Systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking
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, 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.
1. A system for tracking coronary artery disease (CAD) based on non-invasive medical image analysis of a medical image of a subject to facilitate determination of a state of plaque progression, regression, or stabilization, the system comprising:
one or more computer readable storage devices configured to store a plurality of computer executable instructions; and
one or more hardware computer processors in communication with the one or more computer readable storage devices and configured to execute the plurality of computer executable instructions in order to cause the system to:
access a first distribution of density values corresponding to one or more regions of plaque in one or more regions of one or more coronary arteries of a subject, wherein the first distribution of density values is generated from analyzing a first medical image of the subject comprising the one or more regions of the one or more coronary arteries, the first medical image of the subject obtained non-invasively at a first point in time;
access a second medical image of the subject, the second medical image of the subject obtained non-invasively at a second point in time, the second point in time being later than the first point in time, the second medical image of the subject comprising the one or more regions of the one or more coronary arteries of the subject;
identify the one or more regions of the one or more coronary arteries of the subject from the first medical image in the second medical image;
analyze the second medical image to generate a second distribution of density values corresponding to the one or more regions of plaque in the one or more regions of the one or more coronary arteries of the subject;
determine a change between the first distribution of density values corresponding to the one or more regions of plaque and the second distribution of density values corresponding to the one or more regions of plaque, wherein an increase in density values above a first predetermined threshold is indicative of plaque progression, wherein an increase in density values above a second predetermined threshold is indicative of plaque progression, and wherein an increase in density values above a third predetermined threshold is indicative of plaque stabilization; and
generate a graphical representation comprising the determined change between the first distribution of density values corresponding to the one or more regions of plaque and the second distribution of density values corresponding to the one or more regions of plaque, wherein the graphical representation is configured to facilitate determination of a state of plaque progression, regression, or stabilization based at least in part on the determined change in total plaque volume, non-calcified plaque volume, and calcified plaque volume.
2. The system of claim 1 , wherein the density values comprise radiodensity values.
3. The system of claim 1 , wherein the density values comprise material density values.
4. The system of claim 1 , wherein the graphical representation comprises one or more of a post-treatment increase in density values above the first predetermined threshold, a post-treatment increase in density values above the second predetermined threshold, and a post-treatment increase in density values above the third predetermined threshold.
5. The system of claim 1 , wherein the increase in density values above the first predetermined threshold, the increase in density values above the second predetermined threshold, and the increase in density values above the third predetermined threshold comprises a difference in absolute volume.
6. The system of claim 1 , wherein the increase in density values above the first predetermined threshold, the increase in density values above the second predetermined threshold, and the increase in density values above the third predetermined threshold comprises a percentage difference.
7. The system of claim 1 , wherein the graphical representation comprises simultaneous display of the increase in density values above the first predetermined threshold, the increase in density values above the second predetermined threshold, and the increase in density values above the third predetermined threshold.
8. The system of claim 1 , wherein the system is further caused to generate a patient-specific report based at least in part on the determined change between the first distribution of density values corresponding to the one or more regions of plaque and the second distribution of density values corresponding to the one or more regions of plaque.
9. The system of claim 1 , wherein the change between the first distribution of density values corresponding to the one or more regions of plaque and the second distribution of density values corresponding to the one or more regions of plaque is determined on one or more of a patient, vessel, segment, or lesion level.
10. The system of claim 1 , wherein stabilization of density values above the first predetermined threshold between the first point in time and the second point in time is indicative of plaque stabilization.
11. The system of claim 1 , wherein increase in density values above the third predetermined threshold and decrease in density values above the second predetermined threshold between the first point in time and the second point in time is indicative of plaque stabilization.
12. The system of claim 1 , wherein the graphical representation is configured to be used to propose a treatment for the subject.
13. The system of claim 1 , wherein the graphical representation is configured to be used to assess a previous treatment for the subject.
14. The system of claim 1 , wherein the system is further caused to:
access a first assessment of ischemia of the one or more regions of the one or more coronary arteries at the first point in time, wherein the first assessment of ischemia is generated based at least in part on the first medical image;
analyze the second medical image to generate an assessment of ischemia of the one or more regions of the one or more coronary arteries at the second point in time;
determine a change between the first assessment of ischemia and the second assessment of ischemia; and
generate a graphical representation of the determined change between the first assessment of ischemia and the second assessment of ischemia.
15. The system of claim 14 , wherein the assessment of ischemia at the first point in time is generated based at least in part on the first distribution of density values corresponding to one or more regions of plaque.
16. The system of claim 1 , wherein the system is further caused to:
access a first comparison of the first distribution of density values corresponding to the one or more regions of plaque to one or more reference distributions of density values;
generate a second comparison of the second distribution of density values corresponding to the one or more regions of plaque to the one or more reference distributions of density values;
determine a change between the first comparison and the second comparison; and
generate a graphical representation of the determined change between the first comparison and the second comparison.
