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, 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.
1. A computer-implemented method of facilitating assessment of risk of heart disease for a subject based on multi-dimensional information derived from non-invasive medical image analysis, the method comprising:
accessing, by a computer system, one or more medical images of a subject, wherein the medical image of the subject is obtained non-invasively;
analyzing, by the computer system, the one or more medical images of the subject to identify one or more portions of coronary arteries, aorta, and lungs of the subject; identifying, by the computer system, one or more regions of plaque in the identified one or more portions of the coronary arteries;
analyzing, by the computer system, the identified one or more regions of plaque in the coronary arteries to perform quantified phenotyping of coronary atherosclerosis comprising total plaque volume, low-density non-calcified plaque volume, non-calcified plaque volume, and calcified plaque volume in the one or more portions of coronary arteries; identifying, by the computer system, one or more regions of plaque in the identified one or more portions of the aorta;
analyzing, by the computer system, the identified one or more regions of plaque in the aorta to perform quantified phenotyping of aortic atherosclerosis comprising total plaque volume, low-density non-calcified plaque volume, non-calcified plaque volume, and calcified plaque volume in the one or more portions of the aorta; analyzing, by the computer system, the identified one or more portions of the lungs of the subject to determine presence or state of emphysema; and
causing, by the computer system, display of a graphical representation comprising results of the quantified phenotyping of coronary atherosclerosis, results of the quantified phenotyping of aortic atherosclerosis, and presence or state of emphysema to facilitate assessment of risk of heart disease for the subject based on multidimensional analysis of coronary atherosclerosis, aortic atherosclerosis, and emphysema,
wherein the computer system comprises a computer processor and an electronic storage medium.
2. The computer-implemented method of claim 1 , wherein the one or more medical images comprises a single medical image showing the one or more portions of the coronary arteries, aorta, and lungs appear on a single medical image.
3. The computer-implemented method of claim 1 , wherein the one or more medical images comprises a plurality of medical images.
4. The computer-implemented method of claim 1 , wherein one or more of the quantitative phenotyping of coronary atherosclerosis or the quantitative phenotyping of aortic atherosclerosis is performed based at least in part on analysis of density values of one or more pixels of the one or more medical images corresponding to plaque.
5. The computer-implemented method of claim 4 , wherein the density values comprise radiodensity values.
6. The computer-implemented method of claim 1 , wherein the presence or state of emphysema is determined based at least in part on analysis of density values of one or more pixels of the one or more medical images corresponding to the one or more portions of the lungs.
7. The computer-implemented method of claim 6 , wherein the density values comprise radiodensity values.
8. The computer-implemented method of any claim 7 , wherein the one or more regions of plaque are identified as low density non-calcified plaque when a radiodensity value is between about −189 and about 30 Hounsfield units.
9. The computer-implemented method of claim 7 , wherein the one or more regions of plaque are identified as non-calcified plaque when a radiodensity value is between about 30 and about 350 Hounsfield units.
10. The computer-implemented method of claim 7 , wherein the one or more regions of plaque are identified as calcified plaque when a radiodensity value is between about 351 and 2500 Hounsfield units.
11. The computer-implemented method of claim 1 , wherein the one or more medical images comprise a Computed Tomography (CT) image.
12. The computer-implemented method of claim 1 , wherein the one or more medical images are 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).
13. The computer-implemented method of claim 1 , further comprising generating, by the computer system, a multifactor assessment of risk of heart disease for the subject based at least in part on analysis of coronary atherosclerosis, aortic atherosclerosis, and emphysema.
14. The computer-implemented method of claim 1 , wherein the assessment of risk of heart disease is generated utilizing a machine learning algorithm.
15. The computer-implemented method of claim 1 , 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 heart disease for the subject.
16. The computer-implemented method of claim 15 , wherein the assessment of risk of heart disease is generated at least in part by: comparing results of the quantified phenotyping of coronary atherosclerosis to a set of reference values of quantified phenotyping of coronary atherosclerosis corresponding to different levels of risk of heart disease; comparing results of the quantified phenotyping of aortic atherosclerosis to a set of reference values of quantified phenotyping of aortic atherosclerosis corresponding to different levels of risk of heart disease; and comparing the presence or state of emphysema to a set of reference values of state of emphysema corresponding to different levels of risk of heart disease.
17. The computer-implemented method of claim 16 , wherein one or more of the set of reference values of quantified phenotyping of coronary atherosclerosis, set of reference values of quantified phenotyping of aortic atherosclerosis, or set of reference values of state of emphysema is derived from a reference population with varying levels of risk of heart disease.
18. The computer-implemented method of claim 1 , wherein the reference population is selected based on one or more of age, gender, or ethnicity of the subject.
