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

Patent metadata

Field	Value
Publication number	US-12299885-B2
Application number	US-202318531500-A
Country	US
Kind code	B2
Filing date	Dec 6, 2023
Priority date	Mar 10, 2022
Publication date	May 13, 2025
Grant date	May 13, 2025

Abstract

Systems and methods of facilitating determination of risk of coronary artery disease (CAD) based at least in part on one or more measurements derived from non-invasive medical image analysis. The methods can include accessing a non-invasive generated medical image, identifying one or more arteries, identifying, regions of plaque within an artery, analyzing the regions of plaque to identify low density non-calcified plaque, non-calcified plaque, or calcified plaque based at least in part on density, determining a distance from identified regions of low density non-calcified plaque to one or more of a lumen wall or vessel wall, determining embeddedness of the regions of low density non-calcified plaque by one or more of non-calcified plaque or calcified plaque, determining a shape of the more regions of low density non-calcified plaque, and generating a display of the analysis to facilitate determination of one or more of a risk of CAD of the subject.

First claim

The invention claimed is:

1. A computer-implemented method of facilitating determination of risk of coronary artery disease (CAD) based at least in part on a shape of one or more regions of low density non-calcified plaque as determined by automated image analysis processing of a medical image, the method comprising:
accessing, by a computer system, a medical image of a subject, wherein the medical image of the subject is obtained non-invasively;
analyzing, by the computer system, the medical image of the subject to identify one or more vessels;
identifying, by the computer system, one or more regions of plaque within the one or more vessels;
analyzing, by the computer system, the identified one or more regions of plaque to identify one or more regions of low density non-calcified plaque based at least in part on density;
analyzing the one or more regions of low density non-calcified plaque, wherein the analysis of the one or more regions of low density non-calcified plaque comprises determining a shape of the one or more regions of low density non-calcified plaque, the shape of the one or more regions of low density non-calcified plaque comprising one or more of a crescent, round, lobular, or bean shape, wherein the shape of the one or more regions of low density non-calcified plaque is determined based at least in part by a machine learning algorithm, wherein the machine learning algorithm comprises a convolutional neural network trained on a set of medical images in which shapes of regions of plaque have been identified as one or more of a crescent, round, lobular, and bean shape, wherein the set of medical images comprise a plurality of two-dimensional slices of at least one three-dimensional image, wherein the convolutional neural network comprises a plurality of layers, each layer comprising a plurality of overlapping clusters of nodes such that each overlapping cluster of the plurality of overlapping clusters feeds data into multiple nodes of a subsequent layer of the plurality of layers; and
determining, by the computer system, a preliminary risk assessment of CAD of the subject based at least in part on the determined shape of the one or more regions of low density non-calcified plaque, wherein the preliminary risk assessment of CAD of the subject is configured to be used to facilitate determination of risk of coronary artery disease (CAD) and treatment of CAD for a patient,
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 vessels comprises one or more coronary or carotid arteries.

3. The computer-implemented method of claim 1 , wherein one or more axes of the one or more regions of low density non-calcified plaque comprises one or more of a major axis on a longitudinal plane, minor axis on a longitudinal plane, major axis on a latitudinal plane, or minor axis on a latitudinal plane.

4. The computer-implemented method of claim 3 , wherein the one or more axes are determined on a three-dimensional basis.

5. The computer-implemented method of claim 3 , wherein the one or more axes are determined based on one or more two-dimensional images.

6. The computer-implemented method of claim 3 , wherein the longitudinal plane is obtained by taking a two-dimensional slice parallel to a longitudinal axis of a straightened multiplanar view of the one or more vessels.

7. The computer-implemented method of claim 3 , wherein the longitudinal plane is obtained by taking a two-dimensional slice resulting in a longest major axis of the longitudinal plane.

8. The computer-implemented method of claim 1 , wherein the shape of the one or more regions of low density non-calcified plaque is determined as one or more of a crescent, round, lobular, or bean shape.

9. The computer-implemented method of claim 8 , wherein determination of a round or bean shape of the one or more regions of low density non-calcified plaque is indicative of an unstable plaque or high risk of CAD.

10. The computer-implemented method of claim 1 , wherein the analysis of the one or more regions of low density non-calcified plaque further comprises determining one or more lengths of one or more axes of the one or more regions of low density non-calcified plaque.

11. The computer-implemented method of claim 10 , wherein the shape of the one or more regions of low density non-calcified plaque is determined based at least in part on the one or more determined lengths of the one or more axes.

12. The computer-implemented method of claim 11 , wherein the shape of the one or more regions of low density non-calcified plaque is determined based at least in part on determining a standard deviation among the one or more determined lengths of the one or more axes.

13. The computer-implemented method of claim 10 , wherein the analysis of the one or more regions of low density non-calcified plaque further comprises:
determining a volume of the one or more regions of low density non-calcified plaque;
determining a volume of the one or more regions of plaque; and
determining a ratio of the volume of the one or more regions of low density noncalcified plaque to the volume of the one or more regions of plaque.

14. The computer-implemented method of claim 13 , wherein the volume of the one or more regions of low density non-calcified plaque is determined based on the one or more determined lengths of the one or more axes of the one or more regions of low density non-calcified plaque.

15. The computer-implemented method of claim 13 , wherein a determination of the volume of the one or more regions of low density non-calcified plaque above a predetermined threshold is indicative of unstable plaque or high risk of CAD.

16. The computer-implemented method of claim 13 , wherein a determination of the volume of the one or more regions of plaque above a predetermined threshold is indicative of unstable plaque or high risk of CAD.

17. The computer-implemented method of claim 13 , wherein a determination of the ratio of the volume of the one or more regions of low density non-calcified plaque to the volume of the one or more regions of plaque above a predetermined threshold is indicative of unstable plaque or high risk of CAD.

18. The computer-implemented method of claim 1 , wherein the density comprises absolute density.

19. The computer-implemented method of claim 1 , wherein the density comprises radiodensity.

20. The computer-implemented method of claim 1 , wherein the medical image is 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).

21. The computer-implemented method of claim 1 , wherein the analysis of the one or more regions of low density non-calcified plaque further comprises at least one of:
determining a distance from the one or more regions of low density non-calcified plaque to one or more of a lumen wall or vessel wall; or
determining a degree of embeddedness of the one or more regions of low density noncalcified plaque in one or more of non-calcified plaque or calcified plaque.

22. The computer-implemented method of claim 1 , wherein determining the risk of CAD of the subject is based at least in part on the determined shape of the one or more regions of low dens

Assignees

• Cleerly Inc

Inventors

• Min James K
• Earls James P
• Malkasian Shant
• Rodrigues Marques Hugo Miguel
• Chan Chung
• Ronen Shai

Classifications

• G06V10/26

  Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion · CPC title

• G06V10/255

  Detecting or recognising potential candidate objects based on visual cues, e.g. shapes · CPC title

• G06V10/82

  using neural networks · CPC title

• G06V2201/03

  Recognition of patterns in medical or anatomical images · CPC title

• G06T2207/10081

  Computed x-ray tomography [CT] · CPC title