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 a prescribed flow reserve of a patient based on a patient-specific maximum physical activity state to facilitate determination of a cardiovascular disease treatment for the patient, the method comprising:
accessing, by a computer system, data indicative of a lifestyle pattern of a patient, the data comprising one or more of heart rate, blood oxygen level, respiratory rate, or survey data;
determining, by the computer system, a maximum physical activity state for the patient that meets a predetermined confidence threshold, the maximum physical activity state for the patient determined based at least in part on the data indicative of the lifestyle pattern of the patient;
accessing, by the computer system, a medical image of the patient, wherein the medical image is obtained non-invasively;
analyzing, by the computer system, the medical image of the patient to identify a plurality of vessels, the plurality of vessels comprising a first vessel and a second vessel, wherein the first vessel is a different from than the second vessel;
identifying, by the computer system using at least in part a first machine learning algorithm, a first parameter for the first vessel comprising at least one of: a lumen wall of the first vessel, a vessel wall of the first vessel, or presence of plaque in the first vessel;
identifying, by the computer system using at least in part the first machine learning algorithm, a second parameter for the second vessel comprising at least one of: a lumen wall of the second vessel, a vessel wall of the second vessel, or a presence of plaque in the second vessel;
applying, a second machine learning algorithm to determine, by the computer system, a prescribed flow reserve in the first vessel at the maximum physical activity state based on the first parameter for the first vessel and the second parameter for the second vessel, wherein prescribed flow reserve comprises a ratio or percentage of coronary blood flow rate of the patient at the maximum physical activity state against a reference coronary blood flow rate at the maximum physical activity state
wherein the second machine learning algorithm is trained on a dataset to accept the plurality of variables as inputs and to output the prescribed flow reserve,
wherein a value of the second parameter of the second vessel impacts blood flow within the first vessel and the second vessel, and
wherein a value of the first parameter of the first vessel impacts blood flow within the first vessel and second vessel, wherein the first vessel and the second vessel comprise different portions of a network of vessels; and
predicting, by the computer system, an impact of a proposed treatment on the prescribed flow reserve of the patient at the maximum physical activity state, wherein the impact of the proposed treatment on the prescribed flow reserve of the patient is predicted based at least in part on a plurality of reference data derived from a plurality of subjects treated with the proposed treatment with varying prescribed flow reserves, wherein the predicted impact of the proposed treatment on the prescribed flow reserve of the patient at the maximum physical activity state is used to determine whether to treat the patient with the proposed treatment,
wherein the computer system comprises a computer processor and an electronic storage medium.
2 . The computer-implemented method of claim 1 , wherein the prescribed flow reserve of the patient at the maximum physical activity state is determined based at least in part on one or more parameters derived from analyzing a medical image of the patient, the medical image of the patient comprising a portion of coronary arteries, wherein the one or more parameters comprise one or more of 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, total plaque volume, number of mild stenosis, or low-density plaque volume.
3 . The computer-implemented method of claim 2 , wherein the prescribed flow reserve of the patient at the maximum physical activity state is determined using one or more of an artificial intelligence (AI) or machine learning (ML) algorithm.
4 . The computer-implemented method of claim 2 , wherein the one or more parameters further comprise one or more of percent atheroma volume of total plaque, percent atheroma volume of low-density non-calcified plaque, percent atheroma volume of non-calcified plaque, percent atheroma volume, low-density non-calcified plaque volume, percent atheroma volume of total calcified plaque, non-calcified plaque volume, total calcified plaque volume, percent atheroma volume of total non-calcified plaque, percent atheroma volume of low-density calcified plaque, percent atheroma volume of high-density calcified plaque, total non-calcified plaque volume, low-density calcified plaque volume, percent atheroma volume of medium-density calcified plaque, high-density calcified plaque volume, medium-density calcified plaque volume, number of high-risk plaque regions, number of segments with calcified plaque, number of segments with non-calcified plaque, plaque area, plaque burden, necrotic core percentage, necrotic core volume, fatty fibrous volume, fatty fibrous percentage, dense calcium percentage, low-density calcium percentage, medium-density calcified percentage, high-density calcified percentage, presence of two-feature positive plaques, number of two-feature positive plaques, segment length, severity of stenosis, minimum lumen diameter, maximum lumen diameter, mean lumen diameter, number of moderate stenosis, number of zero stenosis, number of severe stenosis, presence of high-risk anatomy, number of severe stenosis excluding CTO, vessel area, lumen area, diameter stenosis percentage, presence of ischemia, number of stents, reference lumen diameter before stenosis, perivascular fat attenuation, or reference lumen diameter after stenosis.
