Systems, devices, and methods for non-invasive image-based plaque analysis and risk determination

1 . A computer-implemented method of assessing microcirculatory resistance of coronary microvasculature based on non-invasive medical image analysis, the computer-implemented method comprising:

accessing, by a computer system, a first medical image of a subject, wherein the first medical image of the subject is obtained at a first point in time after injection of a contrast dye to the subject;

accessing, by the computer system, a second medical image of the subject, wherein the second medical image of the subject is obtained at a second point in time after injection of the contrast dye to the subject;

analyzing, by the computer system, the first medical image and the second medical image to identify a coronary artery;

mapping, by the computer system, myocardium subtended by the coronary artery in the first medical image and the second medical image;

analyzing, by the computer system, a difference in radiodensity between the myocardium subtended by the coronary artery in the first medical image and the second medical image, the difference in radiodensity arising from flow of the contrast dye through microvasculature of the myocardium subtended by the coronary artery;

determining, by the computer system, a generated measure of per-artery microcirculatory resistance of the coronary artery by relating the difference in radiodensity between the myocardium subtended by the coronary artery in the first medical image and the second medical image to a difference in time between the first point in time and the second point in time; and

determining, by the computer system, an assessment of microcirculatory resistance of the coronary artery based at least in part on comparing the generated measure of the per-artery microcirculatory resistance of the coronary artery to a plurality of reference measures of per-artery microcirculatory resistance, the plurality of reference measures of per-artery microcirculatory resistance derived from a plurality of other subjects, wherein the assessment of microcirculatory resistance of the coronary artery is configured to be utilized to determine a treatment for the subject, wherein the computer system comprises a computer processor and an electronic storage medium.

2 . The computer-implemented method of claim 1 , wherein the assessment of microcirculatory resistance of the coronary artery is determined utilizing a machine learning algorithm trained based at least in part on the plurality of reference measures of per-artery microcirculatory resistance.

3 . The computer-implemented method of claim 1 , wherein the generated measure of per-artery microcirculatory resistance comprises an index of microcirculatory resistance (IMR) value.

4 . The computer-implemented method of claim 3 , wherein the index of microcirculatory resistance comprises Pd×Tmn at maximal hyperemia,

wherein Pd comprises distal coronary pressure, and

wherein Tmn comprises mean transit time.

5 . The computer-implemented method of claim 1 , wherein the microvasculature comprises vessels with a diameter less than about 500 μm.

6 . The computer-implemented method of claim 1 , wherein the first medical image and the second medical image comprise a resolution that does not allow for image segmentation of plaque within the microvasculature.

7 . The computer-implemented method of claim 1 , further comprising:

identifying, by the computer system, one or more regions of plaque on one or more of the first medical image or the second medical image; and

generating, by the computer system, one or more quantified plaque parameters associated with the one or more regions of plaque, the one or more quantified plaque parameters comprising one or more of volume of low-density non-calcified plaque, volume of non-calcified plaque, or volume of calcified plaque,

wherein a combination of the one or more quantified plaque parameters and the assessment of microcirculatory resistance of the coronary artery is configured to be used to determine a risk of major adverse cardiovascular event (MACE) for the subject.

8 . The computer-implemented method of claim 7 , wherein low density non-calcified plaque comprises a region of plaque having a radiodensity value of from about −189 to about 30 Hounsfield units, wherein non-calcified plaque comprises a region of plaque having a radiodensity value of from about 31 to about 350 Hounsfield units, and wherein calcified plaque comprises a region of plaque having a radiodensity value of from about 351 to about 2500 Hounsfield units.

9 . The computer-implemented method of claim 1 , wherein the difference in radiodensity between the myocardium subtended by the coronary artery in the first medical image and the second medical image is due to washout of the contrast dye.

10 . The computer-implemented method of claim 1 , further comprising:

generating, by the computer system, a measure of ischemia for the coronary artery,

wherein a combination of the assessment of microcirculatory resistance of the coronary artery and the generated measure of ischemia for the coronary artery is configured to be used to determine a treatment for the subject.

11 . The computer-implemented method of claim 10 , wherein the measure of ischemia comprises fractional flow reserve.

