Systems and methods for improving soft tissue contrast, multi-scale modeling and spectral CT - Patents.com

Abstract

Systems and methods are provided for improving soft tissue contrast, characterizing tissue, classifying phenotypes, stratifying risk, and performing multi-scale modeling aided by multi-energy or multi-contrast excitation and evaluation, including using single and multi-phase acquisitions, as well as broad and localized spectral imaging to assess atherosclerotic plaque tissue, for example, in vessel walls and perivascular spaces.

Description

[Technical field]

[0001] (CROSS REFERENCE TO RELATED APPLICATIONS) This application claims the benefit of and priority to U.S. Provisional Patent Application No. 63 / 147,609, filed February 9, 2021, the entire contents of which are incorporated herein by reference in their entirety and are owned by the assignee of this application.

[0002] (Government Licensing Rights) This work was supported in part by the National Heart, Lung and Blood Institute under Contract No. HL 126224. The U.S. Government may have certain rights in this invention.

[0003] The present invention relates to computer-aided phenotyping (CAP) of disease, which involves the application of computerized image analysis and / or data fusion algorithms to patient data. In particular, the present invention relates to quantitative imaging and analysis to elucidate the disease process of atherosclerosis, including techniques to improve soft tissue contrast, multi-scale modeling and / or spectral CT. [Background technology]

[0004] Atherosclerosis can be life-threatening, especially in older people, but also in relatively young people. Currently, there are limited methods for diagnosing atherosclerosis (e.g., using blood markers such as cholesterol levels) and / or determining the degree of luminal narrowing (stenosis), which makes it difficult to determine the optimal treatment (e.g., performing or not performing surgery, or prescribing intensive drug therapy). For example, many vascular surgeries are not helpful for patients, some patients require surgery but cannot undergo surgery, and others can be effectively treated with drugs but are not prescribed them.

[0005] Current tools can analyze the vessel lumen but may be insufficient to accurately diagnose atherosclerosis because it is a disease of the vessel walls, not of the blood and the passageways through which it flows. Misclassification of risk levels, inability to assess expected response to drug therapy, and / or inability to measure response to drugs are likely to occur.

[0006] Radiation imaging can now be used as a non-invasive and safe method to identify the cause of disease. Current medical imaging tools may include computed tomography (CT, including single-energy, multi-energy, or spectral CT), magnetic resonance imaging (MR, including MRA, DCE-MRI, or multi-contrast MRI), ultrasound (b-mode or intravascular US), and targeted contrast agent approaches using a variety of imaging modalities.

[0007] Advances in imaging technology have made medical imaging an essential component of patient care. Imaging is valuable because it can provide spatially and temporally localized anatomical and / or functional information using non-invasive or minimally invasive methods. However, techniques are required to address the increased resolution, such as exploiting patterns and / or signatures in the data that are not readily assessable by the human eye, and to manage large amounts of data and efficiently integrate them into clinical workflows. New high-resolution imaging techniques allow radiologists to "drown" in data without assistance. Thus, for example, to integrate quantitative imaging for individual patient management, it is desirable to provide a class of decision support informatics tools that allow further utilization of imaging capabilities within the realities of existing tool workflows and / or reimbursement constraints.

[0008] Imaging of atherosclerosis is now routinely performed both invasively by catheter insertion and non-invasively by use of ultrasound, CT, MR and nuclear medicine techniques. The most typical assessment is luminal stenosis. A recent development has been the determination of fractional myocardial flow reserve.

[0009] Currently, one difficulty with imaging atherosclerosis is the lack of robustness of the methods used. For example, current methods typically have low contrast between the outer vessel wall and perivascular tissue, making it difficult to distinguish between the two. Current methods simply utilize an annular ring that surrounds the lumen without specifically determining the outer wall boundary. Tapering of the vessel, branching vessels, nearby tissue, etc. can also be problematic.

[0010] Another difficulty with current atherosclerosis imaging may be due to the specific imaging equipment using limited excitation to obtain information from tissues, and despite the use of multi-contrast MR or multi-energy CT, there may be some degree of non-specific reaction in the generated signal. Summary of the Invention

[0011] Advantages of the invention may include improving soft tissue contrast. Some advantages of the invention may include improving tissue characterization. Some advantages of the invention may include phenotyping. Some advantages of the invention may include risk stratification. Some advantages of the invention may include performing multi-scale modeling aided by multi-energy or multi-contrast excitation and evaluation.

[0012] Some advantages of the present invention may include the use of single-phase multi-phase acquisition and wide-spectrum CT to evaluate atherosclerotic plaque tissue in the vessel wall and perivascular space. Some advantages of the present invention may include the use of distributed tissue types as an overlay of locally organized tissue.

[0013] In one aspect, the invention includes a computerized method for improving analysis of soft tissue. The method may further include acquiring a plurality of radiographic images of a patient, each of the plurality of radiographic images being acquired with a different excitation. The method may further include selecting a process from a plurality of processes for analyzing the plurality of excitations based on an expected soft tissue type. The method may further include segmenting the processed plurality of excitations to represent the soft tissue.

[0014] In some embodiments, the multiple radiographic images are computed tomography (CT) images and the different excitations are different X-ray energies, hi some embodiments, the multiple radiographic images are magnetic resonance (MR) images and the different excitations are different radio frequency pulses.

[0015] In some embodiments, the multiple radiological images are ultrasound images and the different excitations are at different frequencies.

[0016] In some embodiments, the invention includes determining, by a computing device, a first tissue type within a region of interest based on a plurality of the radiological images of the patient, the first tissue type being represented by a grid of points across the region of interest; and determining, by the computing device, a second tissue type within the region of interest based on a plurality of the radiological images of the patient, the second tissue type being a focal region within the region of interest, and at least some grid points of the first tissue type being coincident with grid points of the second tissue type.

[0017] In some embodiments, the plurality of processes comprises a digital subtraction process, a digital addition process, a multivariate statistical process, or an excitation selection process. In some embodiments, the digital subtraction process comprises subtracting a first subset of the plurality of radiographic images from one or more of the plurality of radiographic images that are not in the subset. The digital addition process comprises averaging the received plurality of radiographic images.

[0018] In some embodiments, the multivariate statistical processing comprises combining the multiple radiological images and removing inter-class dependencies by a multivariate statistical approach.

