CPC G06T 7/0012 (2013.01) [G06T 7/90 (2017.01); G06V 20/698 (2022.01); G06T 2207/10024 (2013.01); G06T 2207/10056 (2013.01); G06T 2207/30024 (2013.01); G06T 2207/30204 (2013.01)] | 17 Claims |
1. A method comprising:
accessing an image depicting a biological sample stained with a set of biomarkers;
accessing a reference color matrix, wherein the reference color matrix includes co-localization data for the set of biomarkers, wherein the co-localization data defines a plurality of groups of biomarkers within the set of biomarkers, each group of biomarkers of the plurality of groups of biomarkers including a subset of biomarkers of the set of biomarkers, wherein a first biomarker and a second biomarker of a subset of biomarkers of a first group of biomarkers of the plurality of groups of biomarkers represent a first common biological structure;
unmixing, based on the co-localization data of the reference color matrix, the image to generate a result that identifies, for one or more pixels of the image, a sparsity model that represents a first estimated fraction of contribution of the first biomarker and a second estimated fraction of contribution of the second biomarker; and
outputting the result.
|