the technical difficulties in obtaining sodium fluoride-PET, addressing the long-term problem of identifying individuals at highest risk of heart attack and those who would benefit most from intervention.

[0076]

[0075] Therefore, the present invention addresses the principle of general application in that it provides a method for measuring microcalcification activity in blood vessels (e.g., coronary arteries) without requiring the performance of NaF PET imaging.

[0077]

[0076] Features of the present invention will be described in more detail in the following sections of this description which describe non-limiting aspects, embodiments and examples of the present invention. This description is included for illustrative purposes of the present invention. The following description should not be understood as limiting the broad overview or disclosure of the present invention described above.

[0078] overview

[0077] Those skilled in the art will understand that the inventions described herein are subject to modifications and alterations other than those specifically described. The present invention includes all such modifications and alterations. The present invention also includes, individually or collectively, all of the steps, features, formulations and compounds referred to or shown herein, and any and all combinations or any two or more of the steps or features.

[0079]

[0078] Each document, reference, patent application, or patent cited herein is explicitly incorporated herein in its entirety by reference, meaning that it should be read and considered by the reader as part of the text. The documents, references, patent applications, or patents cited herein are not repeated in this text solely for the sake of brevity.

[0080]

[0079] Any manufacturer's descriptions, explanations, product specifications and product sheets relating to any product described in any document mentioned herein or incorporated herein by reference may be incorporated herein by reference and used in the practice of the present invention.

[0081]

[0080] The present invention is not limited in scope by any of the specific embodiments described herein. These embodiments are for illustrative purposes only. Functionally equivalent products, formulations and methods are clearly within the scope of the present invention as described herein.

[0082]

[0081] The present invention as described herein may include a range of one or more values ​​(e.g., dose, concentration, etc.). The range of values ​​is understood to include all values ​​within the range, including the value that defines the range, and values ​​adjacent to the range that produce the same or substantially the same result as the value immediately adjacent to the value that defines the boundary of the range. Thus, unless otherwise indicated, the numerical parameters described herein and in the claims are approximations that may vary depending on the desired characteristics to be obtained by the present invention.

[0083]

[0082] It should be understood that the above general description and the following detailed description are merely illustrative and descriptive, and do not limit the present invention as described in the claims.

[0084]

[0083] In this application, unless otherwise specified, the use of the singular form also includes the plural form.

[0085]

[0084] The articles "a" and "an" are used herein to refer to one or more (i.e., at least one) objects of the articles. For example, "element" refers to one or more elements.

[0086]

[0085] In this application, unless otherwise stated, the use of “or” means “and / or.” Furthermore, the use of the term “includes” and other forms such as “includes” and “contains” is not limited. Also, unless otherwise specified, terms such as “element” or “constituent” include both elements and constituents that constitute one unit and elements and constituents that constitute two or more subunits.

[0087]

[0086] As used herein and in the claims, the phrase “at least one” with respect to a list of one or more elements should be understood to mean at least one element selected from any one or more elements in the list of elements, but not necessarily including at least one and all of each of the elements specifically listed in the list of elements, nor excluding any combination of elements in the list of elements. This definition also allows for the presence of elements other than those specifically identified in the list of elements to which the phrase “at least one” refers, whether related to or unrelated to the specifically identified elements, at the discretion of the definition. Therefore, as a non-restrictive example, “at least one of A and B” (or equivalently “at least one of A or B” or equivalently “at least one of A and / or B”) means, in one embodiment, at least one A, optionally including elements other than B, in which B is absent (and optionally including elements other than B); in another embodiment, at least one B, optionally including elements other than A, and optionally including elements other than A; and in yet another embodiment, at least one A, optionally including elements other than A, and at least one B, optionally including elements other than B (and optionally including other elements), and so on.

[0088]

[0087] The term “approximately” as used herein refers to a quantity that varies by 30%, preferably 20%, more preferably 10% relative to a reference quantity, and is within the experimental error of the indicated value (e.g., within the 95% confidence interval of the mean) or within 10% of the indicated value (whichever is greater), and is within that range. Using the word “approximately” to modify a number merely indicates that the number should not be interpreted as an exact value. When used to mean an average of all values ​​of a variable and the indicated value of the variable, and to refer to a time interval representing a week, “approximately 3 weeks” means 17 to 25 days, and “approximately 2 to 4 weeks” means 10 to 40 days.

[0089]

[0088] Throughout this specification, unless otherwise required by context, the word “comprise,” or variations such as “comprises” or “comprising,” is understood to mean including a specified integer or group of integers, but not to mean excluding any other integer or group of integers. Also note that in this disclosure and in particular in the claims and / or paragraphs, terms such as “comprise,” “comprises,” and “comprising” may have meanings vested in U.S. patent law; for example, they may mean “include,” “contains,” and “contains”; and terms such as “essentially composed of” and “essentially composed of” have meanings vested in U.S. patent law, for example, elements not explicitly enumerated are permitted, but elements found in the prior art or elements that affect the basic or novel features of the present invention are excluded.

[0090]

[0089] For the purposes of this specification, the method steps are described in order, but that order does not necessarily mean that the steps are performed in chronological order in that order unless there is another logical way to interpret that order.

[0091]

[0090] Furthermore, if the features or aspects of the present invention are described in relation to the Markush group, those skilled in the art will recognize that the present invention may also be described in relation to any individual member or subgroup of a member of the Markush group.

[0092]

[0091] The terms “patient” and “subject” are used interchangeably and include mammals and non-mammals such as primates, livestock, pets, laboratory animals, captured wild animals, birds (including eggs), reptiles and fish. Therefore, the term refers to at least monkeys, humans, pigs, cattle, sheep, goats, horses, mice, rats, guinea pigs, hamsters, rabbits, cats, dogs, chickens, turkeys, ducks and other poultry, frogs and lizards.

[0093]

[0092] The terms “to treat” and “treatment” mean the prevention of a disorder, disease or disease to which such terms apply, or the prevention or reduction of one or more symptoms of such disorder or disease. This includes therapeutic measures, preventive measures, and applications that reduce the risk to a subject developing a disorder or other risk factors. Treatment does not require a complete cure of the disorder and includes embodiments that reduce symptoms, underlying risk factors, or slow the progression of the disorder.

[0094]

[0093] Other definitions of the selected terms used herein are set forth in the detailed description of the invention and apply throughout. Unless otherwise defined, all other scientific and technical terms used herein have the same meaning as commonly understood by those skilled in the art to which the invention pertains.

[0095]

[0094] The various methods or processes outlined herein may be coded as software executable on one or more processors employing any one of various operating systems or platforms. Furthermore, such software may be written using any of many suitable programming languages ​​and / or programming or scripting tools and may be compiled as executable machine code or intermediate code that runs on a framework or virtual machine.

[0096]

[0095] In this regard, when various inventive concepts are executed on one or more computers or other processors, they may be embodied as computer-readable storage media (or more computer-readable storage media) (for example, computer memory, one or more floppy disks, compact disks, optical disks, magnetic tapes, flash memory, field-programmable gate arrays or circuit configurations of other semiconductor devices, or other non-temporary or tangible computer storage media) coded in one or more programs that implement methods for implementing the various embodiments of the present invention discussed above. One or more computer-readable media may be portable so that one or more programs stored therein can be loaded onto one or more different computers or other processors to implement the various aspects of the present invention discussed above.

[0097]

[0096] The terms “program” or “software” are used herein in a general sense and refer to any kind of computer code or set of computer executable instructions that can be used to program a computer or other processor to implement various aspects of the embodiments discussed above. Furthermore, it should be understood that, according to one aspect, one or more computer programs that perform the method of the present invention at runtime do not need to reside on a single computer or processor, but may be distributed in a modular manner among a number of different computers or processors to implement various aspects of the present invention.

[0098]

[0097] Computer executable instructions may take many forms, such as program modules executed by one or more computers or other devices. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. Typically, the functions of program modules may be combined or distributed as needed in various embodiments.

[0099]

[0098] The data structure may also be stored in a computer-readable medium in any suitable format. For simplicity of explanation, the data structure may be shown as having fields that are related through locations within the data structure. Such relationships may also be achieved by assigning locations in the computer-readable medium that carry the relationships between fields to the storage areas of the fields. However, any suitable mechanism may be used to establish relationships between information within the fields of the data structure, including the use of pointers, tags, or other mechanisms for establishing relationships between data elements.

[0100]

[0099] Furthermore, various inventive concepts may be embodied in one or more methods, and one example thereof is provided. The actions performed as part of the method may be ordered in any suitable manner. Thus, although shown as a sequence of actions in the exemplary embodiment, embodiments may be constructed in which the actions are performed in a different order than shown, which may include performing several actions simultaneously.

[0101] Description of the Embodiment

[0100] Note that in the following description, the same or identical reference numerals in different embodiments indicate the same or identical features.

[0102]

[0101] This specification discloses a method for predicting vascular plaque stability, particularly coronary artery plaque stability, and an automated computer implementation system and method for predicting plaque stability, configured as a computer implementation system 100 as outlined in Figure 1, which provides comprehensive data on plaque stability using a patient-specific approach of precision medicine by analyzing intravascular images and biomechanical computer models. This creates patient-specific data, enabling clinicians to assess the risk of plaque rupture and adjust treatment plans to personalize medical care. Figure 1 shows the overall framework, which will be explained in more detail below.

