Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking

Abstract

The disclosure herein relates to systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking. In some embodiments, the systems, devices, and methods described herein are configured to analyze non-invasive medical images of a subject to automatically and/or dynamically identify one or more features, such as plaque and vessels, and/or derive one or more quantified plaque parameters, such as radiodensity, radiodensity composition, volume, radiodensity heterogeneity, geometry, location, perform computational fluid dynamics analysis, facilitate assessment of risk of heart disease and coronary artery disease, enhance drug development, determine a CAD risk factor goal, provide atherosclerosis and vascular morphology characterization, and determine indication of myocardial risk, and/or the like. In some embodiments, the systems, devices, and methods described herein are further configured to generate one or more assessments of plaque-based diseases from raw medical images using one or more of the identified features and/or quantified parameters.

What is claimed is: 
     
         1 . A computer-implemented method of identifying a presence and/or degree of ischemia via an algorithm-based medical imaging analysis, comprising:
 performing a computational fluid dynamics (CFD) analysis of a portion of the coronary vasculature of a patient using imaging data of the portion of the coronary vasculature of the patient;   performing a comprehensive atherosclerosis and vascular morphology characterization of the portion of the coronary vasculature of the patient using coronary computed tomographic angiography (CCTA) of the portion of the coronary vasculature of the patient; and   applying an algorithm that integrates the CFD analysis and the atherosclerosis and vascular morphology characterization to provide an indication of the presence and/or degree of ischemia within the portion of the coronary vasculature of the patient on a pixel-by-pixel basis, the algorithm providing an indication of the presence and/or degree of ischemia for a given pixel based upon an analysis of the given pixel, the surrounding pixels, and a vessel of the portion of the coronary vasculature of the patient with which the pixel is associated.   
     
     
         2 . The computer-implemented method of  claim 1 , further comprising applying an algorithm that integrates the CFD analysis and the atherosclerosis and vascular morphology characterization to provide an indication of the presence and/or degree of ischemia within the portion of the coronary vasculature of the patient on a lesion-by-lesion basis, a stenosis-by-stenosis basis, a segment-by-segment basis, or a vessel-by-vessel basis. 
     
     
         3 . The computer-implemented method of  claim 1 , wherein performing a computational fluid dynamics (CFD) analysis comprises generating a model of the portion of the coronary vasculature of the patient based at least in part on coronary computed tomographic angiography (CCTA) of the portion of the coronary vasculature of the patient. 
     
     
         4 . The computer-implemented method of  claim 1 , wherein performing a computational fluid dynamics (CFD) analysis comprises generating a model of the portion of the coronary vasculature of the patient based at least in part on the atherosclerosis and vascular morphology characterization of the portion of the coronary vasculature of the patient. 
     
     
         5 . The computer-implemented method of  claim 1 , wherein performing a computational fluid dynamics (CFD) analysis comprises computing a fractional flow reserve model of the portion of the coronary vasculature of the patient. 
     
     
         6 . The computer-implemented method of  claim 1 , wherein performing a comprehensive atherosclerosis and vascular morphology characterization of the portion of the coronary vasculature of the patient comprises determining one or more vascular morphology parameters and a set of quantified plaque parameters. 
     
     
         7 . The computer-implemented method of  claim 1 , wherein performing a computational fluid dynamics (CFD) analysis of a portion of the coronary vasculature of a patient comprises (i) generating a CFD-based indication of the presence and/or degree of ischemia within the portion of the coronary vasculature of the patient on a pixel-by-pixel basis. 
     
     
         8 . The computer-implemented method of  claim 1 , wherein applying the algorithm that integrates the CFD analysis and the atherosclerosis and vascular morphology characterization to provide an indication of the presence and/or degree of ischemia within the portion of the coronary vasculature of the patient on a pixel-by-pixel basis comprises providing an indication of agreement with the CFD-based indication of the presence and/or degree of ischemia within the portion of the coronary vasculature of the patient on a pixel-by-pixel basis. 
     
