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 computer-implemented method for assessing risk of coronary artery disease of a subject based on image analysis of a non-invasive medical image of the subject and compound analysis of vascular parameters and plaque parameters derived from the image analysis, the method comprising:
accessing, by a computer system, a medical image of a coronary region of a subject, wherein the medical image of the coronary region of the subject was obtained non-invasively;
identifying, by the computer system, one or more coronary arteries and one or more regions of plaque in the medical image of the coronary region of the subject;
determining, by the computer system using at least in part a machine learning algorithm and the medical image, one or more vascular morphology parameters and one or more quantified plaque parameters of the one or more identified regions of plaque, wherein the one or more quantified plaque parameters comprises a ratio or function of volume of plaque and composition of plaque, wherein the composition of plaque is derived based on analysis of radiodensity values corresponding to the one or more identified regions of plaque, wherein the composition of plaque comprises one or more of non-calcified plaque or calcified plaque, wherein the machine learning algorithm comprises a convolutional neural network trained on a set of medical images in which regions of plaque have been identified;
generating, by the computer system, a graphical representation of a presence or risk of stenosis based at least in part on the one or more vascular morphology parameters and the ratio or function of volume of plaque;
determining, by the computer system, a presence or risk of ischemia based at least in part on the presence or risk of stenosis and the one or more quantified plaque parameters; and
generating, by the computer system, an assessment of risk of coronary artery disease (CAD), wherein the assessment of risk of CAD comprises a weighted measure of the one or more vascular morphology parameters, one or more quantified plaque parameters, presence or risk of stenosis, and presence or risk of ischemia,
wherein the computer system comprises a computer processor and an electronic storage medium.
2. The computer-implemented method of claim 1 , wherein the presence or risk of ischemia is determined on a vessel-by-vessel basis.
3. The computer-implemented method of claim 1 , wherein the graphical representation of the presence or risk of stenosis is generated on a vessel-by-vessel basis.
4. The computer-implemented method of claim 1 , wherein the medical image was obtained using an imaging technique comprising one or more of Computed Tomography (CT), x-ray, ultrasound, magnetic resonance (MR) imaging, nuclear medicine imaging, or near-field infrared spectroscopy (NIRS).
5. The computer-implemented method of claim 1 , wherein one or more of the one or more coronary arteries or the one or more regions of plaque are identified using an artificial intelligence or machine learning algorithm.
6. The computer-implemented method of claim 1 , further comprising generating, by the computer system, a proposed treatment for the subject using the generated weighted measure of the one or more vascular morphology parameters, one or more quantified plaque parameters, presence or risk of stenosis, and presence or risk of ischemia.
7. The computer-implemented method of claim 1 , further comprising analyzing, by the computer system, the generated weighted measure of the one or more vascular morphology parameters, one or more quantified plaque parameters, presence or risk of stenosis, and presence or risk of ischemia by comparison to one or more reference values derived from a population with varying risks of coronary artery disease.
8. The computer-implemented of claim 1 , wherein the one or more regions of plaque are identified by determining a vessel wall and lumen wall of the one or more coronary arteries and identifying a volume between the vessel wall and lumen wall as the one or more regions of plaque.
9. The computer-implemented of claim 1 , wherein the one or more vascular morphology parameters comprises a classification of arterial remodeling.
10. The computer-implemented of claim 1 , wherein the one or more coronary arteries are identified based at least in part on size of the one or more coronary arteries.