[0019] In some embodiments, the plurality of radiographic images are CT images, and each of the plurality of CT images is generated by directing a first X-ray attenuation by a first X-ray source to an energy integrating detector sized to generate the image of a predetermined area of ​​the patient, directing a second X-ray attenuation by a second X-ray source to a photon counting detector that generates an image of a particular tissue target within the predetermined area, and generating a final CT image by a processor based on the image of the predetermined area of ​​the patient and the image of the particular tissue target within the predetermined image.

[0020] In some embodiments, the excitation selection process includes selecting a particular radiographic image from the plurality of radiographic images based on the tissue type.

[0021] In another aspect, the invention includes a hybrid computed tomography (CT) scanner. The hybrid CT scanner may include a first x-ray source that directs a first x-ray attenuation to an energy integrating detector sized to generate an image of a predetermined region of a patient. The hybrid CT scanner may further include a second x-ray source that directs a second x-ray attenuation to a photon counting detector that generates an image of a specific tissue target within the predetermined region. The hybrid CT scanner may further include a processor that generates a final computed tomography (CT) image based on the image of the predetermined region of the patient and the image of the specific tissue target within the predetermined image.

[0022] In some embodiments, the energy integrating detector and the photon counting detector are positioned to obtain information from the same field of view. In some embodiments, the image of the predetermined area of ​​the patient is a grayscale CT image. In some embodiments, the image of the specific tissue target within the predetermined image is a spectral CT image. In some embodiments, the energy integrating detector is positioned relative to the first x-ray source such that it is offset 90 degrees between the photon counting detector and the second x-ray source.

[0023] In some embodiments, the processor is configured to analyze tissue type, the analysis including selecting a process from a plurality of processes to analyze the final CT image based on an expected soft tissue type, and segmenting the processed final CT image to display the soft tissue.

[0024] In some embodiments, the photon-counting detector includes multiple energy bins configured to image the specific tissue target.

[0025] In another aspect, the invention includes a computerized method for determining and displaying mixed tissue types. The method may include receiving, by a computing device, a radiological image of a patient. The method may include determining, by the computing device, a first tissue type within a region of interest based on the radiological image of the patient, the first tissue type being represented by a grid of points across the region of interest. The method may include determining, by the computing device, a second tissue type within the region of interest based on the radiological image of the patient, the second tissue type being a localized region within the region of interest, and at least some grid points of the first tissue type being coincident with grid points of the second tissue type.

[0026] In some embodiments, the multiple radiological images are computed tomography (CT) images, magnetic resonance (MR) images, or ultrasound images. In some embodiments, the first tissue type and the second tissue type are overlaid. In some embodiments, the grid of points has a varying density.

[0027] In some embodiments, the first tissue type is microcalcified tissue and the second tissue type is LNRC, dense calcification, or IPH.

[0028] In some embodiments, the method includes performing, by the computing device, multi-energy photon counting K-edge subtraction imaging of the CT image; performing, by the computing device, spectral image denoising of the CT image using a regularization model; improving, by the computing device, the signal-to-noise ratio of calcium on the K-edge subtracted and denoised CT image; and segmenting, by the computing device, the improved calcium image to represent one or both of focal dense calcifications and diffuse microcalcifications. [Brief description of the drawings]

[0029] Non-limiting examples of embodiments of the present disclosure will now be described with reference to the accompanying drawings hereof, listed after this paragraph, in which dimensions of features shown in the drawings have been chosen for convenience and clarity of presentation and are not necessarily drawn to scale.

[0030] The subject matter of the present invention is particularly pointed out and distinctly claimed in the concluding portion of the specification. However, the organization and method of operation of the invention, together with its objects, features and advantages, may be understood by reading the following detailed description when taken in conjunction with the accompanying drawings, in which: Embodiments of the present invention are illustrated by way of example, and not by way of limitation, in the accompanying drawings in which like reference characters indicate corresponding like or similar elements.

[0031] [Figure 1] 4 is a diagram of an exemplary radiation input and processed output according to some embodiments of the present invention. [Diagram 2] 1 is a diagram illustrating an example where atherosclerosis progresses with common drivers across arterial beds to different degrees based on evolutionary differences and local factors, according to some embodiments of the present invention. [Diagram 3]1 is an example of a first set of CT scans and a second set of CT scans with improved soft tissue contrast according to some embodiments of the present invention. [Figure 4] 1 is a diagram of a system for improving soft tissue segmentation according to some embodiments of the present invention. [Diagram 5] 1 is an example of a method for improving soft tissue segmentation according to some embodiments of the present invention. [Figure 6] FIG. 1 is a front cross-sectional view of a hybrid computed tomography (CT) scanner according to some embodiments of the present invention. [Figure 7A] 1 shows an example of a multi-scale correlation linking radiological plaque morphology to molecular determinants, according to some embodiments of the present invention. [Figure 7B] 1 is an example of multi-scale modeling according to some embodiments of the present invention. [Figure 7C] 1 is an example of extended multi-scale modeling in accordance with some embodiments of the present invention. [Figure 8] 13 is an example of an output screen showing multiple simulated event-free survival probabilities under no treatment and various treatment scenarios, according to some embodiments of the present invention. [Figure 9] 1 illustrates a method for determining and displaying mixed tissue types according to some embodiments of the present invention. [Figure 10] 1 illustrates a method for determining and displaying mixed tissue types of microcalcification screens and dense calcification regions using radiological images of multi-energy spectral CT images, according to some embodiments of the present invention. [Figure 11] 11 is a diagram illustrating an example of the method of FIG. 10 according to some embodiments of the present invention.

[0032] It will be appreciated that for simplicity and clarity of the drawings, elements shown in the figures have not necessarily been drawn accurately or to scale, for example, dimensions of some elements may be exaggerated relative to other elements for clarity and multiple physical components may be included in a single functional block or element. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0033] In general, the invention includes systems and methods for improving soft tissue contrast, characterizing tissue, classifying phenotypes, stratifying risk, and / or performing multi-scale modeling aided by multi-energy or multi-contrast excitation and evaluation. The invention may include the application of single-phase multi-phase image acquisition and may also include the use of broad-spectrum CT to evaluate atherosclerotic plaque tissue, for example, in vessel walls and / or perivascular spaces.

[0034] In general, the invention may involve utilizing a software approach to exploit the different responses of tissues to multi-energy or multi-spectral image sets. The invention may further include hardware configurations that can further identify a range of clinically relevant tissues. Spectral images acquired via multiple energy levels and / or broad spectrum can form the input for one or more algorithms that can improve tissue segmentation.