[0103]

[0102] The system 100 disclosed herein enables rapid segmentation and annotation of intravascular patient imaging data (e.g., OCT) and is specifically configured to link with a computer model that calculates both shear stress and structural stress to return data that is not achievable by other methods shown to predict clinical events (Stone et al., 2016). In fact, Professor Peter Stone of Harvard Medical School, who has advocated for the use of biomechanical data in predicting coronary events, states: "Plaque risk characterization based solely on anatomical structure, while necessary, is insufficient to predict high-risk plaques that may destabilize and cause new clinical events." "If plaque stress could be calculated in a routine and time-efficient manner in the catheterization lab, this information could be extremely useful in identifying the highest-risk plaques and informing management decisions." The methods and computer implementations disclosed herein provide a solution to this pressing clinical need.

[0104]

[0103] System 100 disclosed herein is a user-friendly semi-automatic software tool for evaluating vascular and plaque features of OCT data in 2D and 3D, which can create patient-specific 3D anatomical models from commercially available OCT imaging systems. Importantly, System 100 can be used with any existing OCT imaging system.

[0105]

[0104] Intravascular OCT 103 uses near-infrared light to create images of the inside of the coronary arteries. This technology provides very high-resolution images (pixel size 10-15 microns) and allows cardiologists to observe the inside of the arteries in 10 times more detail than when using the next best technology, intravascular ultrasound (IVUS; pixel size 100-150 microns), and up to 35 times more detail than state-of-the-art CT images (pixel size over 350 microns). OCT also allows cardiologists to clearly identify plaque inside the arteries, measure the accumulation of fat and blood clots, and perform accurate measurements before and after stent placement.

[0106]

[0105] OCT Analysis: System 100 is configured to enable users to quickly analyze plaque features and create pixel-perfect segmentation (i.e., marking) tools for two-dimensional analysis 111 of the imaged arterial lumen, and to segment arteries through machine learning (ML) lumen contour segmentation routines that automate user workflows, for example. An edge detection algorithm based on state-of-the-art machine learning tools (deep learning with capsules) automatically acquires data on arterial contours as well as arterial size, shape, and location. Current tools are time-consuming and manual (e.g., per slice, over 1000 slices per patient). Therefore, System 100 can save a significant amount of time compared to current plaque assessment tools, including automated lumen contour segmentation. Typical performance of System 100 observed shows that mean arterial segmentation is comparable to current state-of-the-art machine learning models, but image processing is significantly faster. Thus, System 100 can produce segmentation indistinguishable from segmentation acquired by human operators and is reproducible in real-time or near real-time processing.

[0107]

[0106] Current features of clinical interest include: lipid regions; surface calcium; deep calcium; plaque-free walls; thrombi; macrophages; microchannels; cholesterol crystals; and thin-capsule fibrous plaques. Each of these poses a risk of causing heart attack and potential death due to plaque rupture or erosion. Each of these biomarkers is available within System 100, and the location of any data point is stored in 3D for use during 3D alignment and during mapping of information between different 3D workspaces. Additional features may be included where relevant.

[0108]

[0107] Once the OCT image analysis is complete, the user can convert the 2D image data into a 3D image for additional analysis 121. This converts the OCT data into a 3D reconstruction.

[0109]

[0108] Software Mapping: In most clinical scenarios, OCT image data is acquired in parallel with another diagnostic method such as CT105 and / or angiography107. System 100 is adapted to fuse high-resolution OCT103 with low-resolution angiography (vascular)107 or computed tomography (CT) or CT angiography (CTA)105. CT data105 or angiography107 is easily converted115 into a three-dimensional model of the arterial tree that provides data about the arterial centerlines within the imaged arterial tree. Image data from different imaging methods may be converted into a common reference frame or coordinate system so that the combination of OCT data103, CT / A data105 and vascular data107 provides a complete representation of the imaged arterial tree, including the left ventricular muscle mass acquired from the CT / A data. Once individual datasets are acquired, System 100 is configured to register the data from different studies together in the same xyz workspace so that all different modes of data can be qualitatively and quantitatively related to one another. When OCT data 103 is fused with vascular data 107 or CT data 105, biomechanical simulation becomes possible. As a result, 3D geometry with precise details in the OCT domain and new 3D quantitative pathological data that cannot be obtained with existing commercial software are obtained.

[0110]

[0109] If for some reason only one specific mode of data is available, the user can often perform many functions of system 100, but there will be some limitations on the available analysis methods. For example, if only OCT data 103 is available, the main limitation is that the calculation of shear stress is unreliable because 3D centerline data from CT / A or vascular data is missing.

[0111]

[0110] The software mapping process performed by the system 100 is configured to automatically interpolate the positions of OCT image frames between anatomical landmarks. These landmarks (e.g., vascular bifurcations) may be obtained from other medical imaging methods (e.g., CT / A or vascular data). Furthermore, CT datasets may be used to obtain left ventricular muscle mass, which is used to improve the boundary conditions for CFD simulations.

[0112]

[0111] Biomechanical Simulation - Structural Stress: Structural simulations can be performed at any location along the imaged blood vessels. These simulations are performed directly on 2D OCT images, which are segmented by the analyst / user using semi-automatic tools available within System 100 to identify different regions of plaque and vessel walls. Since it is impossible to know the exact material properties in vivo, System 100 uses a strategy based on the ratio of tissue stiffness, as in other regions of the cardiovascular system. This is a clinically applicable method and is unique to System 100.

[0113]

[0112] Microcalcification Estimator: The presence of microcalcification in coronary arteries is a predictor of future clinical events. This microcalcification activity is measured by radioactive tracer on PET / CT. 18 The uptake of sodium fluoride (NaF) is used for imaging and quantification. However, NaF-PET / CT imaging is expensive, not widely available, requires considerable technical expertise to analyze the images, and increases the radiation dose to the patient. This specification discloses a novel formula for predicting NaF uptake into vascular walls and plaques, and therefore predicting microcalcification activity. Surprisingly, this formula was found to correlate significantly with NaF uptake in vivo.

[0114]

[0113] The systems and methods disclosed herein enable personalized medical care by providing patients and their physicians with a detailed OCT, biomechanical modeling, and predictive assessment of the likelihood of clinical events based on their arterial microcalcification activity. This allows for a departure from the current "generic" approaches used in hospitals, enabling better preventive measures to be tested for patients identified as high-risk and mitigating the escalation of treatment for low-risk patients. The system enables rapid qualitative and unparalleled quantitative offline analysis of OCT data and provides biomechanical and microcalcification activity data that is not obtainable through other commercial means, thus providing cardiologists with a new set of patient-specific tools.

[0115] advantage

[0114] The computer implementation system 100 disclosed herein is configured to provide clear benefits and advantages of common OCT image analysis tools integrated into OCT scanning equipment, and furthermore, to provide clear advantages over third-party available OCT software analysis tools, and is configured to provide relevant measurements of vascular status from anatomical to functional status, the measurements including:

[0116]

[0115] Intraluminal shear stress (ESS), i.e., biomechanical frictional force acting on the innermost layer of a blood vessel, is a known predictor of plaque growth, progression, and clinical events. While several research tools exist for calculating ESS from blood vessels and CT-based 3D reconstructions (with or without the addition of OCT or IVUS), most are cumbersome, require expertise in computational fluid dynamics, and involve long computation times (e.g., 1-2 days on a typical workstation). System 100 utilizes a hybrid approach to calculate ESS that returns data within a clinically usable timeframe.

[0117]

[0116] Plaque structural stress (PSS) is the force per unit area acting on a plaque. Plaque rupture occurs when the PSS exceeds the plaque cap strength, and the PSS also affects cellular activity linked to plaque remodeling, inflammation, erosion, cell proliferation, and other activities related to plaque progression and stability. In vivo plaque rupture data shows that in more than 80% of cases, the location of the maximum PSS coincides with the rupture site. Although data exists regarding the importance of PSS, it remains a research tool and is not incorporated into commercially available software for plaque analysis. This is partly due to a lack of knowledge regarding patient-specific material properties. System 100 circumvents this by using the principle of static determinism, which is widely used in other cardiovascular diseases such as aneurysms (Joldes et al., 2017), but has not yet been used in coronary artery disease.

[0118]

[0117] OCT particularly excels in plaque feature analysis. Its superior resolution compared to other diagnostic methods means that plaque wall features can be identified and quantified down to the cellular level (e.g., the presence of macrophages). System 100 incorporates advanced tools for rapidly extracting these features.

[0119]

[0118] Microcalcification activity of plaque walls is emerging as a powerful non-invasive indicator of future clinical events. This activity is detected by radiotracerating positron emission tomography (PET) images. 18 This is measured by the uptake of sodium fluoride (NaF). However, PET imaging is expensive, not easily accessible, difficult to interpret, and involves exposing patients to a significant amount of radiation. This specification discloses a novel method for predicting NaF uptake within arterial segments, and therefore the potential for future clinical events, without requiring PET imaging.