12 . A system for image-based assessment of microcirculatory resistance, 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 first medical image of a subject, wherein the first medical image of the subject is obtained at a first point in time after injection of a contrast dye to the subject;

access a second medical image of a subject, wherein the second medical image of the subject is obtained at a second point in time after injection of the contrast dye to the subject;

analyze the first medical image and the second medical image to identify a coronary artery;

map myocardium subtended by the coronary artery in the first medical image and the second medical image;

analyze a difference in radiodensity between the myocardium subtended by the coronary artery in the first medical image and the second medical image, the difference in radiodensity arising from flow of the contrast dye through microvasculature of the myocardium subtended by the coronary artery;

determine a generated measure of per-artery microcirculatory resistance of the coronary artery by relating the difference in radiodensity between the myocardium subtended by the coronary artery in the first medical image and the second medical image to a difference in time between the first point in time and the second point in time; and

determine an assessment of microcirculatory resistance of the coronary artery based at least in part on comparing the generated measure of the per-artery microcirculatory resistance of the coronary artery to a plurality of reference measures of per-artery microcirculatory resistance, the plurality of reference measures of per-artery microcirculatory resistance derived from a plurality of other subjects, wherein the assessment of microcirculatory resistance of the coronary artery is configured to be utilized to determine a treatment for the subject.

13 . The system of claim 12 , wherein the assessment of microcirculatory resistance of the coronary artery is determined utilizing a machine learning algorithm trained based at least in part on the plurality of reference measures of per-artery microcirculatory resistance.

14 . The system of claim 12 , wherein determining the assessment of microcirculatory resistance comprises determining an IMR value for the coronary artery utilizing a machine learning algorithm trained based at least in part on the plurality of reference measures of per-artery microcirculatory resistance and known IMR values.

15 . The system of claim 12 , wherein the first medical image and the second medical image comprise a resolution that does not allow for image segmentation of plaque within the microvasculature.

16 . The system of claim 12 , wherein the microvasculature comprises one or more regions of plaque, and wherein the one or more regions of plaque comprise a size that is not recognizable on the first medical image and the second medical image.

17 . The system of claim 12 , wherein the one or more computer hardware processors are further configured to:

identify one or more regions of plaque on one or more of the first medical image or the second medical image; and

generate one or more quantified plaque parameters associated with the one or more regions of plaque, the one or more quantified plaque parameters comprising one or more of volume of low-density non-calcified plaque, volume of non-calcified plaque, or volume of calcified plaque,

wherein a combination of the one or more quantified plaque parameters and the assessment of microcirculatory resistance of the coronary artery is configured to be used to determine a risk of major adverse cardiovascular event (MACE) for the subject.

18 . The system of claim 12 , wherein the difference in radiodensity between the myocardium subtended by the coronary artery in the first medical image and the second medical image is due to washout of the contrast dye.

19 . The system of claim 12 , wherein the one or more computer hardware processors are further configured to:

generate a measure of ischemia for the coronary artery,

wherein a combination of the assessment of microcirculatory resistance of the coronary artery and the generated measure of ischemia for the coronary artery is configured to be used to determine a treatment for the subject.

20 . A non-transitory computer readable medium configured for image-based assessment of microcirculatory resistance, the non-transitory computer readable medium having program instructions for causing a hardware processor to perform a method of:

accessing a first medical image of a subject, wherein the first medical image of the subject is obtained at a first point in time after injection of a contrast dye to the subject;

accessing a second medical image of a subject, wherein the second medical image of the subject is obtained at a second point in time after injection of the contrast dye to the subject;

analyzing the first medical image and the second medical image to identify a coronary artery;

mapping myocardium subtended by the coronary artery in the first medical image and the second medical image;

analyzing a difference in radiodensity between the myocardium subtended by the coronary artery in the first medical image and the second medical image, the difference in radiodensity arising from flow of the contrast dye through microvasculature of the myocardium subtended by the coronary artery;

determining a generated measure of per-artery microcirculatory resistance of the coronary artery by relating the difference in radiodensity between the myocardium subtended by the coronary artery in the first medical image and the second medical image to a difference in time between the first point in time and the second point in time; and

determining an assessment of microcirculatory resistance of the coronary artery based at least in part on comparing the generated measure of the per-artery microcirculatory resistance of the coronary artery to a plurality of reference measures of per-artery microcirculatory resistance, the plurality of reference measures of per-artery microcirculatory resistance derived from a plurality of other subjects,

wherein the assessment of microcirculatory resistance of the coronary artery is configured to be utilized to determine a treatment for the subject.