[0035] In some embodiments, the algorithm may include noting that the noise is similar across multiple energies, but the tissues are different, and taking advantage of the non-linear response to different tissues by applying averaging techniques that result in a higher signal to noise ratio.

[0036] In some embodiments, different tissues can be resolved better at one energy level than another. In some embodiments, different energies are selected for each tissue. In some embodiments, a digital subtraction approach is used to exploit the non-linear responses to different tissues. In some embodiments, the different tissue responses from each of the optimal energy levels are combined and dependencies between classes are removed through a multivariate statistical approach. In various embodiments, each of these aforementioned embodiments is applied to hardware configurations that amplify such differences, whether designed based on material composition or other physical phenomena, to achieve a benefit. Examples include tissues differentiated by molecular properties, cellular and molecular environment, material density distribution, morphological expression, response to stimuli, etc.

[0037] In some embodiments, the dispersed tissue type is used as an overlay of locally organized tissue.

[0038] 1 is a diagram 100 of an exemplary radiation input 110 and processed output according to some embodiments of the present invention. The processed output may include an image 120 identifying three-dimensional regions for various measurements of calcification, lipid-rich necrotic core (LRNC), and matrix, and an image 130 presenting tables and graphs of data related to the various measurements. As will be apparent to one of ordinary skill in the art, the measurements shown in FIG. 1 are examples and may include other measurements.

[0039] FIG. 2 is a diagram 200 illustrating an example where atherosclerosis progresses with common drivers across arterial beds to different degrees based on evolutionary differences and local factors, according to some embodiments of the present invention.

[0040] Characterization of coronary artery disease can be performed by evaluation of two related but distinct mechanisms: the ability of the arterial system to meet the demand under stress required to deliver more oxygenated blood to downstream perfused tissues, i.e., stress-induced ischemia (e.g., measured as FFR or iFR), and the tendency of plaque to physically break down or embolize, i.e., infarction risk (HRP). Based on the processed output (e.g., the processed output described above in FIG. 1 and below), a treatment path can be optimally selected to characterize the degree to which each of the different mechanisms is present, e.g., to different degrees, one without the other, neither, or both. In some embodiments, the low or high probability of a condition is used to predict the time to adverse event at the individual patient level. Recommendations can be made based on the FRR / HRP ratio. Recommendations can be made based on the probability of the condition and may include maintenance medication, intensive drug therapy, symptomatic treatment, or revascularization.

[0041] In some scenarios, it is desirable to identify tissue types (e.g., complex tissues) that have complex cellular or molecular-level environments that manifest as overlapping material densities. Current methods may be inaccurate and fail to correctly identify tissue types. Current methods may include simple thresholding of material density given by Hounsfield Units (HU) of a voxel. For example, LRNC or idiopathic pulmonary hemosiderosis (IPH) may not be easily and / or reliably identified, and / or the biological processes that cause them and / or are induced in response to them may be complex. LRNC is variably composed of lipid deposits, cholesterol crystals, apoptotic cell debris, macrophages, and / or calcifications. IPH is variably composed of intact and / or ruptured red blood cells, macrophages, hemorrhagic debris, fibrin, cholesterol crystals, and / or calcifications. Complex tissues can present challenges for systems using a single excitation energy for CT or characteristic RF profiles for MR, and heterogeneity in plaque components can be exploited based on differences in tissue response to excitation, e.g., how it responds to one energy versus another, or to one radio frequency versus another, and tissues can respond differently to various energies. Therefore, it is desirable to relax the strict material density dependency. In some embodiments, to relax the strict material density dependency, different density distributions can be mathematically fitted to samples from histopathology.

[0042] In some embodiments, multi-energy signals can be applied during a CT scan, and digital subtraction, averaging, and / or selection techniques can be used to amplify the signal of one tissue type over another, and to relax the strict material density dependence using all levels of noise. In some embodiments, as an exemplary embodiment, the HU of adjacent voxels can be analyzed as a distribution, rather than just as individual voxels, by maximizing the Mumford-Shah function.

[0043] Similar to the stains applied to tissues that help pathologists make judgments when outlining LRNC and IPH, the present invention can be understood to apply "digital stains" to images to achieve similar amplification, since these tissues are heterogeneous and overlapping tissues are composed of multiple cell types with different densities, each tissue responding differently to different incident energies. Pathological annotations that take this into account need to be established using similar judgments as pathologists do with histology, so that clinical insights based on it can be applied when pathologists mark the tissue boundaries of LRNC and IPH on CTA. This does not suffice to apply HU thresholds alone; it requires a mathematical formalism that can be used to mimic the judgments used by human pathologists who are trained to identify tissues.

[0044] MRI, ultrasound, nuclear medicine, and / or other imaging modalities can be reconstructed at various strengths and weaknesses before post-processing. Figure 3 is an example of a first set of CT scans 310a, 320a and a second set of CT scans 310b, 320b with improved soft tissue contrast according to some embodiments of the present invention. A CT scan 310a in the first set of CT scans shows two regions 330a, 340a that are improved in a CT scan 310b in the second set of CT scans as seen in 330b, 340b. A CT scan 320a in the first set of CT scans shows a region 350a that is improved in a CT scan 320b in the second set of CT scans as seen in 350b.

[0045] 4 is a diagram of a system 400 for improving soft tissue segmentation according to some embodiments of the present invention. The system may include an imaging device 410 and a classification unit 430.

[0046] The imaging device 410 may be a CT scanner, a magnetic resonance imaging device, an ultrasound device, and / or other imaging devices known in the art. The imaging device 410 may acquire one or more radiological images (e.g., CT, MR, ultrasound) 420. The multiple radiological images 420 may be monochromatic. The multiple monochromatic images 420 may be taken with multiple excitations. As will be apparent to one of ordinary skill in the art, the multiple images taken with multiple excitations may be the result of transmission, reception, or any combination thereof.

[0047] The multiple excitations may include multiple energies, radio frequency pulses (e.g., sequences), and / or different frequencies or timing, such as those used by CT, MRI, and / or ultrasound, respectively. In some embodiments, each of the multiple monochromatic images 420 is taken with a unique excitation (e.g., a unique x-ray energy, transmitted, received, or both, as a narrow energy range or as a broad range) of the CT scanner, a unique pulse sequence of the MRI, a unique frequency and / or timing of the ultrasound.

