US 12,406,371 B2
Systems and methods for image segmentation using multiple stain indicators
Dongyao Li, Pleasanton, CA (US); Neil Ira Weisenfeld, Pleasanton, CA (US); Paul Ryvkin, San Francisco, CA (US); Xiaoyan Qian, Stockholm (SE); and Preyas Shah, Pleasanton, CA (US)
Assigned to 10x Genomics, Inc., Pleasanton, CA (US)
Filed by 10x Genomics, Inc., Pleasanton, CA (US)
Filed on Jan. 25, 2025, as Appl. No. 19/037,114.
Claims priority of provisional application 63/570,399, filed on Mar. 27, 2024.
Claims priority of provisional application 63/566,088, filed on Mar. 15, 2024.
Claims priority of provisional application 63/625,132, filed on Jan. 25, 2024.
Prior Publication US 2025/0245832 A1, Jul. 31, 2025
Int. Cl. G06T 7/00 (2017.01); G06T 7/11 (2017.01); G06T 7/136 (2017.01); G06T 7/194 (2017.01)
CPC G06T 7/0014 (2013.01) [G06T 7/11 (2017.01); G06T 7/136 (2017.01); G06T 7/194 (2017.01); G06T 2207/20152 (2013.01); G06T 2207/20156 (2013.01); G06T 2207/30024 (2013.01)] 23 Claims
OG exemplary drawing
 
1. A method of cell segmentation comprising:
reading a nuclear segmentation mask of at least one image, the at least one image comprising a plurality of pixels arranged in at least two dimensions, the nuclear segmentation mask identifying a plurality of cellular nuclei stained with a cellular nucleus stain in the at least one image;
for each of the plurality of pixels in the at least one image, determining a plurality of amplitudes for each of the plurality of pixels, each amplitude of the plurality of amplitudes for each of the plurality of pixels corresponding to exactly one dimension of the at least two dimensions;
constructing a graph having a plurality of nodes and a plurality of edges, wherein each of the plurality of nodes corresponds to one of the plurality of pixels and wherein nodes corresponding to neighboring pixels are connected by one of the plurality of edges;
assigning a weight to each of the plurality of edges, wherein the weight of each respective edge is based on the amplitudes of the pixels corresponding to the nodes connected thereby;
based on the graph, determining, for each of the plurality of cellular nuclei, a heat map corresponding to a predicted cell region associated with that cellular nucleus; and
based on the heat maps of the plurality of cellular nuclei, determining a cellular segmentation mask comprising the predicted cell regions.