US 12,175,666 B2
Systems and methods for classifying biomedical image data using a graph neural network
Jason Ku Wang, Los Angeles, CA (US); Maryam Pouryahya, Bethesda, MD (US); Kenneth K. Leidal, Melrose, MA (US); Oscar M. Carrasco-Zevallos, Somerville, MA (US); Ilan Wapinski, Brookline, MA (US); and Amaro Taylor-Weiner, Brooklyn, NY (US)
Assigned to PathAI, Inc., Boston, MA (US)
Filed by PathAI, Inc., Boston, MA (US)
Filed on Feb. 1, 2022, as Appl. No. 17/590,642.
Claims priority of provisional application 63/144,318, filed on Feb. 1, 2021.
Prior Publication US 2022/0245802 A1, Aug. 4, 2022
Int. Cl. G06T 7/00 (2017.01); G06V 10/44 (2022.01); G06V 10/762 (2022.01); G06V 10/82 (2022.01); G16H 30/20 (2018.01); G16H 50/30 (2018.01)
CPC G06T 7/0012 (2013.01) [G06V 10/454 (2022.01); G06V 10/457 (2022.01); G06V 10/7635 (2022.01); G06V 10/82 (2022.01); G16H 30/20 (2018.01); G16H 50/30 (2018.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30056 (2013.01)] 27 Claims
OG exemplary drawing
 
1. A method for classifying biomedical image data, the method comprising:
generating, by at least one computer processor, an annotated representation of biomedical image data;
identifying, by the at least one computer processor, a plurality of pixel clusters based on the biomedical image data;
constructing, by the at least one computer processor, a graph based on the plurality of pixel clusters;
determining, by the at least one computer processor, at least one biomedical feature for at least one node of the graph based on the annotated representation of the biomedical image data; and
processing, by the at least one computer processor, a graph neural network to classify the biomedical image data based on the at least one biomedical feature, wherein the graph neural network includes at least one layer that transforms an input graph with at least one node feature into an updated graph, wherein the at least one node feature is updated in the updated graph.