| CPC G06T 7/0012 (2013.01) [G06T 7/0016 (2013.01); G06T 7/11 (2017.01); G06T 7/33 (2017.01); G06T 7/62 (2017.01); G06V 10/764 (2022.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30048 (2013.01); G06T 2207/30101 (2013.01); G06T 2207/30168 (2013.01)] | 24 Claims |

|
1. A method of identifying vascular portions of a vascular image, the method comprising:
accessing the vascular image comprising a 2-D angiographic image;
applying a first ML-based vascular identifier to the vascular image to produce a first data structure identifying a path that extends along at least some vascular portions, wherein a vascular portion is an image location associated with part of a blood vessel depicted in the vascular image;
applying a second vascular identifier to the vascular image to produce a second data structure identifying one or more pixel masks, wherein the pixel masks comprise respective blobs of vascular portions;
wherein the path
includes some vascular portions not in the one or more pixels masks; and
combining the first and second data structures to produce a combined identification of vascular portions that form a particular blood vessel depicted in the vascular image, wherein combining is based on:
connection information between the one or more pixel masks and the path, or
similarity of directionality between an individual pixel mask and the path.
|