[0048] The number of multiple monochromatic images 420 may depend on the type of tissue or phenotype desired to be identified.

[0049] In some embodiments, some monochromatic images 420 of the plurality of monochromatic images 420 are taken with the same excitation and other monochromatic images 420 are taken with different excitation. For example, the excitation may change between every two monochromatic images 420. In another example, only the first two monochromatic images 420 are with the same excitation and the remaining monochromatic images 420 are taken with unique excitation. As will be apparent to one skilled in the art, the plurality of monochromatic images 420 may include any combination of the same and unique excitation.

[0050] The excitation may depend on the expected tissue type. For example, for an expected tissue type of calcium and a CT imaging device, the excitation (transmitted, received, or both) may be 4 keV. In another example, for an expected tissue type of oxygen and a CT imaging device, the excitation (transmitted, received, or both) may be 530 eV.

[0051] In the example shown in FIG. 4, multiple monochromatic images 420 are shown taken with a CT imaging device and an exemplary range of excitation (transmitted, received, or both) of 65 KeV to 130 KeV, although excitation may be as low as 0.5 keV or as high as 400 keV, depending on the tissue of interest, and such a spectrum allows for identification of the tissue type specifically identified as 440.

[0052] The classification unit 430 may include a number of processes that analyze the number of monochromatic images 420. The multiple processes may include a digital subtraction process, a digital addition process, a multivariate statistical process, and / or an excitation selection process, as described in further detail below with respect to FIGURE 5. The classification unit 430 may output data 440 indicative of one or more classified tissue types (e.g., tissue type segmented image data and / or other data shown in FIGURE 1 above).

[0053] The output data 440 may be classified into tissue types including blood leakage, macrophages, angiogenesis, CALC map, LRNC map, FRESH IPH map, MATX map, microcalcifications, erosions, OLD IPH map, thrombus, or any combination thereof. As will be appreciated by one of ordinary skill in the art, the output data may be any tissue type known in the art.

[0054] 5 is an example of a method 500 for improving soft tissue segmentation according to some embodiments of the present invention. The method may include acquiring a plurality of radiological images (e.g., CT images, MRI images, ultrasound images). The radiological images may be acquired by a hybrid CT imaging apparatus as shown in FIG. 6 below. Each of the plurality of radiological images may be acquired using a different excitation (step 510).

[0055] In some embodiments, the multiple radiographic images are CT images and the different excitations are different X-ray energies (transmitted, received or both, as a narrow energy range or as a broad range). In some embodiments, the multiple radiographic images are MR images and the different excitations are different radio frequency pulses. In some embodiments, the multiple radiographic images are ultrasound images and the different excitations are different frequencies.

[0056] The method may include selecting (step 520) a process from a plurality of processes for analyzing the plurality of radiographic images based on the expected soft tissue type (e.g., by classification unit 430). The plurality of processes may include a digital subtraction process, a digital addition process, a multivariate statistical process, and / or an excitation selection process.

[0057] The selection of one treatment from multiple treatments may be random, based on user input, and / or based on tissue characteristics.

[0058] The digital subtraction process may include taking one of the multiple radiographic images in a spectral range and subtracting it from another of the multiple radiographic images. In some embodiments, the digital subtraction may include subtracting a first subset of the multiple radiographic images from one or more of the multiple radiographic images that are not in the subset. In some embodiments, the digital subtraction process may include subtracting a narrow range from a wide range, for example to raise a narrow band signal above a wide band noise floor. In some embodiments, the digital subtraction process may include subtracting one intermediate bandwidth from another intermediate bandwidth to distinguish between two related tissue types.

[0059] The digital summation process may include averaging multiple radiographic images, which is advantageous since noise is generally similar across energies, but not for tissue signals, as averaging can lead to a higher signal to noise ratio.

[0060] Multivariate statistical processing may include combining each of the multiple radiological images with a mathematical operator other than simple subtraction or addition, and removing inter-class dependencies through a multivariate statistical approach from a set of techniques identified as non-linear operators.

[0061] The excitation selection process may include selecting one radiographic image or a subset of radiographic images of the plurality of images for a particular tissue type because a particular tissue type may be well resolved at one energy level or a subset of energy levels. For example, the energy dependence of one tissue may be at a plateau point at high or low kVp levels, while the energy dependence of other tissues may be in another range, suggesting that one range is used for one tissue and another range is used for other tissues.

[0062] The processed radiological images can be input to one or more classification models. In some embodiments, the classification models may be trained as described in U.S. Patent No. 11,094,058, filed November 28, 2018, which is incorporated by reference herein in its entirety.

[0063] The method may include segmenting the processed plurality of radiological images to represent the soft tissue, step 530. In some embodiments, segmenting the processed plurality of excitations further includes segmenting the medical image data into three-dimensional (3D) objects.

[0064] In some embodiments, segmenting the processed plurality of radiological images includes segmenting the processed plurality of radiological images into an outer wall boundary. In some embodiments, the segmenting includes segmenting the plurality of radiological images into lumen and outer wall based on the segmented lumen boundary, outer wall, perivascular region, and / or lesion tissue boundary. Figure 4 of U.S. Pat. No. 11,094,058 shows examples of segmentation levels of a multi-scale vessel wall analyte map along with corresponding descriptions.

[0065] 6 is a front cross-sectional view of a hybrid computed tomography (CT) scanner 600, a processor 670, and two analog-to-digital converters 655, 665, according to some embodiments of the present invention. The hybrid CT scanner 600 can provide truncated spectral scans and / or local reconstructions constrained to a global grayscale image from a conventional CT configuration.

[0066] The hybrid CT scanner 600 includes a first X-ray source 610, a second X-ray source 620, a photon-counting detector 630, an energy-integrating detector 640, and a gantry 650. The energy-integrating detector 640 may be disposed at a predetermined angle with respect to the first X-ray source 610, between the photon-counting detector 630 and the second X-ray source 620.

[0067] The predetermined angle is approximately 90 degrees, as shown in Figure 6. The predetermined angle can be based on optimizing the physical space around the arc to allow the integrating detector to cover a wide range.

[0068] The first X-ray source 610 and / or the second X-ray source 620 may be a polychromatic X-ray source. The first X-ray source 610 and / or the second X-ray source 620 may be any X-ray source known in the art for use in CT scanners.