[0120]

[0119] The System 100 platform allows for virtual stent placement. OCT provides unparalleled image resolution, making stent planning inherently more accurate. Precise vascular dimensions are determined, enabling accurate stent selection. Then, by selecting the appropriate 3D stent shape in System 100, the stent can be virtually positioned at the desired location within the vessel, after which flow simulation can be performed. This makes it possible to obtain data on stent performance before surgery.

[0121]

[0120] The characteristic analysis of the blood vessel wall is similar to plaque analysis, and with unparalleled image resolution, it means that the blood vessel wall can be rapidly identified and quantified. System 100 has now developed an automated tool that segments the lumen based on deep learning (artificial intelligence, AI), which surpasses the most advanced technology.

[0122]

[0121] Thin-film measurement: Again, image resolution is a crucial factor. Thin films become clinically dangerous when their thickness is less than 65 microns. Due to its resolution, OCT is the only diagnostic method capable of measuring biomarkers of this risk.

[0123]

[0122] Multimodal imaging: System 100 is configured to process any image data available to the clinician. CT and angiography images, even with vFFR, cannot provide accurate information about the progression, erosion, and rupture of the plague. An ideal scenario would involve a combination of imaging techniques (e.g., CCTA and OCT), but if the clinician desires to reduce the analysis performed using a single imaging technique (e.g., CCTA or angiography), this is possible with System 100.

[0124]

[0123] Vascular branching is included in the analysis of system 100. This provides accurate information about the flow within the arterial segment and explains the branching flow along the vessels.

[0125]

[0124] The fractional flow reserve (FFR) is the ratio of pressure upstream to downstream of a stenosis. Intervention is considered when the pressure difference is greater than a certain threshold (e.g., 30%). FFR using only imaging data is a current "hot topic" in cardiology because it allows for the measurement of FFR without requiring two main factors that limit standard FFR uptake: induction of hyperemia (forced increase in flow) or the presence of a pressure measuring wire. Furthermore, image-based FFR has other significant advantages. FFRCT (i.e., HeartFlow) is completely non-invasive as it requires only CT, but the calculation is quite time-consuming (it takes several hours via HeartFlow). Most patients undergo angiography (invasive imaging) during routine clinical practice, but angiography-based FFR is much faster and less expensive (i.e., VIRTUheart and CAAS).

[0126]

[0125] FFR can also be calculated based on a combination of OCT data and angiography data (or OCT only if angiography data is not available).

[0127]

[0126] Rapid Timeframe: System 100 is designed to operate within a clinical timeframe and aims to be a “push button.” The method used in System 100 has been verified to produce data using an efficient simulation strategy (i.e., a few minutes of CPU time) that is comparable to data from longer simulations (i.e., several days of CPU time).

[0128]

[0127] VR Visualization: The output from system 100 is also VR compatible, providing an immersive view of the problem and the resulting data.

[0129] Embodiments of the present invention

[0128] In a first aspect of the present invention, a method is provided for measuring microcalcification activity in an artery (preferably a coronary artery), the method being: (a) A step of measuring: (i) the presence and / or amount of coronary artery plaque or visible disease markers in the vascular tissue sample; (ii) The presence and / or amount of healthy tissue in the vascular tissue sample; (iii) One or more of the characteristics that define an abnormal hemodynamic environment within a blood vessel; (iv) One or more geometric features associated with vascular remodeling and affecting intravascular hemodynamics, and / or (v) A step of measuring one or more of the material properties that affect vascular hemodynamics, (b) a step of calculating the microcalcification activity in the blood vessel as a function of the measurements obtained in step (a).

[0130]

[0129] In one embodiment of the present invention, microcalcification activity in blood vessels, such as arteries or veins, including coronary arteries, is measured using positron emission tomography (PET).

[0131]

[0130] According to the present invention, any set of measurements can be fitted to a model (via regression or machine learning techniques) to obtain results for precise microcalcification activity, which is typically measured using NaF PET.

[0132]

[0131] In one embodiment of the present invention, the presence and / or amount of vascular plaque is measured based on well-established geometric disease markers from intravascular optical coherence tomography (OCT) images, specifically, the presence of lipids, calcium, and macrophages (bright spots) within the plaque. For example, mean lipid arc [°], mean calcium arc [°], and mean bright spot measurements can be obtained. Additional geometric measurements indicating disease are related to the diameter, area, volume, thickness, twist, and eccentricity of the vessel, as well as all combinations of these measurements. Similarly, these measurements can be obtained by any other imaging diagnostic method common in clinical practice.

[0133]

[0132] In another embodiment of the present invention, the presence and / or amount of healthy tissue is measured based on the measurement of the amount of visible healthy arterial wall using intravascular OCT imaging: plaque-free wall (PFW) is inversely correlated with disease. For example, a measurement of the mean arc [°] of the plaque-free wall can be obtained. Similarly, this measurement can be obtained by any other imaging method common in clinical practice.

[0134]

[0133] In further embodiments of the present invention, measurements of abnormal hemodynamic environments, such as blood-derived particle retention or abnormal WSS, are typically estimated using computational fluid dynamics (CFD) simulations or other methods that can directly estimate wall shear stress (WSS) via imaging techniques such as MRI. For example, by measuring low shear area (LSA): area of ​​low WSS [%] or high shear area (HSA): area of ​​high WSS [%] or mean WSS [Pa]. Additional hemodynamically derived metrics include, but are not limited to, the oscillatory shear index (OSI), relative residence time (RRT), low oscillatory shear (LOS), endothelial activation potential (ECAP), velocity-derived field function (e.g., vorticity), pressure drop, or any gradient of the aforementioned metrics (e.g., gradient of WSS).

[0135]

[0134] In yet another embodiment of the present invention, measurements of geometric features associated with vascular remodeling and affecting hemodynamics are preferably obtained from intravascular OCT images (circumference and eccentricity) and computed tomography angiography (CCTA). For example, by measuring mean circumference [mm] (using OCT), mean eccentricity (using OCT), arterial wall / layer thickness, and / or ventricular muscle mass [g] (using CT).

[0136]

[0135] In yet another embodiment of the present invention, material properties affecting hemodynamics, such as % hematocrit, can be measured during routine blood collection and used to adjust the viscosity model used to calculate WSS in CFD. Other methods for measuring / estimating % hematocrit are also applicable here.

[0137]

[0136] In a preferred embodiment of the present invention, the microcalcification activity measured by step (b) of the method enables evaluation of treatment options based on one or more target metrics.

[0138]

[0137] In one embodiment of the present invention, imaging techniques used to acquire measurements of the method include computed tomography (CT), magnetic resonance imaging (MRI), ultrasound, intravenous ultrasonography (IVUS), optical coherence tomography (OCT), single-photon emission computed tomography (SPECT), PET, and NaF PET. Preferably, the measurements are acquired using NaF PET.

[0139]

[0138] A function for estimating microcalcification activity may be obtained for a given set of measurements belonging to any of categories (i) to (v) obtained from one or more sources (e.g., coronary artery imaging). Currently, an explicitly defined formula is used and fitted using a standard optimization (error minimization) method for microcalcification activity ( 18 This describes the contribution of any number of categorical measurements to the F-NaF PET (measured using PET).

[0140]

[0139] These formulas are illustrated by the following example of a function for P (prediction of microcalcification activity (μCA)), where formulas of form P1 to P6 use categorical measures (A1, ..., En) as arguments, and lowercase letters describe coefficients determined using a fitting method (e.g., iterative optimization). Offset values ​​(constants) may be determined during fitting. The subscript n is the maximum coefficient or measure of the function argument within each category (A-E). Note that the function arguments here are categorized, in relation to previous / other explanations / presentations of the function arguments (i.e., general patient data) in this document. This is done to describe how different function forms aggregate the relevant measures to minimize the numerical fitting coefficient of the parametric function. Formulas can be implemented / fitted by ignoring the measures and coefficients of a particular category if such data is not available or excluded. For brevity, the formulas written here describe intermediate / repeating arguments / terms / categories as "...". TIFF0007898507000011.tif18170TIFF0007898507000012.tif37170TIFF0007898507000013.tif16170TIFF0007898507000014.tif16170TIFF0007898507000015.tif17169TIFF0007898507000016.tif33170Format P1 assumes that all measurements contribute independently to the function (intrinsic coefficients). Form P2 is obtained by looking at measurements of a given category given the same proportional scaling coefficient and multiplying them by an intrinsic exponent. Format P3 simplifies Format P2 by using the same exponent for measurements in a given category. Forms P4 and P5 provide examples of categorically multiplicative forms, but these forms can increase measurement errors and are sensitive to measurements of zero (or extreme values). Format P6 illustrates the formats available to various groups within a category. Measurements from categories A and B are closely related and may share unique indices, but the simulation results (category C) are considered exclusive.

[0141]

[0140] To further optimize the method, as described below, other finite combinations of formulas may be used or generated. However, all of these functions include at most one exponential coefficient per measurement to simplify the fitting process. Formula (in particular P1) leverages a power law formula that has been used to describe relative growth scaling relationships throughout biology, including coronary artery blood supply. A simple power law relationship appears in fluid dynamics, and in analytical solutions to the Navier-Stokes equations for flow inside pipes (which are physiologically relevant), quantities such as flow, pressure, and friction / WSS depend on the radius.