11. A computer-implemented method for assessing risk of coronary artery disease of a subject based on image analysis of a non-invasive medical image of the subject and compound analysis of vascular parameters and plaque parameters derived from the image analysis, the method comprising:
accessing, by a computer system, a medical image of a coronary region of a subject, wherein the medical image of the coronary region of the subject was obtained non-invasively;
identifying, by the computer system, one or more coronary arteries and one or more regions of plaque in the medical image of the coronary region of the subject;
determining, by the computer system, one or more vascular morphology parameters;
determining, by the computer system using at least in part a machine learning algorithm and the medical image, plaque composition of the one or more identified regions of plaque, wherein the plaque composition is derived based on analysis of radiodensity values corresponding to the one or more identified regions of plaque, wherein the plaque composition comprises one or more of low-density plaque or high-density plaque, wherein the machine learning algorithm comprises a convolutional neural network trained on a set of medical images in which regions of plaque have been identified;
determining, by the computer system, a presence or risk of stenosis based at least in part on the one or more vascular morphology parameters and a ratio or function of volume of plaque;
determining, by the computer system, one or more quantified plaque parameters of the one or more identified regions of plaque, the one or more quantified plaque parameters comprising one or more of volume of total plaque, volume of low-density plaque, or volume of high-density plaque;
determining, by the computer system, a presence or risk of ischemia based at least in part on the presence or risk of stenosis and the one or more quantified plaque parameters; and
generating, by the computer system, an assessment of risk of coronary artery disease (CAD), wherein the assessment of risk of CAD comprises a weighted measure of the one or more vascular morphology parameters, one or more quantified plaque parameters, the presence or risk of stenosis, and presence or risk of ischemia,
wherein the computer system comprises a computer processor and an electronic storage medium.
12. The computer-implemented method of claim 11 , wherein the presence or risk of ischemia is determined on a vessel-by-vessel basis.
13. The computer-implemented method of claim 11 , wherein the medical image was obtained using an imaging technique comprising one or more of Computed Tomography (CT), x-ray, ultrasound, magnetic resonance (MR) imaging, nuclear medicine imaging, or near-field infrared spectroscopy (NIRS).
14. The computer-implemented method of claim 11 , further comprising analyzing, by the computer system, the generated weighted measure of the one or more vascular morphology parameters, one or more quantified plaque parameters, and presence or risk of ischemia by comparison to one or more reference values derived from a population with varying risks of coronary artery disease.
15. The computer-implemented of claim 11 , wherein the one or more regions of plaque are identified by determining a vessel wall and lumen wall of the one or more coronary arteries and identifying a volume between the vessel wall and lumen wall as the one or more regions of plaque.
16. A system for assessing risk of coronary artery disease of a subject based on image analysis of a non-invasive medical image of the subject and compound analysis of vascular parameters and plaque parameters derived from the image analysis, 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 medical image of a coronary region of a subject, wherein the medical image of the coronary region of the subject was obtained non-invasively;
identify one or more coronary arteries and one or more regions of plaque in the medical image of the coronary region of the subject;
determine one or more vascular morphology parameters;
determine, using at least in part a machine learning algorithm and the medical image, plaque composition of the one or more identified regions of plaque, wherein the plaque composition is derived based on analysis of radiodensity values corresponding to the one or more identified regions of plaque, wherein the plaque composition comprises one or more of low-density plaque or high-density plaque, wherein the machine learning algorithm comprises a convolutional neural network trained on a set of medical images in which regions of plaque have been identified;
determine one or more quantified plaque parameters of the one or more identified regions of plaque, the one or more quantified plaque parameters comprising one or more of volume of total plaque, volume of low-density plaque, or volume of high-density plaque;
generate a graphical representation of presence or risk of stenosis based at least in part on the one or more vascular morphology parameters and a ratio of function of volume of plaque;
determine a presence or risk of ischemia based at least in part on the presence or risk of stenosis and the one or more quantified plaque parameters; and
generate an assessment of risk of coronary artery disease (CAD), wherein the assessment of risk of CAD comprises a weighted measure of the one or more vascular morphology parameters, one or more quantified plaque parameters, the presence or risk of ischemia, and presence or risk of stenosis.
17. The system of claim 16 , wherein the graphical representation of the presence or risk of stenosis is generated on a vessel-by-vessel basis.
18. The system of claim 16 , wherein one or more of the one or more coronary arteries or the one or more regions of plaque are identified using an artificial intelligence or machine learning algorithm.
19. The system of claim 16 , wherein the system is further caused to analyze the generated weighted measure of the one or more vascular morphology parameters, one or more quantified plaque parameters, and presence or risk of stenosis by comparison to one or more reference values derived from a population with varying risks of coronary artery disease.
20. The system of claim 16 , wherein the one or more regions of plaque are identified by determining a vessel wall and lumen wall of the one or more coronary arteries and identifying a volume between the vessel wall and lumen wall as the one or more regions of plaque.