Cancer detection using biopsy digital images

A computing apparatus comprising:

• a memory;
• and
• a processing device, operatively coupled to the memory, to:
• receive a digital image of a tissue biopsy stained for a presence of a biomarker, wherein the biomarker is associated with a presence of cancer in the tissue, and wherein the digital image comprises a plurality of pixels;
• determine a corresponding set of color attribute values of a color space for each pixel of the plurality of pixels;
• classify, in view of the corresponding set of color attribute values of the color space, each pixel of the plurality of pixels between a first subset of pixels depicting tissue and a second subset of pixels not depicting tissue using a first trained machine learning model;
• determine whether the digital image depicts cancerous tissue in view of a number of pixels in the second subset of pixels;
• and
• responsive to determining that the digital image depicts cancerous tissue in view of the number of pixels in the second subset of pixels, determine a predicted cancer stage for the digital image of the tissue biopsy based at least in part on a color intensity category associated with the corresponding set of color attribute values of the color space for each pixel of the first subset of pixels.

A non-transitory computer readable storage medium, having instructions stored therein, which when executed by a processing device of a computer system, cause the processing device to:

• receive a digital image of a tissue biopsy stained for a presence of a biomarker, wherein the biomarker is associated with a presence of cancer in the tissue, and wherein the digital image comprises a plurality of pixels;
• determine a corresponding set of color attribute values of a color space for each pixel of the plurality of pixels;
• classify, in view of the corresponding set of color attribute values of the color space, each pixel of the plurality of pixels between a first subset of pixels depicting tissue and a second subset of pixels not depicting tissue using a first trained machine learning model;
• determine whether the digital image depicts cancerous tissue in view of a number of pixels in the second subset of pixels;
• and
• responsive to determining that the digital image depicts cancerous tissue in view of the number of pixels in the second subset of pixels, determine a predicted cancer stage for the digital image of the tissue biopsy based at least in part on a color intensity category associated with the corresponding set of color attribute values of the color space for each pixel of the first subset of pixels.