[0142]

[0141] Optimized (parametric) fit: To determine the coefficients of a scalar equation such as P (above), the sum of squared errors may be minimized according to the Nelder-Mead simplex algorithm: a direct search method for multidimensional unconstrained minimization: TIFF0007898507000017.tif10170

[0143]

[0142] Here, TIFF0007898507000018.tif5170 is a vector of measured NaF uptake data. TIFF0007898507000019.tif4170 is a vector containing estimates. These estimates are calculated for each sample using a scalar equation for P. In the first iteration of the algorithm, the coefficients of P are inferred (or set to arbitrary random values). After each iteration, the coefficients are updated until a minimum value is found, and the algorithm terminates. This occurs when the change in error is less than a specified tolerance. To assist the algorithm's function in finding the optimal set of coefficients, the input data (arguments for P) are normalized by their mean value.

[0144]

[0143] Before providing specific examples, the main aspects of the methodology / framework are described more broadly below. At the heart of this is the training and testing of predictive models. After this, the model may be considered suitable for use.

[0145]

[0144] Broadly speaking, process 200 includes the following steps as shown in Figure 2.

[0146]

[0145] Step 1: Obtain training data consisting of the following Step 201: [A] Includes data relating to multiple patients and multiple data which may further include image data and / or biomechanical data at one or more anatomical locations. Tr B Tr , C Tr , D Tr ...] General patient data 203, and Microcalcification activity data from multiple patients at one or more anatomical locations 205 (μCA).

[0147]

[0146] Step 2: Step 207 of fitting a multivariate function / model which can estimate / predict the μCA of new data acquired in the same manner as the input training data, the function being: TIFF0007898507000020.tif6170

[0148]

[0147] Step 3: Evaluate the multivariate model by evaluating the pre-fitted function f, and the training set [A Te B Te , C Te , D Te ...] is a new set of general patient test data that was not included in the previous set, a set of estimates of microcalcification activity for a new set of function inputs (μCA Est Steps to obtain ). TIFF0007898507000021.tif6170

[0149]

[0148] Step 4: Use the error function Ef to set a set of estimates of microcalcification activity (μCA Est ) is a known / corresponding value (μCA Te Step 211: Calculate the error estimate by comparing it with the set of values. TIFF0007898507000022.tif6170

[0150]

[0149] Step 5: Check the error estimate / evaluate the fit of the model. If the error estimate meets the required set of desired criteria, such as accuracy, precision, and sensitivity to input data, the model is considered fit for the purpose and can be used to predict microcalcification activity.

[0151]

[0150] If the error is small and the result is statistically significant, the estimated microcalcification activity is obtained. If the error is not small and / or the result is not statistically significant, further training is required by adding more training data.

[0152]

[0151] The following information provides background information on each aspect of the training and testing process listed in Figure 2.

[0153] Step 1(i) - General patient data 203 [A, B, C, D...]

[0152] Typical patient data is derived from multiple patients and multiple data types and includes image data and / or biomechanical data at one or more anatomical locations.

[0154]

[0153] Preferably, general patient data includes patient data related to the estimation of microcalcification activity, and this patient data includes, 18 F-Sodium fluoride ( 18 This includes information that may affect microcalcification activity detected / measured using positron emission tomography (PET) (F-NaF).

[0155]

[0154] There are no restrictions on the number of datasets collected for fitting or on the classification data within each dataset. For example, all measurements may or may not be geometric in nature. However, they must reasonably correspond to metrics / measurements expected to be associated with the atherosclerotic process and, therefore, microcalcification activity, and must be obtainable from clinical practice and / or through image processing of medical imaging diagnostics using common imaging means used, thus enabling the immediate application of the methodology.

[0156]

[0155] In certain configurations, geometric measurements correspond to image-based diameter measurements (standard measures of vascular patency / health) in specific blood vessels prone to calcification processes, with extreme diameters associated with unhealthy vascular structures, and vascular size as well. 18 This is expected to affect the surface area available for transporting the F-NaF tracer to the binding site. Geometric measurements are obtained by image processing of patient image data, including one or more of the following: computed tomography, optical coherence tomography, intravascular ultrasound, X-ray angiography, magnetic resonance imaging, or PET imaging.

[0157]

[0156] Apart from direct anatomical measurements of geometric shape, the measurement of vascular health or disease burden (e.g., coronary artery calcium score) and patient-specific measurements that have been shown to support the progression of cardiovascular disease are relevant. These measurements include, for example, image-based measurements (i.e., computed tomography, optical coherence tomography, intravascular ultrasound, radiographic angiography, magnetic resonance imaging, or PET imaging) and non-image-based measurements such as patient history or blood sample data. Other relevant measurements are, for example, biomechanical measurements such as blood pressure, blood flow, or local hemodynamic properties, and tissue stress. These types of metrics are, 18 It is expected to play a role in the transport of F-NaF tracers to their binding sites and is broadly associated with the progression of cardiovascular disease.

[0158]

[0157] The collected data may optionally undergo transformation / scaling in order to improve the performance of the fitting algorithm before being used in the model fitting process.

[0159] Step 1(ii) - Microcalcification activity data 205 (μCA)

[0158] 18 F-NaF PET image data is acquired at one or more measurement scales from a PET scan of a patient's heart or other vascular region. This data should be collected for multiple patients and is the dependent variable in the fitting of multivariate functions / models (step 207 in Figure 2).

[0160]

[0159] In accordance with standard methods for measuring PET data, the recorded 18 F-NaF PET data is recorded as an assessment of the standardized uptake value at each sample region / position. This value is preferably adjusted (normalized) with respect to blood pool activity by measuring / evaluating the standardized uptake value at a reference position. As an example of this, it is conceivable to obtain an average value from the target region of the right atrium. By doing this, the PET measurement process is standardized between patients and provides a measurement of the tissue-to-background ratio (TBR). In the coronary arteries, 18 F-NaF PET is often reported as TBR or other similar uptake measurements. See, for example, Coronary Microcalcification Activity (CMA) (Kwiecinski, J et al., J Am Coll Cardiol. 2020;75(24):3061-74). [[ID=第十九]]

[0161]

[0160] Further, the measurement scale is from medical images 18This refers to the method by which F-NaF PET data is sampled. This data may be obtained as the maximum value within a region of the patient's vascular system. Alternatively, data may be sampled at discrete length intervals / regions of interest along the patient's blood vessels. Examples include sampling data every 5 cm along the midline of a vessel, or sampling data between bifurcations, or sampling data every nth image, or sampling the maximum value of data for each vessel or predetermined anatomical segment / section. The data may be mapped as a continuous function by measuring with respect to a continuous variable such as spatial dimension (e.g., axial distance in the medical image stack or distance along the midline of a coronary artery). Acquiring data in this manner allows the continuous function to be evaluated in a specific way (undefined / during data acquisition) before the fitting step (e.g., obtaining the maximum / mean value of the function in a particular region / interval). Furthermore, the locality of the sampled data points (e.g., spatial dimension) may be considered an independent variable in the fitting of the multivariate function. This allows the fitted multivariate function to be: 18 This allows for the evaluation of the spatial dependence of microcalcification activity measured using F-NaF PET. In this process, general patient data also benefits from similar spatial discretization when acquired from medical images.

[0162]

[0161] To improve the spatial / anatomical localization of the measurements, PET images are simultaneously aligned with other image sources (which have a secondary / clearer representation of patient-specific anatomical structures), such as contrast-enhanced computed tomography (to improve the appearance of blood vessels), and each 18 It is preferable to improve the recording of spatial data associated with F-NaF PET samples. To support this process and to better present PET image data, motion correction algorithms such as elastic motion correction may be used.

[0163]

[0162] The collected data may optionally undergo transformation / scaling before being used in the model fitting process in order to improve the performance of the fitting algorithm.

[0164] Step 2 - Fit the multivariate function / model 207

[0163] The fitting process 207 may be performed using any method for fitting a multivariate function, such as parametric regression or nonparametric regression, as will be understood by those skilled in the art. Examples herein include the Nelder-Mead simplex method, but alternative optimization methods that are expected to have the same or similar coefficients are available and suitable, as will be readily understood by those skilled in the art. However, in all cases, training and test data are required, regardless of whether a machine learning method is used in the fitting process 207. Nonparametric regression is preferred because the form of the predictor equation (function f in Figure 2) does not have a default form but is determined / constructed from information derived from the data being fitted. However, this requires more data than parametric regression. This requires that a portion of the training data 201 be saved as validation data 215 during the fitting process, as shown in Figure 2. The majority of the training data 201 may be used to fit the model, but this validation set (or subset) 215 is used to estimate the prediction error for model selection. The category of nonparametric regression includes methods such as kernel regression and machine learning support vector machines. Parametric fitting, on the other hand, uses methods where the form of the function is assumed / predetermined and the coefficients of the function are learned / determined. This may be performed using parametric machine learning algorithms or conventional optimization methods that find the minimum of the objective function ("sum of squared errors"). For nonlinear functions, a particular example suitable for use in Method 200 is a direct search method for multidimensional unconstrained minimization—such as the Nelder-Mead simplex method. When performing parametric optimization (i.e., equations 1-6), the form of the function being fitted can benefit from leveraging commonly used functional forms that have been used to describe relationships throughout biology, such as allometric scaling functions.