[0069] During operation, a patient 660 enters the hybrid CT scanner 600 and a first x-ray source 610 can direct a first x-ray attenuation toward the patient 660 and the energy integrating detector 640. The energy integrating detector 640 can be sized to generate an image of a predetermined region of the patient 660.

[0070] The energy integrating detector 640 can have a curvature defined by a radius R and a diameter D and extend along an arc A such that a predetermined area of ​​the patient is imaged. For example, the radius R can be 30 inches, the diameter D can be 60 inches, and the arc A can be 135 degrees.

[0071] In some embodiments, the first x-ray attenuation is transmitted in the range of 65 to 130 keV, or a broader range.

[0072] The energy integrating detector 640 receives at least a portion of the first x-ray attenuation and the energy transmitted through the patient 660 .

[0073] A second x-ray source 620 can direct a second x-ray attenuation toward the patient 660 and the photon-counting detector 630. The photon-counting detector 630 can generate an image of a particular tissue target within a predetermined region.

[0074] In some embodiments, the second X-ray attenuation is transmitted to a similar extent or a different extent than the first embodiment.

[0075] The photon-counting detector 630 receives at least a portion of the second x-ray attenuation and the energy transmitted through the patient 660 .

[0076] The energy integrating detector 640 and the photon counting detector 630 transmit the energy they receive to the processor 670 via A / D converters 655 and 665, respectively.

[0077] It is known that if an object is piecewise constant, a compressed sensing-based reconstruction algorithm can be used to accurately reconstruct the region of interest. TV minimization-based spectral intra-reconstruction finds important applications in the CT field, such as dose reduction, fast data acquisition, easy data storage, and hardware cost reduction. The assumption made in many reconstruction schemes that the imaged object is piecewise constant is usually not met in clinical CT imaging due to tissue composition and / or contrast agents with gradient densities much smaller than the voxel scale, so to avoid this assumption, the inventors use a global energy integral type image to facilitate intra-spectral CT reconstruction and minimize reconstruction errors due to significant data truncation using processor 670.

[0078] A processor 670 receives the output from the energy integrating detector 640 and the photon counting detector 630 and processes the images to generate a final CT image based on the image of the predetermined area of ​​the patient and the image of the particular tissue target within the predetermined image. The final CT image can be used as input for the processing described above in FIG.

[0079] The processor 670 may include multiple processing modules. The processing modules may include a module 671 that receives the spectral CT from the photon-counting detector 630 from the A / D converter 655. The spectral CT can be sent to the photon-counting detector signal processing module 672 to create a sinogram. The sinogram can be sent to the local scan module 673 for reconstruction. Module 675 may receive the grayscale CT from the energy-integrating detector 640 from the A / D converter 675. The grayscale CT can be sent to the energy-integrating detector processing module 676 to create a sinogram. The sinogram can be sent to the global scan module 677 for reconstruction. The output of the local scan module 673 (e.g., a narrowband output) and the output of the global scan module 677 (e.g., a multi-energy output (e.g., multiple narrowband outputs or a single wideband output) that can obtain information from more energies than the local scan).

[0080] As is known in the art, the processing modules on processor 670 may be implemented with a single processor or multiple processors.

[0081] The energy-integrating detector 640 may be considered a global scan of the patient 660, while the photon-counting detector 630 may be considered a local scan. The CT image from the energy-integrating detector 640 may be used for standalone CT reconstruction or as a global grayscale constraint for intra-spectral CT local tomography reconstruction using the photon-counting detector 630. The photon-counting detector 630 may include multi-energy bins configured to image specific tissue targets, and multiple channels of the reconstructed global grayscale constraint spectral image may be used to reveal and differentiate tissues.

[0082] The intra-spectral CT reconstruction using the grayscale image as the global constraint can be determined as follows:

[0083] N is the number of spectral channels (e.g., the number of energies or tube voltages in a CT image), and I i Assume that u is the photon intensity in a particular spectral channel and i is the channel index. The energy integral projection image is given by

number

number

number

number

[0084] δμ i Assuming that (r) is small enough, we use a Taylor series expansion and ignore higher order terms,

number

[0085]

number

number

[0086] In addition,

number

[0087] Assuming there are three channels, i.e., N=3,

number

[0088]

number

[0089]

number

[0090] where N is the total number of spectral channels and I is the photon intensity emitted by the X-ray source. i is the photon intensity in a spectral channel, i is the spectral channel index, μ is the attenuation map to be reconstructed, B is the detected photon intensity from the spectral channel, G is the detected grayscale photon intensity, r is the spatial position in the 3D space, δ is the small change, and exp(x) is the exponential function.

[0091] FIG. 7A shows an example of a multi-scale association linking radiological plaque morphology to molecular determinants, according to some embodiments of the present invention. For example, prediction-based scoring, including validation of surrogate markers, can be used for (1) dynamic vascular performance, including, for example, performance in hyperemia (e.g., a cause of ischemia) and / or rupture risk (e.g., a cause of infarction) (2). Quantification of morphometric quantities, including, for example, but not limited to, IPH, can be analyzed with modalities including, for example, single-energy CTA or multispectral CTA (3). Fluid mechanics, e.g., shear stress assessment and finite element modeling (FEM), can elucidate the mechanical triggers of smooth muscle cell (SMC) differentiation (4) and substantiate (2).

[0092] FIG. 7B is an example of multi-scale modeling according to some embodiments of the present invention. In FIG. 7B, x represents cellular and / or molecular species predisposition and / or expression (e.g., characterizing tissue), y represents macromolecular tissue presentation assayed by radiology and / or used to classify phenotypes, and z represents predicted outcomes (such as risk stratification), simulated progression, and / or simulated regression under different classes of treatment. When x and y are known, x and y can be used to train the model, generate hypotheses, and / or provide a basis for simulations. When x is known but y is not, or vice versa, a predictive model can be utilized once trained using examples where both x and y are known. One exemplary objective is to provide a means that is practically and / or economically easy to implement clinically to obtain information across scales.

[0093] In some embodiments, causality can be analytically established, such as whether x causes y and / or if y is seen, can a mechanism be identified where levels of x likely produce y. In some embodiments, the utility of such analysis includes being able to individualize treatment, where knowing x tells us what particular drug or surgical intervention may be optimal.

