US 12,078,597 B2
Framework for image based unsupervised cell clustering and sorting
Ming-Chang Liu, San Jose, CA (US); and Su-Hui Chiang, San Jose, CA (US)
Assigned to SONY GROUP CORPORATION, Tokyo (JP); and SONY CORPORATION OF AMERICA, New York, NY (US)
Filed by SONY GROUP CORPORATION, Tokyo (JP); and Sony Corporation of America, New York, NY (US)
Filed on Apr. 5, 2021, as Appl. No. 17/222,131.
Claims priority of provisional application 63/116,065, filed on Nov. 19, 2020.
Prior Publication US 2022/0155232 A1, May 19, 2022
Int. Cl. G01N 21/64 (2006.01); G06F 18/214 (2023.01); G06F 18/231 (2023.01); G06N 3/04 (2023.01); G06T 7/00 (2017.01); G06V 10/44 (2022.01)
CPC G01N 21/6486 (2013.01) [G01N 21/6458 (2013.01); G06F 18/214 (2023.01); G06F 18/231 (2023.01); G06N 3/04 (2013.01); G06T 7/0012 (2013.01); G06V 10/44 (2022.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30024 (2013.01)] 15 Claims
OG exemplary drawing
 
1. A method comprising:
training a feature extractor which comprises receiving one or more cell image datasets with or without ground truth information to train the feature extractor;
performing offline initial image-based unsupervised clustering, wherein performing the offline initial image-based unsupervised clustering for a set of cell images includes using the feature extractor to extract features of the cell images, using a small subset of the given cell images to train a cluster component, and using the cluster component to identify the clusters of the given cell images in an unsupervised manner; and
performing online image-based single cell sorting, wherein performing online image-based single cell sorting includes utilizing the feature extractor to extract features of cell images and using the cluster component for unsupervised cell sorting.