19. The computer-implemented method of claim 1 , wherein the assessment of risk of heart disease is generated at least in part by: assessing risk of heart disease based on the results of quantified phenotyping of coronary atherosclerosis; assessing risk of heart disease based on the results of the quantified phenotyping of aortic atherosclerosis; assessing risk of heart disease based on the presence or state of emphysema; generating a weighted measure of the risk of heart disease assessed based on the results of quantified phenotyping of coronary atherosclerosis, the results of the quantified phenotyping of aortic atherosclerosis, and the presence or state of emphysema; and generating the multifactor assessment of heart disease based on the weighted measure.
20. A computer-implemented method of assessing risk of heart disease for a subject based on multi-dimensional information derived from non-invasive medical image analysis, the method comprising:
accessing, by a computer system, results of quantified phenotyping of coronary atherosclerosis of a subject at a first point in time, the quantified phenotyping of coronary atherosclerosis comprising total plaque volume, low-density non-calcified plaque volume, non-calcified plaque volume, and calcified plaque volume in one or more portions of coronary arteries of the subject;
accessing, by a computer system, results of quantified phenotyping of aortic atherosclerosis of the subject at the first point in time, the quantified phenotyping of aortic atherosclerosis comprising total plaque volume, low-density non-calcified plaque volume, non-calcified plaque volume, and calcified plaque volume in one or more portions of the aorta of the subject;
accessing, by the computer system, a medical image of the subject, wherein the medical image of the subject is obtained at a second point in time, the medical image comprising the one or more portions of coronary arteries and the one or more portions of the aorta of the subject;
performing, by the computer system, quantitative phenotyping of coronary atherosclerosis at the second point in time; performing, by the computer system, quantitative phenotyping of aortic atherosclerosis at the second point in time;
analyzing, by the computer system, progression of coronary atherosclerosis based at least in part on comparing the results of quantitative phenotyping of coronary atherosclerosis between the first point in time and the second point in time;
analyzing, by the computer system, progression of aortic atherosclerosis based at least in part on comparing the results of quantitative phenotyping of aortic atherosclerosis between the first point in time and the second point in time; and
assessing, by the computer system, a risk of heart disease for the subject based at least in part on the analysis of the progression of coronary atherosclerosis and the progression of aortic atherosclerosis,
wherein the computer system comprises a computer processor and an electronic storage medium.
21. The computer-implemented method of claim 20 , wherein the risk of heart disease for the subject is assessed to be high when the volume of non-calcified plaque in one or more of the coronary arteries or aorta is higher at the second point in time than at the first point in time.
22. The computer-implemented method of claim 20 , wherein the risk of heart disease for the subject is assessed to be high when the total plaque volume in one or more of the coronary arteries or aorta is higher at the second point in time than at the first point in time.
23. The computer-implemented method of any claim 20 , wherein the risk of heart disease for the subject is assessed to be high when the subject was non-responsive to a medication prescribed to the subject at the first point in time to stabilize atherosclerosis.
24. A computer-implemented method of assessing risk of heart disease for a subject based on multi-dimensional information derived from non-invasive medical image analysis, the method comprising:
accessing, by a computer system, results of quantified phenotyping of coronary atherosclerosis of a subject at a first point in time, the quantified phenotyping of coronary atherosclerosis comprising total plaque volume, low-density non-calcified plaque volume, non-calcified plaque volume, and calcified plaque volume in one or more portions of coronary arteries of the subject;
accessing, by a computer system, a state of emphysema of the subject analyzed at the first point in time;
accessing, by the computer system, a medical image of the subject, wherein the medical image of the subject is obtained at a second point in time, the medical image comprising the one or more portions of coronary arteries and lungs of the subject;
analyzing, by the computer system, the medical image to perform quantitative phenotyping of coronary atherosclerosis at the second point in time; analyzing, by the computer system, the medical image to determine a state of emphysema at the second point in time;
analyzing, by the computer system, progression of coronary atherosclerosis based at least in part on comparing the results of quantitative phenotyping of coronary atherosclerosis between the first point in time and the second point in time;
analyzing, by the computer system, progression of emphysema based at least in part on comparing the state of emphysema between the first point in time and the second point in time; and
assessing, by the computer system, a risk of heart disease for the subject based at least in part on the analysis of the progression of coronary atherosclerosis and the progression of emphysema,
wherein the computer system comprises a computer processor and an electronic storage medium.
25. The computer-implemented method of claim 24 , wherein the risk of heart disease for the subject is assessed to be high when the volume of non-calcified plaque in the one or more portions of coronary arteries is higher at the second point in time than at the first point in time.
26. The computer-implemented method of claim 24 , wherein the risk of heart disease for the subject is assessed to be high when the total plaque volume in the one or more portions of coronary arteries is higher at the second point in time than at the first point in time.