[0094] In some embodiments, analytical methods can be used to establish whether the relationship between x and y can be spatially differentiated to determine, for example, whether specificity can increase diagnostic confidence by avoiding dilution that results from not taking spatial context into account, as well as the value of single cell techniques over techniques that do not provide differentiation.

[0095] FIG. 7C is an example of extended multi-scale modeling according to some embodiments of the present invention. Extending the multi-scale modeling technique, x, y, and z may include the addition of time-dependent functions. For example, x(t) may represent plaque development, such as due to premature aging and / or other mechanistic explanations at the cellular / molecular level, y(t) may represent macroscopic phenotypes observed over time in radiology, and z(t) may predict what will happen next under a candidate treatment plan (including, for example, if left untreated). In some embodiments, the analysis provides y(t) as a 3D object validated with histology for a spatially resolved basis at the macroscopic level, and / or also appears in convolutional neural networks for phenotype classification. To connect to the molecular / cellular level, literature can be mined or tissue resources can be used to augment de novo experiments for data collection.

[0096] 8 is an example of an output screen 800 showing multiple simulated event-free survivability probabilities under no treatment and various treatment scenarios, according to some embodiments of the present invention. The simulated event-free survivability probabilities include systemic inflammation treatment 810, intensive lipid-lowering treatment 820, statins 830, revascularization (e.g., stent) 840, and no treatment 850.

[0097] Whether single or multi-energy CT scans are acquired, complex tissue presentations (e.g., tissue in regions containing more than one tissue type at a particular location) can be identified. For example, complex tissue regions may have microcalcifications occurring, such as with MATX or LRNC. Adaptive grid sizing and / or adaptive region growing can be used to create nuanced representations of complex tissue types. Complex biology can be represented as screen or grid point overlays, and the progression of complex biology, not just the end result, can be determined. For example, the progression of microcalcifications, not just the end result of dense macrocalcifications, can be determined.

[0098] Such screen or grid point overlays can generally enhance the presentation of the focal tissue without replacing it. Continuing with the example of microcalcifications, the subjective term "patchy calcification" is used, but this term fails to express intermediate signs of local organization. In one embodiment, intermediate signs of local organization of microcalcifications can be visually represented as a "grid overlay" that displays sparse or dense dots (e.g., dot density, rather than material density) to show the pattern of organization.

[0099] The grid overlay can be represented as a "texture" for a human observer to visualize in software, and / or as "mottling" for a data object well suited for computer processing. Thus, tissue organization can affect MATX as well as LRNC and / or other tissue regions. Similar to IPH, microcalcifications can be subdivided into two tissue / stage types: dense and / or early stage. Microcalcifications may become grids, while dense macrocalcifications may become foci. The microcalcification grid generalizes how tissues are represented and can be interpreted as a distribution of foci that can represent transitional states where foci are clustered. For example, not yet clustered, but approaching clustered. Tissue types such as blood leakage, microcalcifications, angiogenesis, etc. can be represented as grids of various point densities. Tissue types represented as localized regions, such as LRNC, CALC, IPH, etc., may become localized regions. MATX can be expressed as localized regions, but preferably have regions described as other tissues.

[0100] FIG. 9 illustrates a method 900 for determining and displaying mixed tissue types according to some embodiments of the present invention.

[0101] The method may include receiving a radiological image of a patient (step 910). The radiological image may be a CT image, an MR image, or an ultrasound image. If the radiological image is a CT image, the CT image may be acquired using a hybrid CT imaging device, as described in FIG.

[0102] The method may include determining a first tissue type within the region of interest based on a radiological image of the patient, the first tissue type being a grid of points in the region of interest (step 920). For example, the first tissue type may be any tissue type that can progress from less dense to more dense. The first tissue type may be any tissue type that can disperse into another tissue type. The first tissue type may be blood leakage, microcalcifications, and / or neovascularization.

[0103] Each grid of points can be represented as a point density, where some of the points on the grid of points may have the same density value, all of the points may have the same density value, or each point may have a unique density value.

[0104] The first tissue type may be determined by the system shown in FIG. 4 above, the method shown in FIG. 5 above, the system shown in FIG. 6 above, or any combination thereof.

[0105] The method may include determining 930 a second tissue type within the region of interest based on the radiological image of the patient, the second tissue type being a localized region within the region of interest, and at least some grid points of the first tissue type being coincident with grid points of the second tissue type. The second tissue type may be any tissue type that can be represented as a localized region. The second tissue type may be LRNC, CALC, and / or IPH.

[0106] The second tissue type may be determined by the system shown in FIG. 4 above, the method shown in FIG. 5 above, the system shown in FIG. 6 above, or any combination thereof.

[0107] FIG. 10 illustrates a method 100 for determining and displaying mixed tissue types of microcalcification screens and dense calcification regions using radiological images of multi-energy spectral CT images, according to some embodiments of the present invention.

[0108] The method includes receiving a multi-energy spectral CT image (step 1010) (eg, by the system shown in FIG. 4 above).

[0109] The method may include performing 1020 multi-energy photon-counting K-edge differential imaging. In some embodiments, for K-edge resolved imaging in a multi-energy system with a photon-counting detector (PCD), the energy bin has a significant impact on the intensity of the extracted K-edge signal, providing optimized energy bins that have the potential to improve classification between microcalcifications and focal / dense calcifications.

[0110] The method may include performing 1030 denoising of the spectral image using a regularization model. In some embodiments, the linear attenuation coefficient map is decomposed into basis materials that are separable in the spectral and spatial domains. The nonlinearity can be translated into the reconstruction of the mass density map. Reducing the dimensionality of the optimization variables and / or using a minimization scheme that solves the reconstruction with a weighted nuclear norm and total variation regularization can reduce noise and provide more spectral information.

[0111] The method may include, for example, refining (eg, removing) calcium by subtracting A from B (step 1040), effectively improving the signal-to-noise ratio.

[0112] The method may include segmenting the improved calcium (step 1050), which results in localized regions of high density calcification and microcalcification screens (eg, grid overlays).

