US 11,751,831 B2
Systems and methods for characterizing high risk plaques
James K. Min, Denver, CO (US)
Assigned to Cleerly, Inc., Denver, CO (US)
Filed by Cleerly, Inc., Denver, CO (US)
Filed on Dec. 29, 2022, as Appl. No. 18/148,296.
Application 18/148,296 is a continuation of application No. 17/662,762, filed on May 10, 2022.
Application 17/662,762 is a continuation of application No. 17/033,136, filed on Sep. 25, 2020, granted, now 11,350,899, issued on May 3, 2022.
Application 17/033,136 is a continuation of application No. 16/750,278, filed on Jan. 23, 2020, granted, now 10,813,612, issued on Oct. 27, 2020.
Claims priority of provisional application 62/797,024, filed on Jan. 25, 2019.
Prior Publication US 2023/0138889 A1, May 4, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. A61B 6/00 (2006.01); A61B 6/03 (2006.01); G06T 7/00 (2017.01)
CPC A61B 6/504 (2013.01) [A61B 6/032 (2013.01); A61B 6/5217 (2013.01); A61B 6/5223 (2013.01); G06T 7/0012 (2013.01); G06T 7/97 (2017.01); G06T 2207/10028 (2013.01); G06T 2207/10072 (2013.01); G06T 2207/30101 (2013.01)] 30 Claims
OG exemplary drawing
 
1. A computer-implemented method for risk assessment of coronary plaque by analyzing metrics generated from radiodensity values of coronary plaque of a subject and previously stored metrics generated from radiodensity values of coronary plaque of a collection of a plurality of other subjects, the method comprising:
generating image information for the subject, the image information including image data of computed tomography (CT) scans along a vessel of the subject, the image data having radiodensity values of coronary plaque and radiodensity values of perivascular tissue located adjacent to the coronary plaque, wherein generating the image information comprises:
accessing CT scan parameters stored for the subject in a database, the CT scan parameters comprising:
a CT scanner type; and
one or more of contrast type used in the subject or an injection rate of contrast into the subject; and
automatically determining radiodensity values of coronary plaque in the image data;
determining, based on applying a machine learning algorithm to the image information, coronary plaque information of the subject, wherein determining the coronary plaque information comprises:
quantifying, using the image information, radiodensity values in a region of coronary plaque of the subject; and
generating metrics of coronary plaque of the subject using the quantified radiodensity values in the region of coronary plaque;
accessing a database of coronary plaque information of a collection of a plurality of other subjects, the coronary plaque information in the database including a collection of metrics generated from radiodensity values of a region of coronary plaque in the plurality of other subjects; and
generating a risk assessment of the coronary plaque information of the subject by comparing the metrics of the coronary plaque and one or more characteristics of the subject to the collection of metrics of the coronary plaque of the plurality of other subjects, in the database, having one or more of the one or more characteristics of the subject,
wherein the method is performed by one or more computer hardware processors configured to execute computer-executable instructions on a non-transitory computer storage medium.