[0165] Step 3 - Evaluate the multivariate model 209

[0164] As shown in FIG. 2, the evaluation 209 of the model is important for testing the accuracy and fitness of the model. The model is evaluated against a set of test data (general patient data: input / arguments of the model; A Te , B Te , C Te , D Te ...) collected in the same way as the training data. This data is preferably obtained from a wide set of patients at multiple sites and is of sufficient size to ensure that the fitted model does not receive simple errors such as sensitivity during extrapolation (non-physical values obtained for data outside the training data). The test set 215 should not include the general patient data 203 used during training 201. Further, microcalcification activity data 205 (μCATe) needs to be obtained so that the error of the fitted model can be quantified for the same set of patients.

[0166] Step 4 - Calculate the error estimate 211

[0165] Once a set of estimates / predictions of the microcalcification activity (μCA Est ) of the test data is generated, they can be compared to the true microcalcification activity values (μCA Te ). The differences between each of these data sets result in an error distribution. If the errors are normally distributed, the linear correlation between μCA Est and μCA Te is a very simple way to evaluate model performance. The error distribution may be simply used to evaluate the accuracy (ideally centered around zero) and precision (ideally with a small variance / range / spread) of the model. Other useful information may be generated from the error distribution, such as investigating the relationship between the error and the predictor value or the fitted value: this helps to evaluate the sensitivity of the model to the input / output.

[0167]

[0166] The model output may be converted to discrete / nominal classification, which provides other methods (e.g., sensitivity and specificity) through which error estimates can be tested. In the case of binary classification, this is done through the measurement of true positives, false positives, true negatives and false negatives. A cutoff value is required to classify elevated microcalcification activity. This can be established against a set of control patients (without suspected cardiovascular disease) and / or a threshold of tissue-to-background ratio (e.g., a relative background value greater than 1).

[0168] Step 4(a) - Check the error estimates to evaluate the model fit.

[0167] If the error estimate meets the required set of criteria, such as accuracy, precision, and sensitivity to input data, the model is considered fit for the purpose and can be used to predict microcalcification activity.

[0169] Preferred Embodiment

[0168] The following examples of specific embodiments of the present invention are presented to better understand the nature of the present invention. An example of a purely image-based model using parametric model generation is the vascular structure of the coronary arteries. Here, typical patient data is obtained from intravascular optical coherence tomography (OCT) imaging data and coronary computed tomography angiography (CCTA) imaging data. Microcalcification activity data is obtained following a alignment step with (contrast-enhanced) CCTA imaging data (aligning both the image space and the objects within it), 18 Data are acquired from F-NaF PET imaging. Typical patient data and microcalcification activity measurements are sampled from various regions of the coronary artery structure: major coronary segments described by commonly used coronary segment maps. Following the data acquisition phase, a parametric model is fitted and tested. All methods and results are detailed in Table A below.

[0170]

[0169] In this example, all training and test data are collected at the same stage.

[0171]

[0170] When using the system to determine microcalcification activity from coronary CT angiography (CCTA) data, the system receives raw CCTA image data and then determines the quality of these image data by accessing associated image metadata: for example, the slice thickness and pixel size of the CTCA acquisition must exceed certain thresholds. If the quality control check is passed, the system classifies the CCTA data for use in the AI ​​training dataset. Where applicable, the system compares morphological and plaque features identifiable in CCTA with corresponding features visible in invasive imaging of the same patient (e.g., OCT). This is to verify that the features identifiable in CCTA are spatially correlated with the features identifiable in OCT. After quality control, data such as anatomical metrics and image-based pixel density distribution are extracted from the AI-derived geometric shapes for use in the regression training model. If the quality control check is not passed, the system returns an error indicating that the raw CCTA data is unusable for training data or further purposes of the system.

[0172] Step 1(i) - General patient data 203

[0171] These datasets are considered independent variables (inputs or predictors) of the model and are labeled as A, B, C, D, etc. Multiple measurements are taken for each input. In the case of three inputs (i.e., A, B, and C), each patient has multiple measurements for each of A, B, and C, taken at multiple locations. For example, in the coronary vascular system, input examples may include arterial tortuosity (tort); low shear area (LSA); and plaque-free wall (PFW). These are measured in each coronary artery segment within the vascular structure across a spatial region imaged by all three imaging methods (and common to them).

[0173]

[0172] Torrend: Torrend of the vascular lumen centerline 301 (Figure 3) measured from CCTA. Torrend tends to be greater in diseased blood vessels. The vascular centerline is usually constructed from the wall boundary distance field or by calculating the wall distance using ray casting, and may be reliably constructed using many centerline algorithms. Prior to this process, the boundaries of the blood vessel must be defined, which here is done by image segmentation: in this process, objects on the image are thresholded (masked) within a target area between Hounds field units / pixel levels that includes the target object (vascular lumen) and does not include other surrounding objects. Once the centerline data is extracted, here, centerline torrend is simply measured as the ratio of the total length LC301 along the centerline segment (i.e., the sum of the distances between consecutive points) divided by the shortest distance LS303 (straight line) between the endpoints of the centerline, which is the boundary of the target area where patient-specific measurements are taken, as shown in Figure 3.

[0174]

[0173] Low Shear Area (LSA): The percentage of vascular (segment) lumen surface area where the wall shear stress value is below a specific threshold (0.4 Pa is used in this example, but 1 Pa is also commonly used to represent low shear stress in the arterial system). This threshold is associated with stagnant blood flow near the wall and increased monocyte wall adhesion. Low wall shear stress is associated with the onset and progression of atherosclerosis. Low wall shear stress is calculated from the region defined by the vascular lumen boundary using computational fluid dynamics, as well as centerline reconstruction. For the current dataset, this can be done using segmented vascular boundaries from CCTA or OCT images. If OCT images are selected (due to their superior pixel resolution), the OCT vascular lumen boundaries are registered in the CCTA image space, curvature is given to the OCT vascular boundaries, and the OCT measurements are spatially corresponding / aligned with vascular segments defined by a coronary segment map from which each measurement region is defined. The following image shows low-shear regions (in Pascals) identified on the surface of OCT-derived geometric shapes after registration in the CCTA image space (see Figure 4).

[0175]

[0174] Plaque-free wall (PFW): Plaque-free wall is an OCT measurement acquired on an OCT image, e.g., image 500 in Figure 5, as an angle 501 around the luminal center 503 where the arterial wall is clearly visible and not obstructed by plaque features that attenuate the OCT signal (this is inversely proportional to the presence of disease), and where the vascular intima 505 and media 507 are healthy. The angle measurement method allows PFW to be mapped to the vascular boundary so that PFW is expressed as a percentage of the luminal surface area of ​​the vascular segment. Figure 5 shows an example of a PFW arc angle 501 superimposed on an OCT image 500.

[0176] Step 1(ii) - Microcalcification activity data 205

[0175] The model's dependent variable (predicted variable / output) was evaluated for each vascular segment in the common image space. 18 These are measurements of microcalcification activity on F-NaF PET images. Each segment should also include corresponding general patient data measurements from each of the three categories mentioned above: Tort, LSA, and PFW.

[0177]

[0176] Figure 6 also displays LSA surface area data. 18 This shows 600 example images of F-NaF PET segment measurements: both datasets are obtained for the same anatomical region.

[0178]

[0177] Microcalcification activity is measured as the maximum tissue-to-background ratio (TBR) for each segment: the maximum standardized uptake within a segment is normalized by blood pool activity. Blood pool activity is measured as the mean standardized uptake of the right atrium. (Since microcalcification activity occurs in the wall rather than the lumen) the areas in which TBR is measured on PET images include the coronary artery wall.

[0179] Step 2 - Fitting Multivariate Functions / Models

[0178] Here, half of the collected data is used to train the model. The multivariate model is assumed to have the following combination of power laws, which are commonly used to represent allometric relationships: TIFF0007898507000023.tif5170 Here, a, b, c, d, e, and f are coefficients of the model determined during model fitting, μCA Est This is the model estimate of microcalcification activity (maximum segment TBR value). In this example, to determine the coefficients, the sum of squared errors (ε) is minimized according to the Nelder-Mead simplex algorithm: TIFF0007898507000024.tif5170 Here, μCA Tr This is a vector / array containing all measurements of the largest segment TBR in the training data set, and μCA Est This is a vector / array of estimates for a given set of coefficients being optimized. Once the coefficients are generated, a correlation analysis is performed to evaluate how well the model fits the training data. Given that the model has been optimized to fit this data, a high correlation is expected. For a linear polynomial, the fit result 701 is shown in Figure 7.

[0180] Step 3 - Evaluate the multivariate model, calculate error estimates, and assess the model's fit.

[0179] Once the model coefficients are determined, the remaining general patient data (data not included in the training data used to fit the model) is evaluated. In contrast to the training data, the linear polynomial fit 801 in Figure 8 to this data is slightly weaker but still significant (R 2 Tr=0.71;R 2 T e =0.70; p-value T e <0.0001).