[0113] In some embodiments, principal component analysis (PCA) for feature extraction is used together with spectral imaging to extract small HU differences of soft tissues present in multi-energy images. Soft tissues can be extracted using, for example, adaptive region growing and K-means clustering techniques. Using a region growing algorithm, regions with the same properties as predefined properties can be isolated, giving good segmentation results for original images with sharp edges. In some embodiments, the steps of segmentation may be 1) applying morphological reconstruction for smoothing flat regions of the image and / or preserving edges, 2) using multi-scale morphological gradients to avoid edge fattening and / or merging, 3) using top / bottom hat transformation for contrast enhancement, 4) modifying the morphological gradients of the image by providing local minima at both intrinsic and extrinsic marker locations, and 5) using weighted functions to combine the top / bottom hat transformation algorithm with the marker algorithm to obtain a new algorithm. In this way, over-segmentation from traditional watersheds can be prevented.

[0114]

[0041] Figure 11 is a diagram illustrating an example of the method of Figure 10, according to some embodiments of the present invention. Diagram 1110 illustrates a received multi-energy spectral CT image (e.g., step 1010 shown in Figure 10 above).

[0115] Diagram 1130 shows the output of performing multi-energy photon-counting K-edge subtraction imaging in a CT image (e.g., step 1020 shown in FIG. 10 above). Diagram 1120 shows the output of performing spectral image denoising using a regularization model in a CT image (e.g., step 1030 shown in FIG. 10 above). Diagram 1140 shows the output of removing calcium (e.g., step 1040 shown in FIG. 10 above). Diagrams 1150 and 1160 show segmenting the removed calcium into dense calcifications 1160 and microcalcifications 1150 (e.g., step 1050 shown in FIG. 10 above).

[0116] For example, and not to limit the scope of embodiments of the invention, discussions utilizing terms such as "processing," "computing," "calculating," "determining," "establishing," "analyzing," "collating," and the like, may refer to operations and / or processes of a computer, computing platform, computing system, or other electronic computing device that manipulates and / or transforms data represented as physical (e.g., electronic) quantities in the computer's registers and / or memory into other data that is similarly represented as physical quantities in the computer's registers and / or memory, or other non-transitory information storage medium capable of storing instructions for performing operations and / or processes.

[0117] Embodiments of the present invention are not limited thereto, and the terms "plurality" and "multiple" as used herein may include, for example, "multiple" or "two or more". The terms "plurality" or "multiple" may be used throughout this specification to describe two or more components, devices, elements, units, parameters, etc. A set term as used herein may include one or more items. Unless expressly stated, the method embodiments described herein are not limited to a particular order or sequence. Furthermore, some of the described method embodiments or elements thereof may occur or be performed simultaneously, at the same time, together.

[0118] The computer program may be written in any form of programming language, including compiled or interpreted languages, and may be deployed in any form including a stand-alone program, or as subroutines, components, and / or other units suitable for use in a computing environment. The computer program may be deployed to run on one computer or on multiple computers at one site.

[0119] The method steps may be performed by one or more programmable processors executing a computer program to perform the functions of the invention by manipulating input data to generate output. The method steps may be performed by an apparatus or implemented as special purpose logic circuitry. The circuitry may be, for example, an FPGA (field programmable gate array) and / or an ASIC (application specific integrated circuit). Modules, subroutines, and software agents may refer to portions of a computer program, processor, special circuitry, software, and / or hardware that implements the functionality.

[0120] Processors suitable for the execution of a computer program include, by way of example, both general purpose and special purpose microprocessors, as well as any one or more processors of any kind of digital computer. Typically, a processor receives instructions and data from a read-only memory or a random access memory, or both. The essential components of a computer are a processor, which executes instructions, and one or more memory devices for storing instructions and data. Typically, a computer is operatively coupled to receive data from, or to transmit data to, one or more mass storage devices (e.g., magnetic, magneto-optical, or optical disks) that store the data.

[0121] Data transmission and instructions can also take place via a communications network. Suitable information carriers for embodying computer program instructions and data include, by way of example, all forms of non-volatile memory, including semiconductor memory devices. The information carrier may be, for example, an EPROM, EEPROM, flash memory device, magnetic disk, internal hard disk, removable disk, magneto-optical disk, CD-ROM and / or DVD-ROM disk. The processor and the memory may be supplemented by and / or incorporated in dedicated logic circuitry.

[0122] To provide for user interaction, the techniques described above can be implemented in a computer having a display device, a transmission device, and / or a computing device. The display device may be, for example, a cathode ray tube (CRT) and / or a liquid crystal display (LCD). The user interaction may be, for example, a display of information to the user, a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer (e.g., interact with user interface elements), and the like. Other types of devices may also be used to provide for user interaction. The other device may be, for example, feedback provided to the user in any form of sensory feedback (e.g., visual feedback, auditory feedback, or haptic feedback). Input from the user may be received in any form including, for example, acoustic input, speech input, and / or haptic input.

[0123] Computing devices may include, for example, computers, computers with browser devices, telephones, IP telephones, mobile devices (e.g., mobile phones, personal digital assistant (PDA) devices, laptop computers, email devices), and / or other communication devices. Computing devices may be, for example, one or more computer servers. A computer server may be, for example, part of a server farm. Browser devices include, for example, computers (e.g., desktop computers, laptop computers, tablets) with a World Wide Web browser (e.g., Microsoft® Internet Explorer® available from Microsoft Corporation, Chrome available from Google, Mozilla® Firefox available from Mozilla Corporation, Safari available from Apple). Mobile computing devices include, for example, personal digital assistants (PDAs).

[0124] Websites and / or web pages may be provided, for example, over a network (e.g., the Internet) using a web server, which may be, for example, a computer with a server module (e.g., Microsoft® Internet Information Services available from Microsoft Corporation, Apache Web Server available from the Apache Software Foundation, Apache Tomcat Web Server available from the Apache Software Foundation).

[0125] The storage module may be, for example, a random access memory (RAM) module, a read only memory (ROM) module, a computer hard drive, a memory card (e.g., a universal serial bus (USB) flash drive, a secure digital (SD) flash card), a floppy disk, and / or any other data storage device. Information stored in the storage module may be maintained, for example, in a database (e.g., a relational database system, a flat database system) and / or any other logical information storage mechanism.

[0126] The above-described techniques may be implemented in a distributed computing system including a back-end component. The back-end component may be, for example, a data server, a middleware component, and / or an application server. The above-described techniques may be implemented in a distributed computing system including a front-end component. The front-end component may be, for example, a client computer having a graphical user interface, a web browser through which a user can interact with the implementation, and / or other graphical user interface for a transmitting device. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), the Internet, a wired network, and / or a wireless network.