5 . The computer-implemented method of claim 4 , wherein low-density non-calcified plaque comprises a region of plaque with a radiodensity value less than or equal to about 30 Hounsfield units on a computed tomography (CT) image, non-calcified plaque comprises a region of plaque with a radiodensity value greater than about 30 Hounsfield units and less than or equal to about 350 Hounsfield units on a CT image, calcified plaque comprises a region of plaque with a radiodensity value greater than about 350 Hounsfield units on a CT image, low-density calcified plaque comprises a region of plaque with a radiodensity value greater than about 350 Hounsfield units and less than or equal to about 700 Hounsfield units on a CT image, medium-density calcified plaque comprises a region of plaque with a radiodensity value greater than about 700 Hounsfield units and less than or equal to about 1000 Hounsfield units on a CT image, and high-density calcified plaque comprises a region of plaque with a radiodensity value greater than about 1000 Hounsfield units on a CT image.
6 . The computer-implemented method of claim 2 , further comprising predicting, by the computer system, presence of pre-treatment ischemia in the patient at the determined maximum physical activity state when the patient is determined not to be treated with the proposed treatment, wherein presence of pre-treatment ischemia is predicted using an artificial intelligence (AI) or machine learning (ML) algorithm applied to the one or more parameters derived from analyzing the medical image of the patient, wherein prediction of presence of pre-treatment ischemia at the determined maximum physical activity state is suggestive of treating the patient with the proposed treatment.
7 . The computer-implemented method of claim 2 , further comprising predicting, by the computer system, presence of post-treatment ischemia in the patient at the determined maximum physical activity state when the patient is determined to be treated with the proposed treatment, wherein presence of post-treatment ischemia is predicted using an artificial intelligence (AI) or machine learning (ML) algorithm applied to the one or more parameters derived from analyzing a post-treatment medical image of the patient, the post-treatment medical image of the patient comprising a portion of coronary arteries, wherein prediction of presence of post-treatment ischemia at the determined maximum physical activity state is suggestive of treating the patient with additional treatment.
8 . The computer-implemented method of claim 2 , wherein the medical image is obtained using computed tomography (CT).
9 . The computer-implemented method of claim 2 , 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).
10 . The computer-implemented method of claim 1 , wherein the prescribed flow reserve of the patient at the maximum physical activity state is determined based at least in part on fractional flow reserve derived from computed tomography.
11 . The computer-implemented method of claim 1 , wherein the prescribed flow reserve of the patient at the maximum physical activity state is determined based at least in part on fractional flow reserve derived from computed tomography, computational fractional flow reserve, virtual fractional flow reserve, vessel fractional flow reserve, quantitative flow ratio, or invasive fractional flow reserve.
12 . The computer-implemented method of claim 1 , wherein the impact of the proposed treatment on the prescribed flow reserve of the patient at the maximum physical activity state prescribed flow reserve is determined using one or more of an artificial intelligence (AI) or machine learning (ML) algorithm.
13 . The computer-implemented method of claim 1 , further comprising generating, by the computer system, a graphical visualization of one or more of the determined maximum physical activity state for the patient, the prescribed flow reserve of the patient at the determined maximum physical activity state, or the predicted impact of the proposed treatment on the prescribed flow reserve of the patient at the maximum physical activity state.
14 . The computer-implemented method of claim 1 , wherein the survey data comprises data related to physical activity levels of the subject.
15 . The computer-implemented method of claim 1 , wherein one or more of heart rate, blood oxygen level, or respiratory rate of the patient is collected via a wearable device over a period of time.
16 . The computer-implemented method of claim 1 , wherein the maximum physical activity state comprises one or more of rest, walking, jogging, running, or sprinting.
17 . The computer-implemented method of claim 1 , wherein the maximum physical activity state is determined on a continuous scale.
18 . The computer-implemented method of claim 1 , wherein the proposed treatment comprises stenting.
19 . The computer-implemented method of claim 1 , wherein the proposed treatment comprises one or more of lifestyle change, exercise, diet, medication, stenting, or surgical procedure.
20 . The computer-implemented method of claim 1 , wherein the predetermined confidence threshold comprises about 90%.