[0181]

[0180] Furthermore, Ef = μCA Est -μCA Te The error distribution obtained was normally distributed with a mean of 0.099 and a standard deviation of 0.24. μCA TeAssuming a mean value of 1.16, the model tended to overpredict microcalcification activity by approximately 9% with moderate accuracy. Furthermore, a negative correlation (Spearman's Rho) was found between the PFW value and the error value (Rho = -0.73, p < 0.001), suggesting that the current model tends to underpredict microcalcification activity in healthier vascular segments when measured using the PFW metric.

[0182]

[0181] Considering this information, the model may be useful for patients presenting CCTA and OCT images of the coronary system, but benefits may be gained by excluding PFW and / or using alternative metrics instead.

[0183]

[0182] Additional purposes, advantages and novel features are described below or will become apparent to those skilled in the art by examining the drawings and the following detailed descriptions of some non-limiting embodiments.

[0184] Examples

[0183] In one example of the present invention, different category data are obtained according to Table 1. TIFF0007898507000025.tif110170

[0185]

[0184] The following results are the maximum measured 18 This shows a linear regression between F-NaF PET uptake (maximum target to background ratio (TBR)) and the estimated microcalcification activity P calculated using equation (1) for P1.

[0186]

[0185] In Figure 9, all measurements from Table 1 are used for fitting, and comparisons are performed on coronary artery segment and coronary vessel (i.e., entire OCT pullback) measurement scales. Note that the size of each segment used to obtain the measurements is different, and the maximum TBR on the vessel scale is the maximum TBR of all segments across the vessel.

[0187]

[0186] In Figure 9, fits 901 and 903 show a strong linear relationship between the model and the data. At the vascular measurement scale, the number of degrees of freedom of the fitted model (23 coefficients) exceeds the number of data points used to optimize / fit the model coefficients (20). Therefore, the current example models are almost certainly overfitting the data: the resulting models may not be able to fit additional data or reliably predict future observations.

[0188]

[0187] Figure 10 shows that by ignoring geometric measurements and reducing the number of categorical measurements used, the model performs well on the vascular measurement scale and the risk of data overfitting is low. However, performance on the segment measurement scale is not maintained. In this group of variables, the normalized area (LSA[%]) at low WSS (<0.4 Pa) and the mean arc of the plaque-free wall (mean, PFW Arc[°]) contribute most (on average) to the approximation of microcalcification activity.

[0189]

[0188] Furthermore, by using only the OCT-derived metrics, it is possible to generate a model that performs well at both measurement scales (Figure 11). Interestingly, when fitted at different measurement scales, the resulting model differs in the weights applied to the various geometric measurements of circumference and eccentricity. The optimization process is dependent on the initial conditions and does not necessarily require finding a global minimum. However, variations in the model are not unexpected. Local geometric measurements indicate segment location and vary throughout the coronary vascular system with the development of plaque phenotypes. Typically, proximal vascular segments are larger than distal segments, and high-risk plaques tend to form on proximal vascular structures.

[0190]

[0189] The relationship between these geometric variables and TBR and LSA measurements in Table 2 shows that, individually, both circumference and eccentricity have a positive relationship with TBR and LSA. However, the correlation coefficient for eccentricity is weak, while the correlation for circumference is slightly stronger. Since the relationships between all variables affect the model results, it is clear that the strength of individual correlations does not reflect their contribution to the multivariate model. TIFF0007898507000026.tif112170

[0191]

[0190] Table 2 shows the blood supply (LVM). 3 / 4 Additional simple models for approximating LSA are shown, incorporating factors that affect ) and viscosity (HCT). These models provide an improved approximation of microcalcification activity TBR compared to geometric measurements alone and compete with CFD measurements of LSA. By incorporating these simple models into the previous 6-parameter OCT-derived multivariate model (Figure 11), the correlation coefficient (R 2 Seg :0.71~0.72, R 2 ves This improves the independent parameter (R :0.81~0.90) which has a power law scaling coefficient. 2 Seg =0.75;R 2 Ves (=0.88) HCT and LVM 3 / 4 It simply includes it.

[0192]

[0191] At present, we can conclude that simple multivariate functions such as P1 in equation (1) above can be adjusted to provide a model that fits the data well, while relying on a subset of readily available categorical measures. However, other alternative methods are also available, including those in which the form of the multivariate function is not defined before fitting.

[0193]

[0192] This method is limited by the amount of consistent data available (applicable here only to segmented data). The method fits the training data well with the current dataset, similar to function P1 in Figures 9-11, but it failed to predict the test data.

[0194]

[0193] A specific alternative is a machine learning method that performs data-driven fitting (nonparametric), which generates an equation for P. A two-layer feedforward network with sigmoid hidden neurons and linear output neurons is one implementation example. If the data is consistent and there are enough neurons in the hidden layer of the model, this model can fit the multidimensional mapping problem arbitrarily well. This network is implemented using the Levenberg-Marquardt backpropagation algorithm and a default value of 10 neurons in the hidden layer. However, it is not immune to the effects of overfitting. The performance of the model was tested with various ratios of training, validation, and test data. In some examples, as shown in Figure 12, which illustrates a concrete example of AI-based fitting, the training data fits perfectly, but it is clear that the model is overfitted and will not perform well on future data.

[0195]

[0194] This problem also occurs when fitting high-dimensional models of P1 (more than 3 arguments) to the training and test sets, and as a result, the true predictive power of the models in Figures 10 and 11 is unknown without further data. However, some analyses were performed using low-dimensional models (Tables 3 and 4 below). These models are promising but would benefit from further scrutiny of larger datasets. The LSA and PFW models show consistency across all training / test dataset ratios. All models perform well when a high proportion of data is provided for training. TIFF0007898507000027.tif91170TIFF0007898507000028.tif82170

[0196]

[0195] The proposed method is: 18 This study demonstrates that measurable microcalcification activity detected using F-NaF PET is predictable using local hemodynamic conditions, the presence or absence of coronary plaque, and measurements of related metrics. The absence of plaque-free walls and the presence of low endothelial low-shear stress regions, common markers of the disease, were essential to the multivariate model discussed.

[0197] Implementation Example - Hardware Overview

[0196] According to one embodiment, the technology described herein is implemented by at least one computing device. The technology may be implemented in whole or in part using a combination of at least one server computer and / or other computing devices coupled using a network such as a packet data network. The computing device may include digital electronic devices such as at least one application-specific integrated circuit (ASIC) or field-programmable gate array (FPGA) that are wired together to perform the technology or are permanently programmed to perform the technology, or it may include at least one general-purpose hardware processor programmed to perform the technology according to program instructions in firmware, memory, other storage devices or a combination thereof. Such a computing device may implement the described technology by combining custom hardwired logic, ASICs or FPGAs with custom programming. Computing devices may include server computers, workstations, personal computers, portable computer systems, handheld devices, mobile computing devices, wearable devices, body-worn or implantable devices, smartphones, smart home appliances, internetworking devices, robots or autonomous or semi-autonomous devices such as unmanned ground vehicles or unmanned aerial vehicles, any other electronic devices incorporating hardwired logic and / or programmable logic to implement the described technologies, one or more virtual computing machines or instances in a data center, and / or a network of server computers and / or personal computers.

[0198]

[0197] FIG. 13 is a block diagram showing an exemplary computer system in which one embodiment of the above-described system 100 may be implemented. In the example of FIG. 13, a computer system 1300 and instructions for implementing the disclosed technology in hardware, software, or a combination of hardware and software are schematically represented at the same level of detail generally used by those skilled in the art to convey information about computer architecture and computer system implementation, for example, as boxes and circles.

[0199]

[0198] The computer system 1300 includes an input / output (I / O) subsystem 1302 that may include a bus and / or other communication mechanism for communicating information and / or instructions between components of the computer system 1300 via an electronic signal path. The I / O subsystem 1302 may include an I / O controller, a memory controller, and at least one I / O port. The electronic signal path is schematically represented in the drawings, for example, as lines, one-way arrows, or two-way arrows.

[0200]

[0199] At least one or more hardware processors 1304 are coupled to the I / O subsystem 1302 for processing information and instructions. The hardware processors 1304 may include, for example, a general-purpose microprocessor or microcontroller, and / or a dedicated microprocessor such as an embedded system or a graphics processing unit (GPU) or a digital signal processor or an ARM processor etc. The processor 1304 may include a unified arithmetic logic unit (ALU), or may be coupled to a separate ALU. One or more of the hardware processors 1304 may be implemented as dedicated image processing means for segmenting, annotating, and otherwise analyzing patient image data. Alternatively, the functions of the image processing means may be shared among each of the hardware processors 1304.

[0201]

[0200] The computer system 1300 includes one or more units of memory 1306, such as main memory, which is coupled to the I / O subsystem 1302 for electronically and digitally storing data and instructions executed by the processor 1304. Memory 1306 is also used to store patient image data and training data for retrieval by the processor 1304. Memory 1306 may include volatile memory such as various forms of random access memory (RAM) or other dynamic storage devices. Memory 1306 may also be used to store temporary variables or other intermediate information during the execution of instructions executed by the processor 1304. If such instructions are stored in a non-temporary computer-readable storage medium accessible by the processor 1304, the computer system 1300 can be rendered into a dedicated machine customized to perform the operations specified by the instructions.