     
         9 . The computer-implemented method of  claim 1 , wherein applying the algorithm that integrates the CFD analysis and the atherosclerosis and vascular morphology characterization to provide an indication of the presence and/or degree of ischemia within the portion of the coronary vasculature of the patient on a pixel-by-pixel basis comprises analyzing variation in coronary volume, area, and/or diameter over the entirety of a cardiac cycle. 
     
     
         10 . The computer-implemented method of  claim 1 , wherein analyzing variation in coronary volume, area, and/or diameter over the entirety of a cardiac cycle comprises analyzing an effect of identified atherosclerotic plaque within a wall of an artery on the deformation of the artery. 
     
     
         11 . A computer-implemented method for non-invasively estimating blood flow characteristics to assess the severity of plaque and/or stenotic lesions using blood distribution predictions and measurements, the method comprising:
 generating and outputting an initial indicia of a severity of the plaque or stenotic lesion using one or more calculated blood flow characteristics, where generating and outputting the initial indicia of a severity of the plaque or stenotic lesion comprises:
 receiving one or more patient-specific images and/or anatomical characteristics of at least a portion of a patient's vasculature; 
 receiving images reflecting a measured distribution of blood delivered through the patient's vasculature, and projecting one or more values of the measured distribution of the blood to one or more points of a patient-specific anatomic model of the patient's vasculature generated using the received patient-specific images and/or the received anatomical thereby creating a patient-specific measured model indicative of the measured distribution; 
 defining one or more physiological and boundary conditions of a blood flow to non-invasively simulate a distribution of the blood through the patient-specific anatomic model of the patient's vasculature; 
 simulating, using a processor, the distribution of the blood through the one or more points of the patient-specific anatomic model using the defined one or more physiological and boundary conditions and the received patient-specific images and/or anatomical characteristics, thereby creating a patient-specific simulated model indicative of the simulated distribution; 
 comparing, using a processor, the patient-specific measured model, and the patient-specific simulated model to determine whether a similarity condition is satisfied, and updating the defined physiological and boundary conditions and re-simulating the distribution of the blood through the one or more points of the patient-specific anatomic model until the similarity condition is satisfied; 
 calculating, using a processor, one or more blood flow characteristics of blood flow through the patient-specific anatomic model using the updated physiological and boundary conditions; and 
 generating and outputting the initial indicia of a severity of the plaque or stenotic lesion using the one or more blood flow characteristics of blood flow that were calculated using the updated physiological and boundary conditions; 
   performing a comprehensive atherosclerosis and vascular morphology characterization of the portion of the patient's vasculature using coronary computed tomographic angiography (CCTA) of the portion of the patient's vasculature; and   applying an algorithm that integrates the initial indicia of a severity of the plaque or stenotic lesion and the atherosclerosis and vascular morphology characterization to provide an indication of the presence and/or degree of ischemia within the portion of the patient's vasculature on a pixel-by-pixel basis.   
     
     
         12 . The computer-implemented method of  claim 11 , wherein
 said receiving images comprises receiving images reflecting a measured distribution of blood a contrast agent delivered through the patient's vasculature;   said projecting one or more values comprises projecting one or more contrast values of the measured distribution of a contrast agent to one or more points of a patient-specific anatomic model of the patient's vasculature generated using the received patient-specific images and/or the received anatomical thereby creating a patient-specific measured model indicative of the measured distribution;   said defining one or more physiological and boundary conditions of a blood flow to non-invasively simulate a distribution of the blood through the patient-specific anatomic model of the patient's vasculature comprises defining one or more physiological and boundary conditions of a blood flow to non-invasively simulate a distribution of a contrast agent through the patient-specific anatomic model of the patient's vasculature;   said simulating, using a processor, the distribution of the blood through the one or more points of the patient-specific anatomic model comprises simulating, using a processor, the distribution of the contrast agent through the one or more points of the patient-specific anatomic model using the defined one or more physiological and boundary conditions and the received patient-specific images and/or anatomical characteristics, thereby creating a patient-specific simulated model indicative of the simulated distribution; and   said updating the defined physiological and boundary conditions and re-simulating the distribution of the blood through the one or more points of the patient-specific anatomic model until the similarity condition is satisfied comprises updating the defined physiological and boundary conditions and re-simulating the distribution of the contrast agent through the one or more points of the patient-specific anatomic model until the similarity condition is satisfied.   
     
