	US 12,229,966 B2
	Systems and methods for classification of arterial image regions and features thereof
Shimin Li, Acton, MA (US); Ajay Gopinath, Bedford, MA (US); and Kyle Savidge, Medford, MA (US)
Assigned to LightLab Imaging, Inc., Westford, MA (US)
Filed by LightLab Imaging, Inc., Westford, MA (US)
Filed on Jan. 11, 2023, as Appl. No. 18/153,148.
Application 18/153,148 is a continuation of application No. 17/561,018, filed on Dec. 23, 2021.
Application 17/561,018 is a continuation of application No. 16/741,718, filed on Jan. 13, 2020, granted, now 11,250,294, issued on Feb. 15, 2022.
Claims priority of provisional application 62/791,876, filed on Jan. 13, 2019.
Prior Publication US 2023/0162367 A1, May 25, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 3/08 (2023.01); G06F 18/211 (2023.01); G06F 18/214 (2023.01); G06F 18/40 (2023.01); G06N 3/04 (2023.01); G06T 7/11 (2017.01)

CPC G06T 7/11 (2017.01) [G06F 18/211 (2023.01); G06F 18/214 (2023.01); G06F 18/40 (2023.01); G06N 3/04 (2013.01); G06N 3/08 (2013.01); G06V 2201/03 (2022.01)]

12 Claims

1. A method for assessing a coronary artery comprising:

acquiring a set of blood vessel image data;

generating calcium annotations within the set of blood vessel image data;

training a neural network of a machine learning system using the calcium annotations within the set of blood vessel image data;

providing patient image data to the trained neural network;

determining a prevalence of calcium within the patient image data based on output of the trained neural network;

determining one or more blood vessel flow values based on the patient image data;

providing for display, by one or more processors, a representation of the prevalence of calcium and the one or more blood vessel flow values.