US 12,423,810 B2
Image-based unsupervised multi-model cell clustering
Su-Hui Chiang, San Jose, CA (US); and Ming-Chang Liu, 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 Nov. 28, 2022, as Appl. No. 18/070,352.
Application 18/070,352 is a continuation in part of application No. 17/222,131, filed on Apr. 5, 2021, granted, now 12,078,597.
Claims priority of provisional application 63/116,065, filed on Nov. 19, 2020.
Prior Publication US 2023/0377139 A1, Nov. 23, 2023
Int. Cl. G06T 7/00 (2017.01); G06V 10/44 (2022.01); G06V 10/762 (2022.01)
CPC G06T 7/0012 (2013.01) [G06V 10/44 (2022.01); G06V 10/762 (2022.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30024 (2013.01)] 24 Claims
OG exemplary drawing
 
1. A method comprising:
performing offline initial image-based unsupervised clustering, wherein performing the offline initial image-based unsupervised clustering for a set of cell images includes using a 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;
training a plurality of models, wherein each model of the plurality of models is designed to extract a feature of each cell; and
performing online image-based single cell sorting.