[0127] The system may include clients and servers. Clients and servers are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

[0128] The above-mentioned networks may be implemented as packet-based networks, circuit-based networks, and / or combinations of packet-based and circuit-based networks. Packet-based networks may include, for example, the Internet, carrier Internet Protocol (IP) networks (e.g., local area networks (LANs), wide area networks (WANs), campus area networks (CANs), metropolitan area networks (MANs), home area networks (HANs), private IP networks, IP private branch exchanges (IPBXs), wireless networks (e.g., radio access networks (RANs), 802.11 networks, 802.16 networks, general packet radio service (GPRS) networks, high performance wireless LANs), and / or other packet-based networks. Circuit-based networks may include, for example, the public switched telephone network (PSTN), private branch exchanges (PBXs), wireless networks (e.g., RANs, Bluetooth, code division multiple access (CDMA) networks, time division multiple access (TDMA) networks, Global System for Mobile Communications (GSM) networks), and / or other circuit-based networks.

[0129] Some embodiments of the present invention may be embodied in the form of a system, a method, or a computer program product. Likewise, some embodiments may be embodied as a combination of hardware, software, or both. Some embodiments may be embodied as a computer program product stored in the form of computer-readable program code on one or more non-transitory computer-readable media. Such non-transitory computer-readable media may include instructions that, when executed, cause a processor to perform method steps according to the embodiments. In some embodiments, the instructions stored on the computer-readable media may be in the form of an installed application and in the form of an installation package.

[0130] Such instructions may be loaded and executed, for example, by one or more processors. For example, the computer-readable medium may be a non-transitory computer-readable storage medium. The non-transitory computer-readable storage medium may be, for example, an electronic, optical, magnetic, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof.

[0131] The computer program code may be written in any suitable programming language and may be executed by a single computer system or by multiple computer systems.

[0132] Those skilled in the art will appreciate that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics of the present invention. The foregoing embodiments are therefore to be considered in all respects as illustrative and not limiting of the invention described herein. The scope of the present invention is therefore indicated by the appended claims, rather than the foregoing description, and all changes that come within the meaning and range of equivalency of the claims are intended to be embraced therein.

[0133] In the above detailed description, many specific details are set forth to provide an understanding of the present invention. However, it will be understood by those skilled in the art that the present invention may be practiced without these specific details. In addition, detailed descriptions of well-known methods, procedures, components, modules, units and / or circuits are omitted so as not to obscure the present invention. Some features or elements described with respect to one embodiment may be combined with features or elements described with respect to other embodiments.

Claims

1. 1. A computerized method for improving soft tissue analysis, comprising: acquiring, by a computing device, a plurality of radiological images of the patient, each of the plurality of radiological images being acquired using a different excitation; selecting, by the computing device, a process from a plurality of processes for analyzing a plurality of excitations based on an expected soft tissue type; segmenting, by the computing device, the plurality of radiological images processed by the one process to represent the soft tissue; determining, by the computing device, a first tissue type within a region of interest based on the plurality of radiological images of the patient, the first tissue type being represented by a grid of points across the region of interest; determining, by the computing device, a second tissue type within the region of interest that is different from the first tissue type based on the plurality of radiological images of the patient, the second tissue type being a localized region within the region of interest, and at least some grid points of the first tissue type being coincident with grid points of the second tissue type; The computerized method includes:

2. 2. The computerized method of claim 1, wherein the multiple radiological images are computed tomography (CT) images and the different excitations are different x-ray energies.

3. The computerized method of claim 1 , wherein the multiple radiological images are magnetic resonance (MR) images and the different excitations are different radio frequency pulses.

4. The computerized method of claim 1 , wherein the multiple radiological images are ultrasound images and the different excitations are different frequencies.

5. The computerized method of claim 1 , wherein the plurality of processes comprises a digital subtraction process, a digital addition process, a multivariate statistical process, or an excitation selection process.

6. The computerized method of claim 5 , wherein the digital subtraction process comprises subtracting a first subset of the plurality of radiographic images from one or more of the plurality of radiographic images that are not in the subset.

7. The computerized method of claim 5 , wherein the digital summing process comprises averaging the multiple received radiological images.

8. The multivariate statistical processing includes: combining the plurality of radiographic images; and Removing inter-class dependencies through multivariate statistical approaches; 6. The computerized method of claim 5, comprising:

9. The plurality of radiation images are CT images, and each of the plurality of CT images includes directing a first x-ray attenuation by a first x-ray source onto an energy integrating detector sized to generate an image of a region of the patient; directing second x-ray attenuation by a second x-ray source to a photon-counting detector that produces an image of a specific tissue target within the predetermined region; by generating, by a processor, a final CT image based on the image of the predetermined area of ​​the patient and the image of the particular tissue target within the predetermined area.

2. The computerized method of claim 1.

10. The computerized method of claim 5 , wherein the excitation selection process includes selecting a particular radiographic image from the plurality of radiographic images based on tissue type.

11. 1. A computerized method for determining and displaying mixed tissue types, comprising: receiving, by a computing device, a radiological image of a patient; determining, by the computing device, a first tissue type within a region of interest based on the radiological image of the patient, the first tissue type being represented by a grid of points across the region of interest; determining, by the computing device, a second tissue type within the region of interest that is different from the first tissue type based on the radiological image of the patient, the second tissue type being a localized region within the region of interest, and at least some grid points of the first tissue type being coincident with grid points of the second tissue type; The computerized method includes:

12. 12. The computerized method of claim 11, wherein the radiological image is a computed tomography (CT) image, a magnetic resonance (MR) image, or an ultrasound image.

13. The computerized method of claim 11 , wherein the first tissue type and the second tissue type are overlaid.

14. The computerized method of claim 11 , wherein the grid of points has a varying density.

15. 12. The computerized method of claim 11, wherein the first tissue type is microcalcified tissue and the second tissue type is LNRC, dense calcification, or IPH.

16. The radiation image is a CT image, performing multi-energy photon counting K-edge subtraction imaging on the CT image by the computing device; performing, by the computing device, spectral image denoising on the CT image using a regularization model; improving, by the computing device, the signal-to-noise ratio of calcium on the K-edge subtracted and denoised CT image; segmenting, by the computing device, the improved calcium image to represent one or both of focal dense calcifications and diffuse microcalcifications; The computerized method of claim 11 further comprising:

Images