27. The computer-implemented method of claim 24 , wherein the risk of heart disease for the subject is assessed to be high when the subject was non-responsive to a medication prescribed to the subject at the first point in time to stabilize atherosclerosis.
28. A computer-implemented method of assessing risk of peripheral artery disease (PAD) for a subject based on multi-dimensional information derived from non-invasive medical image analysis, the method comprising:
accessing, by a computer system, one or more medical images of a subject, wherein the medical image of the subject is obtained non-invasively;
analyzing, by the computer system, the one or more medical images of the subject to identify one or more coronary arteries of the subject;
identifying, by the computer system, one or more regions of plaque in the identified one or more coronary arteries; analyzing, by the computer system, the identified one or more regions of plaque in the coronary arteries to perform quantified phenotyping of coronary atherosclerosis comprising total plaque volume, low-density non-calcified plaque volume, non-calcified plaque volume, and calcified plaque volume in the one or more coronary arteries;
comparing, by the computer system, results of the quantified phenotyping of coronary atherosclerosis to a set of reference values of quantified phenotyping of coronary atherosclerosis corresponding to different levels of risk of PAD; and
generating, by the computer system, an assessment of risk of PAD for the subject based at least in part on the comparison of the results of the quantified phenotyping of coronary atherosclerosis to the set of reference values, wherein the computer system comprises a computer processor and an electronic storage medium.
29. The computer-implemented method of claim 28 , further comprising: identifying, by the computer system, one or more portions of the aorta of the subject on the medical image; identifying, by the computer system, one or more regions of plaque in the identified one or more portions of the aorta; analyzing, by the computer system, the identified one or more regions of plaque in the aorta to perform quantified phenotyping of aortic atherosclerosis comprising total plaque volume, low-density non-calcified plaque volume, non-calcified plaque volume, and calcified plaque volume in the one or more portions of the aorta; and comparing, by the computer system, results of the quantified phenotyping of aortic atherosclerosis to a set of reference values of quantified phenotyping of aortic atherosclerosis corresponding to different levels of risk of PAD, wherein the assessment of risk of PAD for the subject is further generated based at least in part on the comparison of the results of the quantified phenotyping of aortic atherosclerosis to the set of reference values of quantified phenotyping of aortic atherosclerosis.
30. The computer-implemented method of claim 28 , further comprising: identifying, by the computer system, one or more portions of the lungs of the subject on the medical image; analyzing, by the computer system, the identified one or more portions of the lungs of the subject to determine a state of emphysema for the subject; and comparing, by the computer system, the determined state of emphysema for the subject to a set of reference values of states of emphysema corresponding to different levels of risk of PAD, wherein the assessment of risk of PAD for the subject is further generated based at least in part on the comparison of the results of the determined state of emphysema for the subject to the set of reference values of states of emphysema.
31. A computer-implemented method of assessing a health risk of a subject based on quantitative phenotyping derived from non-invasive medical image analysis, the method comprising:
accessing, by a computer system, one or more medical images of a subject, wherein the medical image of the subject is obtained non-invasively;
analyzing, by the computer system, the one or more medical images of the subject to identify one or more regions of interest, the one or more regions of interest comprising one or more portions of portions of coronary arteries, aorta, or lungs of the subject;
automatically analyzing, by the computer system, the one or more regions of interest to perform quantified phenotyping, the quantified phenotyping comprising one or more of coronary atherosclerosis, aortic atherosclerosis, or emphysema;
accessing, by the computer system, a first dataset comprising a plurality of predetermined diagnoses to determine presence of an applicable predetermined diagnosis corresponding to results of the quantified phenotyping;
accessing, by the computer system, when an applicable predetermined diagnosis corresponding to results of the quantified phenotyping is present, a second dataset comprising a plurality of predetermined medical conditions to determine presence of an applicable predetermined medical condition corresponding to the applicable predetermined diagnosis;
automatically determining, by the computer system, when an applicable predetermined medical condition corresponding to the applicable predetermined diagnosis is present, a third database comprising a plurality of health risk scores to determine an applicable health risk score for the subject corresponding to the applicable predetermined medical condition, wherein the applicable health risk score is derived from the quantified phenotyping of the one or more medical images; and
determining, by the computer system, one or more candidate treatments for the subject based on the applicable health risk score,
wherein the computer system comprises a computer processor and an electronic storage medium.
32. The computer-implemented method of claim 31 , further comprising causing, by the computer system, generation of a graphical representation of the determined one or more candidate treatments for the subject.
33. The computer-implemented method of claim 31 , wherein the quantitative phenotyping is performed based at least in part on analysis of density values of one or more pixels of the one or more medical images.
34. The computer-implemented method of claim 31 , wherein the density values comprise radiodensity values.
35. The computer-implemented method of claim 31 , wherein the one or more medical images are 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).