Systems, devices, and methods for non-invasive image-based plaque analysis and risk determination
Various embodiments described herein relate to systems, devices, and methods for non-invasive image-based plaque analysis and risk determination. In particular, in some embodiments, the systems, devices, and methods described herein are related to analysis of one or more regions of plaque, such as for example coronary plaque, using non-invasively obtained images that can be analyzed using computer vision or machine learning to identify, diagnose, characterize, treat and/or track coronary artery disease.
1. A computer-implemented method of determining presence of ischemia based at least in part on a plurality of variables derived from non-invasive medical image analysis, the method comprising:
accessing, by a computer system, a medical image of a subject, wherein the medical image of the subject is obtained non-invasively;
analyzing, by the computer system, the medical image of the subject to identify a plurality of vessels, the plurality of vessels comprising at least a first vessel;
identifying, by the computer system, one or more lesions in the first vessel;
identifying, by the computer system, one or more regions of plaque within the one or more lesions in the first vessel;
determining, by the computer system using at least in part a first machine learning algorithm, a plurality of variables associated with the one or more lesions in the first vessel and the one or more regions of plaque within the one or more lesions in the first vessel, wherein the plurality of variables comprise stenosis, total plaque volume, non-calcified plaque volume, calcified plaque volume, lesion length, remodeling index, plaque slice percentage, stenosis area percentage, presence of low-density plaque, stenosis diameter percentage, presence of positive remodeling, reference diameter after stenosis, reference diameter before stenosis, vessel length, lumen volume, number of chronic total occlusion (CTO), vessel volume, number of stenosis, and number of mild stenosis; and
applying, by the computer system, a second machine learning algorithm to determine a presence of ischemia in the first vessel based at least in part on the plurality of variables,
wherein the computer system comprises a computer processor and an electronic storage medium.
2. The computer-implemented method of claim 1 , further comprising generating, by the computer system, a graphical display comprising:
a visualization of the plurality of vessels including the first vessel,
an indication associated with the visualization of the first vessel indicating a likelihood of the presence of ischemia in the first vessel,
an indication of stenosis in the first vessel, and
an indication of atherosclerosis based at least in part on the total plaque volume, the non-calcified plaque volume, and the calcified plaque volume of the first vessel,
wherein the indication of the presence of ischemia, the indication of stenosis, and the indication of atherosclerosis are configured to aid a clinician in diagnosing coronary artery disease of the subject.
3. The computer-implemented method of claim 1 , wherein the total plaque volume, the non-calcified plaque volume, and the calcified plaque volume are determined based at least in part on analyzing density of one or more pixels corresponding to plaque in the medical image.
4. The computer-implemented method of claim 3 , wherein the density comprises material density.
5. The computer-implemented method of claim 3 , wherein the density comprises radiodensity.
6. The computer-implemented method of claim 5 , wherein low density non-calcified plaque corresponds to one or more pixels with a radiodensity value between about −189 and about 30 Hounsfield units.
7. The computer-implemented method of claim 5 , wherein non-calcified plaque corresponds to one or more pixels with a radiodensity value between about 31 and about 189 Hounsfield units.
8. The computer-implemented method of claim 5 , wherein non-calcified plaque corresponds to one or more pixels with a radiodensity value between about 190 and about 350 Hounsfield units.
9. The computer-implemented method of claim 5 , wherein calcified plaque corresponds to one or more pixels with a radiodensity value between about 351 and 2500 Hounsfield units.
10. The computer-implemented method of claim 1 , wherein the medical image comprises a Computed Tomography (CT) image.
11. The computer-implemented method of claim 1 , wherein the medical image is obtained using an imaging technique 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).
12. The computer-implemented method of claim 1 , wherein the plurality of vessels comprises one or more coronary arteries.
13. The computer-implemented method of claim 12 , wherein the one or more coronary arteries comprise one or more of left main (LM), ramus intermedius (RI), left anterior descending (LAD), diagonal 1 (D1), diagonal 2 (D2), left circumflex (Cx), obtuse marginal 1 (OM1), obtuse marginal 2 (OM2), left posterior descending artery (L-PDA), left posterolateral branch (L-PLB), right coronary artery (RCA), right posterior descending artery (R-PDA), or right posterolateral branch (R-PLB).
14. The computer-implemented method of claim 1 , wherein at least one of the first machine learning algorithm or the second machine learning algorithm is trained based at least in part on a dataset comprising the plurality of variables and presence of ischemia derived using invasive fractional flow reserve.
15. The computer-implemented method of claim 1 , wherein at least one of the first machine learning algorithm or the second machine learning algorithm is trained based at least in part on a dataset comprising the plurality of variables and presence of ischemia derived using one or more of CT fractional flow reserve, computational fractional flow reserve, virtual fractional flow reserve, vessel fractional flow reserve, or quantitative flow ratio.
16. The computer-implemented method of claim 1 , further comprising generating, by the computer system, an assessment of risk of coronary artery disease (CAD) or major adverse cardiovascular event (MACE) of the subject based at least in part on the determination of presence of ischemia in the first vessel.
17. The computer-implemented method of claim 16 , further comprising generating, by the computer system, a recommended treatment for the subject based at least in part on the generated assessment of risk of CAD or MACE.
18. A system for determining presence of ischemia based at least in part on a plurality of variables derived from non-invasive medical image analysis, the system comprising:
a non-transitory computer storage medium configured to at least store computer-executable instructions; and
one or more computer hardware processors in communication with the non-transitory computer storage medium, the one or more computer hardware processors configured to execute the computer-executable instructions to at least:
access a medical image of a subject, wherein the medical image of the subject is obtained non-invasively;
analyze the medical image of the subject to identify a plurality of vessels, the plurality of vessels comprising at least a first vessel;
identify one or more lesions in the first vessel;
identify one or more regions of plaque within the one or more lesions in the first vessel;
determine, at least in part, with a first machine learning algorithm, a plurality of variables associated with the one or more lesions in the first vessel and the one or more regions of plaque within the one or more lesions in the first vessel, wherein the plurality of variables comprise stenosis, total plaque volume, non-calcified plaque volume, calcified plaque volume, lesion length, remodeling index, plaque slice percentage, stenosis area percentage, presence of low-density plaque, stenosis diameter percentage, presence of positive remodeling, reference diameter after stenosis, reference diameter before stenosis, vessel length, lumen volume, number of chronic total occlusion (CTO), vessel volume, number of stenosis, and number of mild stenosis; and
apply a second machine learning algorithm to determine a presence of ischemia in the first vessel based at least in part on the plurality of variables.