[0202]

[0201] The computer system 1300 further includes non-volatile memory, such as read-only memory (ROM) 1308 or other static storage device coupled to the I / O subsystem 1302, for storing information and instructions for the processor 1304. The ROM 1308 may include various forms of programmable ROM (PROM), such as erasable PROM (EPROM) or electrically erasable PROM (EEPROM). The units of the persistent storage device 1310 may include various forms of non-volatile RAM (NVRAM), such as FLASH memory, or solid-state storage devices, magnetic disks, or optical disks such as CD-ROMs or DVD-ROMs, and may be coupled to the I / O subsystem 1302 for storing information and instructions. The storage device 1310 is an example of a non-temporary computer-readable medium that, when executed by the processor 1304, can be used to store instructions and data that cause a computer implementation to perform the techniques of this specification.

[0203] Instructions within memory 1306, ROM 1308, or storage 1310 may include one or more sets of instructions arrayed as a module, method, object, function, routine, or call. The instructions may be arrayed as one or more computer programs, operating system services, or application programs including mobile apps. The instructions may include an operating system and / or system software; one or more libraries supporting multimedia, programming, or other functions; data protocol instructions or stacks for implementing TCP / IP, HTTP, or other communication protocols; file format processing instructions for parsing or rendering files encoded using HTML, XML, JPEG, MPEG, or PNG; user interface instructions for rendering or interpreting commands of a graphical user interface (GUI), command line interface, or text user interface; application software such as an office suite, Internet access application, design and manufacturing application, graphics application, audio application, software engineering application, educational application, game, or other application. The instructions may implement a web server, web application server, or web client. The instructions may be arrayed as a data storage layer using a presentation layer, application layer, and relational database system using or not using Structured Query Language (SQL), object store, graph database, flat file system, or other data storage.

[0204]

[0203] The computer system 1300 may be coupled to at least one output device 1312 via the I / O subsystem 1302. In one embodiment, the output device 1312 is a digital computer display. Examples of displays that may be used in various embodiments include a touchscreen display, or a light-emitting diode (LED) display, or a liquid crystal display (LCD), or an electronic paper display. The computer system 1300 may include other types of output devices 1312 in place of or in addition to the display device. Examples of other output devices 1312 include a printer, a ticket printer, a plotter, a projector, a sound card or video card, a speaker, a buzzer or piezoelectric device or other audible device, a lamp or LED or LCD indicator, a tactile device, an actuator or a servo.

[0205]

[0204] At least one input device 1314 is coupled to the I / O subsystem 1302 to communicate signals, data, command selections, or gestures to the processor 1304. Examples of input devices 1314 include touchscreens, microphones, still and video digital cameras, alphanumeric and other keys, keypads, keyboards, graphic tablets, image scanners, joysticks, clocks, switches, buttons, dials, slides, and / or various types of sensors such as force sensors, motion sensors, thermal sensors, accelerometers, gyroscopes, and inertial measuring unit (IMU) sensors, and / or radio communication such as mobile phones or Wi-Fi, radio frequency (RF), or various types of transceivers such as infrared (IR) transceivers and Global Positioning System (GPS) transceivers.

[0206]

[0205] Another type of input device is a control device 1316 that can perform other automatic control functions, such as cursor control or navigation in a graphical interface on a display screen, in place of or in addition to the input function. The control device 1316 may be a touchpad, mouse, trackball, or cursor direction keys for communicating direction information and command selection to the processor 1304 and for controlling the movement of a cursor on the display 1312. The input device may have at least two degrees of freedom within two axes, a first axis (e.g., x) and a second axis (e.g., y), which allows the device to specify a position in a plane. Another type of input device is a wired, wireless, or optical control device, such as a joystick, wand, console, steering wheel, pedals, gear shift mechanism, or other type of control device. The input device 1314 may include a combination of several different input devices, such as a video camera and a depth sensor.

[0207]

[0206] In another embodiment, the computer system 1300 may comprise an Internet of Things (IoT) device in which one or more of the output device 1312, input device 1314, and control device 1316 are omitted. Alternatively, in such an embodiment, the input device 1314 may comprise one or more cameras, motion detectors, thermometers, microphones, seismic detectors, other sensors or detectors, measuring devices or encoders, and the output device 1312 may comprise a dedicated display such as a single-line LED or LCD display, one or more indicators, a display panel, an instrument, a valve, a solenoid, an actuator or a servo.

[0208]

[0207] If the computer system 1300 is a mobile computing device, the input device 1314 may include a Global Positioning System (GPS) receiver coupled to a GPS module capable of triangulating multiple GPS satellites and determining and generating geographical location or location data, such as latitude and longitude values ​​of the geophysical location of the computer system 1300. The output device 1312 may include hardware, software, firmware, and interfaces for generating location reporting packets, notifications, pulses or heartbeat signals, or other repetitive data transmissions that identify the location of the computer system 1300, either alone or in combination with other application-specific data directed to the host 1324 or server 1330.

[0209]

[0208] The computer system 1300 may implement the techniques described herein using customized wiring logic, at least one ASIC or FPGA, firmware and / or program instructions or logic that, when loaded and used or executed in combination with the computer system, cause the computer system to operate or program as a dedicated machine. According to one embodiment, the techniques described herein are executed by the computer system 1300 in response to the processor 1304 executing at least one sequence of at least one instruction contained in the main memory 1306. Such instructions may be read into the main memory 1306 from another storage medium, such as storage 1310. After executing the sequence of instructions contained in the main memory 1306, the processor 1304 executes the process steps described herein. In alternative embodiments, wiring circuits may be used instead of or in combination with software instructions.

[0210]

[0209] As used herein, the term “storage medium” refers to any non-temporary medium that stores data and / or instructions for operating a machine in a particular manner. Such storage mediums may include non-volatile media and / or volatile media. Non-volatile media include, for example, optical or magnetic disks such as storage 1310. Volatile media include dynamic memory such as memory 1306. Common forms of storage media include, for example, hard disks, solid-state drives, flash drives, magnetic data storage media, any optical or physical data storage media, memory chips, and the like.

[0211]

[0210] The storage medium is different from the transmission medium, but may be used in combination with the transmission medium. The transmission medium is involved in the transfer of information between storage mediums. For example, the transmission medium includes coaxial cables, copper wires, and optical fibers, which include wires that constitute the bus of the I / O subsystem 1302. The transmission medium may take the form of acoustic waves or optical waves, such as waves generated during radio and infrared data communications.

[0212]

[0211] Various forms of media may be involved in transporting at least one sequence of at least one instruction for execution to the processor 1304. For example, the instruction may first be transported to a magnetic disk or solid-state drive of a remote computer. The remote computer may load the instruction into its dynamic memory and transmit the instruction over a communication link such as a telephone line using optical fiber or coaxial cable or a modem. A modem or router local to the computer system 1300 may receive data over the communication link and convert the data into a format readable by the computer system 1300. For example, a receiver such as a radio frequency antenna or infrared detector may receive data transported by radio signals or optical signals, and appropriate circuitry may provide the data to the I / O subsystem 1302, such as by placing the data on a bus. The I / O subsystem 1302 transports the data to memory 1306, from which the processor 1304 retrieves and executes the instruction. The instruction received by memory 1306 may optionally be stored in storage 1310 either before or after execution by the processor 1304.

[0213]

[0212] The computer system 1300 also includes a communication interface 1318 coupled to the bus 1302. The communication interface 1318 provides bidirectional data communication coupled to a network link 1320 that is directly or indirectly connected to at least one communication network, such as network 1322 or a public or private cloud on the Internet. For example, the communication interface 1318 may be an Ethernet networking interface, an Integrated Services Digital Network (ISDN) card, a cable modem, a satellite modem, or a modem that provides data communication connectivity to a corresponding type of communication line, such as an Ethernet cable or any kind of metal cable or fiber optic line or telephone line. Network 1322 broadly represents a local area network (LAN), a wide area network (WAN), a campus network, an internetwork, or any combination thereof. The communication interface 1318 may include a LAN card that provides data communication connectivity to a compatible LAN, or a cellular radiotelephone interface that is wired to transmit or receive cellular data in accordance with cellular radiotelephone radio networking standards, or a satellite radio interface that is wired to transmit or receive digital data in accordance with satellite radio networking standards. In this implementation, the communication interface 1318 transmits and receives electrical, electromagnetic, or optical signals via a signal path that carries digital data streams representing various types of information.

[0214]

[0213] The network link 1320 typically provides electrical, electromagnetic, or optical data communications to other data devices directly or through at least one network, using, for example, satellite, cellular, Wi-Fi, or Bluetooth technology. For example, the network link 1320 may provide a connection to the host computer 1324 through network 1322.