17. The system of claim 1 , wherein the medical image is obtained using coronary computed tomography angiography (CCTA).
18. The system of claim 1 , wherein the medical image comprises a non-contrast CT image.
19. The system of claim 1 , wherein the medical image is obtained using an imaging modality comprising one or more of CT, x-ray, ultrasound, echocardiography, MR imaging, optical coherence tomography (OCT), nuclear medicine imaging, positron-emission tomography (PET), single photon emission computed tomography (SPECT), or near-field infrared spectroscopy (NIRS).
20. The system of claim 1 , wherein the second distribution of density values corresponding to the one or more regions of plaque is generated using a machine learning algorithm.
21. A computer-implemented method for tracking coronary artery disease (CAD) based on non-invasive medical image analysis of a medical image of a subject to facilitate determination of a state of plaque progression, regression, or stabilization, the method comprising:
accessing, by a computer system, a first distribution of density values corresponding to one or more regions of plaque in one or more regions of one or more coronary arteries of a subject, wherein the first distribution of density values is generated from analyzing a first medical image of the subject comprising the one or more regions of the one or more coronary arteries, the first medical image of the subject obtained non-invasively at a first point in time;
accessing, by the computer system, a second medical image of the subject, the second medical image of the subject obtained non-invasively at a second point in time, the second point in time being later than the first point in time, the second medical image of the subject comprising the one or more regions of the one or more coronary arteries of the subject;
identifying, by the computer system, the one or more regions of the one or more coronary arteries of the subject from the first medical image in the second medical image;
analyzing, by the computer system, the second medical image to generate a second distribution of density values corresponding to the one or more regions of plaque in the one or more regions of the one or more coronary arteries of the subject;
determining, by the computer system, a change between the first distribution of density values corresponding to the one or more regions of plaque and the second distribution of density values corresponding to the one or more regions of plaque, wherein an increase in density values above a first predetermined threshold is indicative of plaque progression, wherein an increase in density values above a second predetermined threshold is indicative of plaque progression, and wherein an increase in density values above a third predetermined threshold is indicative of plaque stabilization; and
generating, by the computer system, a graphical representation comprising the determined change between the first distribution of density values corresponding to the one or more regions of plaque and the second distribution of density values corresponding to the one or more regions of plaque, wherein the graphical representation is configured to facilitate determination of a state of plaque progression, regression, or stabilization based at least in part on the determined change in total plaque volume, non-calcified plaque volume, and calcified plaque volume,
wherein the computer system comprises a computer processor and an electronic storage medium.
22. The computer-implemented method of claim 21 , wherein the graphical representation comprises one or more of a post-treatment increase in density values above the first predetermined threshold, a post-treatment increase in density values above the second predetermined threshold, and a post-treatment increase in density values above the third predetermined threshold.
23. The computer-implemented method of claim 22 , wherein the increase in density values above the first predetermined threshold, the increase in density values above the second predetermined threshold, and the increase in density values above the third predetermined threshold comprises a difference in absolute volume.
24. The computer-implemented method of claim 22 , wherein the increase in density values above the first predetermined threshold, the increase in density values above the second predetermined threshold, and the increase in density values above the third predetermined threshold comprises a percentage difference.
25. The computer-implemented method of claim 21 , wherein the graphical representation comprises simultaneous display of a post-treatment increase in density values above the first predetermined threshold, a post-treatment increase in density values above the second predetermined threshold, and a post-treatment increase in density values above the third predetermined threshold.
26. The computer-implemented method of claim 21 , further comprising generating, by the computer system, a patient-specific report based at least in part on the determined change between the first distribution of density values corresponding to the one or more regions of plaque and the second distribution of density values corresponding to the one or more regions of plaque.
27. The computer-implemented method of claim 21 , wherein the change between the first distribution of density values corresponding to the one or more regions of plaque and the second distribution of density values corresponding to the one or more regions of plaque is determined on one or more of a patient, vessel, segment, or lesion level.
28. The computer-implemented method of claim 21 , wherein stabilization of density values above the first predetermined threshold between the first point in time and the second point in time is indicative of plaque stabilization, and wherein increase in density values above the third predetermined threshold and decrease in density values above the second predetermined threshold between the first point in time and the second point in time is indicative of plaque stabilization.
29. The computer-implemented method of claim 21 , further comprising:
accessing, by the computer system, a first assessment of ischemia of the one or more regions of the one or more coronary arteries at the first point in time, wherein the first assessment of ischemia is generated based at least in part on the first medical image;
analyzing, by the computer system, the second medical image to generate an assessment of ischemia of the one or more regions of the one or more coronary arteries at the second point in time;
determining, by the computer system, a change between the first assessment of ischemia and the second assessment of ischemia; and
generating, by the computer system, a graphical representation of the determined change between the first assessment of ischemia and the second assessment of ischemia.
30. The computer-implemented method of claim 21 , further comprising:
accessing, by the computer system, a first comparison of the first distribution of density values corresponding to the one or more regions of plaque to one or more reference distributions of density values;
generating, by the computer system, a second comparison of the second distribution of density values corresponding to the one or more regions of plaque to the one or more reference distributions of density values;
determining, by the computer system, a change between the first comparison and the second comparison; and
generating, by the computer system, a graphical representation of the determined change between the first comparison and the second comparison.