     
         13 . The computer-implemented method of  claim 11 , wherein the blood flow characteristics include one or more of, a blood flow velocity, a blood pressure, a heart rate, a fractional flow reserve (FFR) value, a coronary flow reserve (CFR) value, a shear stress, or an axial plaque stress. 
     
     
         14 . The computer-implemented method of  claim 11 , wherein receiving one or more patient-specific images includes receiving one or more images from coronary angiography, biplane angiography, 3D rotational angiography, computed tomography (CT) imaging, magnetic resonance (MR) imaging, ultrasound imaging, or a combination thereof. 
     
     
         15 . The computer-implemented method of  claim 11 , wherein the patient-specific anatomic model includes information related to the vasculature, including one or more of:
 a geometrical description of a vessel, including the length or diameter;   a branching pattern of a vessel;   one or more locations of any stenotic lesions, plaque, occlusions, or diseased segments; or   one or more characteristics of diseases on or within vessels, including material properties of stenotic lesions, plaque, occlusions, or diseased segments.   
     
     
         16 . The computer-implemented method of  claim 11 , wherein performing a comprehensive atherosclerosis and vascular morphology characterization of the portion of the patient's vasculature using coronary computed tomographic angiography (CCTA) of the portion of the patient's vasculature comprises:
 generating image information for the patient, the image information including image data of computed tomography (CT) scans along a vessel of the patient, and radiodensity values of coronary plaque and radiodensity values of perivascular tissue located adjacent to the coronary plaque; and   determining, using the image information of the patient, coronary plaque information of the patient, wherein determining the coronary plaque information comprises
 quantifying, using the image information, radiodensity values in a region of coronary plaque of the patient, 
 quantifying, using the image information, radiodensity values in a region of perivascular tissue adjacent to the region of coronary plaque of the patient, and 
 generating metrics of coronary plaque of the patient using the quantified radiodensity values in the region of coronary plaque and the quantified radiodensity values in the region of perivascular tissue adjacent to the region of coronary plaque. 
   
     
     
         17 . The computer-implemented method of  claim 16 , further comprising:
 accessing a database of coronary plaque information and characteristics of other people, the coronary plaque information in the database including metrics generated from radiodensity values of a region of coronary plaque in the other people and radiodensity values of perivascular tissue adjacent to the region of coronary plaque in the other people, and the characteristics of the other people including information at least of age, sex, race, diabetes, smoking, and prior coronary artery disease; and   characterizing the coronary plaque information of the patient by comparing the metrics of the coronary plaque information and characteristics of the patient to the metrics of the coronary plaque information of other people in the database having one or more of the same characteristics, wherein characterizing the coronary plaque information includes identifying the coronary plaque as a high risk plaque.   
     
     
         18 . The computer-implemented method of  claim 17 , wherein characterizing the coronary plaque comprises identifying the coronary plaque as a high risk plaque if it is likely to cause ischemia based on a comparison of the coronary plaque information and characteristics of the patient to the coronary plaque information and characteristics of the other people in the database. 
     
     
         19 . The computer-implemented method of  claim 17 , wherein characterizing the coronary plaque comprises identifying the coronary plaque as a high risk plaque if it is likely to rapidly progress based on a comparison of the coronary plaque information and characteristics of the patient to the coronary plaque information and characteristics of the other people in the database. 
     
     
         20 . The computer-implemented method of  claim 17 , wherein generating metrics using the quantified radiodensity values in the region of coronary plaque and the quantified radiodensity values in a region of perivascular tissue adjacent to the region of the patient comprises determining, along a line, a slope value of the radiodensity values of the coronary plaque and a slope value of the radiodensity values of the perivascular tissue adjacent to the coronary plaque.