Anatomical and functional assessment of CAD using machine learning

A system for assessing coronary artery disease, the system comprising:

• one or more processors:
• one or more memories storing instructions that when executed cause the one or more processors to:
• (a) receive a plurality of angiography images of a vessel inspection region for a subject, wherein the angiography images are captured over a sampling time period and wherein the vessel inspection region comprises one or more vessels;
• (b) apply the angiography images to a vessel segmentation machine learning model and generate, using the vessel segmentation machine learning model, two-dimensional (2D) segmented vessel images for the one or more vessels;
• (c) generate, from the 2D segmented vessel images, a one-dimensional (1D) segmented vessel tree geometric model of the one or more vessels;
• (d) apply the 1D segmented vessel tree geometric model to a fluid dynamics machine learning model to assimilate, using the fluid dynamics machine learning model, flow data over the sampling time period for the one or more vessels;
• (e) apply the 1D segmented vessel tree geometric model and the assimilated flow data to a graph-theory based reduced order model based on computational fluid dynamics model;
• and
• (f) determine a state of vessel occlusion.

A tangible, non-transitory computer-readable medium storing instructions, that, when executed by one or more processors of a computer system, cause the computer system to:

• (a) receive angiography image data of a vessel inspection region for a subject, wherein the angiography image data comprises angiography images captured over a sampling time period;
• (b) apply the angiography image data to a vessel segmentation machine learning model and generate, using the vessel segmentation machine learning model, two-dimensional (2D) segmented vessel images for the vessel inspection region;
• (c) generate from the 2D segmented vessel images a three-dimensional (3D) segmented vessel tree geometric model of vessels within the vessel inspection region;
• (d) apply the 3D segmented vessel tree geometric model to a fluid dynamics machine learning model to assimilate, using the fluid dynamics machine learning model, flow data over the sampling time period for one or more vessels within the vessel inspection region;
• (e) apply the 3D segmented vessel tree geometric model and the assimilated flow data to a 3D high-fidelity computational fluid dynamics model;
• and
• (f) determine a state of vessel occlusion for the one or more vessels within the vessel inspection region.

A tangible, non-transitory computer-readable medium storing instructions, that, when executed by one or more processors of a computer system, cause the computer system to:

• (a) receive a plurality of angiography images of a vessel inspection region for a subject, wherein the angiography images are captured over a sampling time period and wherein the vessel inspection region comprises one or more vessels;
• (b) apply the angiography images to a vessel segmentation machine learning model and generate, using the vessel segmentation machine learning model, two-dimensional (2D) segmented vessel images for the one or more vessels;
• (c) generate, from the 2D segmented vessel images, a one-dimensional (1D) segmented vessel tree geometric model of the one or more vessels;
• (d) apply the 1D segmented vessel tree geometric model to a fluid dynamics machine learning model to assimilate, using the fluid dynamics machine learning model, flow data over the sampling time period for the one or more vessels;
• (e) apply the 1D segmented vessel tree geometric model and the assimilated flow data to a graph-theory based reduced order model based on computational fluid dynamics model;
• and
• (f) determine a state of vessel occlusion.