[0215]

[0214] Furthermore, the network link 1320 may provide connectivity through network 1322, or connectivity to other computing devices via Internetworking devices and / or computers operated by an Internet Service Provider (ISP) 1326. ISP 1326 provides data communication services through a worldwide packet data communication network represented as the Internet 1328. Server computer 1330 may be connected to the Internet 1328. Server 1330 broadly represents any computer, data center, virtual computing instance with or without a virtual machine or hypervisor, or computer running a containerized program system such as DOCKER or KUBERNETES. Server 1330 may be implemented using multiple computers or instances and represent electronic digital services that are accessed and used by transmitting web service requests, uniform resource locator (URL) strings with parameters in an HTTP payload, API calls, application service calls, or other service calls. The computer system 1300 and server 1330 may form an element of a distributed computing system, including other computers, processing clusters, server farms, or other computers collaborating to perform tasks or run applications or services. Server 1330 may comprise one or more sets of instructions, organized as modules, methods, objects, functions, routines, or calls. The instructions may be organized as one or more computer programs, operating system services, or application programs, including mobile applications.The instructions may include an operating system and / or system software; one or more libraries supporting multimedia, programming, or other functions; data protocol instructions or stacks for implementing TCP / IP, HTTP, or other communication protocols; file format processing instructions for parsing or rendering files encoded using HTML, XML, JPEG, MPEG, or PNG; user interface instructions for rendering or interpreting commands in a graphical user interface (GUI), command-line interface, or text user interface; and application software such as office suites, internet access applications, design and manufacturing applications, graphics applications, audio applications, software engineering applications, educational applications, games, or other applications. Server 1330 may also include a web application server hosting a presentation layer, an application layer, and a data storage layer such as a relational database system, object store, graph database, flat file system, or other data storage, with or without using Structured Query Language (SQL).

[0216]

[0215] The computer system 1300 can send messages and receive data and instructions, including program code, through the network, network link 1320, and communication interface 1318. In the example of the internet, server 1330 may send the requested code of an application program through the internet 1328, ISP 1326, local network 1322, and communication interface 1318. The received code may be executed by processor 1304 as received, and / or stored in storage device 1310 or other non-volatile storage device for later execution.

[0217]

[0216] The execution of instructions as described in this section may be implemented as a process in the form of an instance of a computer program that is running and consists of program code and its current activity. Depending on the operating system (OS), a process may consist of multiple execution threads that execute instructions simultaneously. In this respect, a computer program is a passive collection of instructions, while a process may be the actual execution of those instructions. Multiple processes may be associated with the same program; for example, opening multiple instances of the same program often means that multiple processes are running. Multitasking may be implemented to allow multiple processes to share a processor 1304. Each processor 1304 or processor core executes a single task at a time, but the computer system 1300 may be programmed to implement multitasking that allows each processor to switch between running tasks without waiting for each task to finish. In one embodiment, switching may occur when a task performs an input / output operation, when a task indicates that it is switchable, or in the event of a hardware interrupt. Time sharing is implemented to enable fast response for interactive user applications by allowing rapid use of context switching to make it appear as if multiple processes are running simultaneously. In one embodiment, for security and reliability reasons, the operating system may prevent direct communication between independent processes, providing strictly mediated and controlled inter-process communication capabilities.

[0218]

[0217] The term “cloud computing” is used herein to typically describe a computing model that enables on-demand access to a shared pool of computing resources, such as computer networks, servers, software applications, and services, and enables rapid provisioning and resource release with minimal administrative effort or service provider interaction.

[0219]

[0218] Cloud computing environments (sometimes called cloud environments or simply clouds) can be implemented in a variety of ways that best suit various requirements. For example, in a public cloud environment, the underlying computing infrastructure is owned by the organization that makes its cloud services available to other organizations or the public. In contrast, private cloud environments are typically intended for use by or within a single organization. Community clouds are intended to be shared by multiple organizations within a community, while hybrid clouds consist of two or more types of clouds (e.g., private, community, or public) linked by data and application portability.

[0220]

[0219] Generally, the cloud computing model allows some of the responsibilities previously provided by an organization's own information technology department to be instead provided as a service layer within the cloud environment for use by consumers (either within or outside the organization, depending on the public / private nature of the cloud). Depending on the specific implementation, the exact definition of the components or functions provided by or within each cloud service layer may differ, but common examples include: Software as a Service (SaaS), where consumers use software applications running on cloud infrastructure, while the SaaS provider manages or controls the underlying cloud infrastructure and applications; Platform as a Service (PaaS), where consumers can develop, deploy and otherwise control their own applications using software programming languages ​​and development tools supported by the PaaS provider, while the PaaS provider manages or controls other aspects of the cloud environment (i.e., everything below the runtime execution environment). Infrastructure as a Service (laaS) allows consumers to deploy and run any software application and / or provision processing, storage, networking, and other basic computing resources, while the laaS provider manages or controls the underlying physical cloud infrastructure (i.e., everything below the operating system layer). Database as a Service (DBaaS) allows consumers to use database servers or database management systems running on cloud infrastructure, while the DBaaS provider manages or controls the underlying cloud infrastructure, applications, and servers, including one or more database servers.

Claims

1. A method for measuring microcalcification activity in a patient's vascular system, wherein the method is: (a) A step of measuring patient data, (i) the presence and / or amount of coronary artery plaque or visible disease markers in the vascular tissue sample derived from the patient's vascular system, (ii) The presence and / or amount of healthy tissue in the vascular tissue sample derived from the patient's vascular system, (iii) One or more characteristics that define the abnormal hemodynamic environment within the blood vessels originating from the patient's vascular system, (iv) One or more geometric features associated with vascular remodeling that affect intravascular hemodynamics originating from the patient's vascular system, and / or (v) A step of measuring patient data including one or more material properties that affect intravascular hemodynamics originating from the patient's vascular system, (b) A method comprising the step of predicting NaF uptake in the vascular system of the patient as a function of the patient data.

2. The method according to claim 1, wherein step (b) includes the step of calculating the NaF tissue-to-background ratio.

3. The method according to claim 1, wherein the patient data is derived from patient image data.

4. The patient image data is Computed tomography data, Optical coherence tomography data, Intravascular ultrasound data, X-ray angiography data, Magnetic resonance image data, Angiography image data, or CT angiography image data The method according to claim 3, wherein one or more of the following are present.

5. The method according to claim 1, wherein the patient data includes biomechanical measurements.

6. The biomechanical measurement values ​​are blood pressure, Blood flow or local hemodynamic characteristics, and The method according to claim 5, wherein the biomechanical measurement value is selected from the group consisting of tissue stress.

7. The method according to claim 1, wherein the one or more geometric features described above correspond to the atherosclerotic process and / or microcalcification activity.

8. The method according to claim 1, wherein the one or more geometric features described above correspond to image-based diameter measurements within blood vessels prone to calcification.

9. A computer-implemented method for measuring microcalcification activity in a patient's vascular system, wherein the method is: (a) A step of measuring patient data, (i) the presence and / or amount of coronary artery plaque or visible disease markers in the vascular tissue sample derived from the patient's vascular system, (ii) The presence and / or amount of healthy tissue in the vascular tissue sample derived from the patient's vascular system, (iii) One or more characteristics that define the abnormal hemodynamic environment within the blood vessels originating from the patient's vascular system, (iv) One or more geometric features associated with vascular remodeling that affect intravascular hemodynamics originating from the patient's vascular system, and / or (v) A step of measuring patient data including one or more material properties that affect intravascular hemodynamics originating from the patient's vascular system, (b) A method comprising the step of using a trained machine learning model, regression model or predictive model to predict NaF uptake in the patient's vascular system as a function of the patient data.

10. The method according to claim 9, wherein the trained machine learning model includes a first trained regression model or a predictive model.

11. The method according to claim 1, wherein the patient's vascular system is one or more of the coronary arteries, carotid arteries, cerebral arteries, aorta, peripheral arteries, or veins.

12. The method according to claim 1, wherein the patient data includes CT angiography image data.

13. A computer system, wherein the computer system is At least one processor, A memory device for storing patient data, wherein the patient data is (i) the presence and / or amount of coronary artery plaque or visible disease markers in the vascular tissue sample derived from the patient's vascular system, and / or (ii) The presence and / or amount of healthy tissue in the vascular tissue sample derived from the patient's vascular system, and / or (iii) One or more characteristics that define an abnormal hemodynamic environment within a blood vessel originating from the patient's vascular system, and / or (iv) One or more geometric features associated with vascular remodeling that affect intravascular hemodynamics originating from the patient's vascular system, and / or (v) With respect to one or more material properties that affect the hemodynamics of blood vessels originating from the patient's vascular system, The at least one processor is configured to use a trained machine learning model, regression model, or predictive model to calculate microcalcification activity in the blood vessels as a function of the patient data, and includes at least one memory device. A computer system comprising: an AI-trained model for the patient data; and a predictive processor for predicting NaF uptake in the patient's vascular system.

14. The computer system according to claim 13, wherein the processor is adapted to calculate the NaF tissue-to-background ratio.

15. The computer system according to claim 13, wherein the patient data is derived from patient image data.

16. The patient image data is Computed tomography data, Optical coherence tomography data, Intravascular ultrasound data, X-ray angiography data, Magnetic resonance image data, Angiography image data, or CT angiography image data The computer system according to claim 15, wherein one or more of the following are included.

17. The computer system according to claim 13, wherein the patient data includes biomechanical measurements.

18. The biomechanical measurement is blood pressure, Blood flow or local hemodynamic characteristics, and The computer system according to claim 17, wherein the biomechanical measurement value is selected from the group consisting of tissue stress.

Images