Abstract: A cancer prediction engine receives a digital image of a tissue biopsy stained for a presence of a biomarker associated with a presence of cancer in the tissue, determines a set of color attribute values of a color space for each pixel of the digital image, classifies, in view of the color attribute values, each pixel of the digital image between a first subset of pixels depicting tissue and a second subset of pixels not depicting tissue, determines 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, determines 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 color attribute values for each pixel of the first subset of pixels.

Abstract: A cancer prediction engine receives a digital image of a tissue biopsy stained for a presence of a biomarker associated with a presence of cancer in the tissue, determines a set of color attribute values of a color space for each pixel of the digital image, classifies, in view of the color attribute values, each pixel of the digital image between a first subset of pixels depicting tissue and a second subset of pixels not depicting tissue, determines 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, determines 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 color attribute values for each pixel of the first subset of pixels.

Abstract: Nuclear Factor I/B (Nfib), a protein important to lung maturation in human embryos, is an oncogene in SCLC. This novel bioinformatics image-processing tool analyzes digital images of biopsies stained for Nfib. First, the model was trained to determine whether the biopsy was cancerous or not, then it was trained to predict the whether the biopsy represented limited stage SCLC or extensive stage SCLC. The factors considered were the amount of positive Nfib staining, amount of negative Nfib staining, amount of “non-tissue” areas on the slide, and the intensity of the staining itself. Overall this tool is highly accurate with 95.11% accuracy. Doctors can directly use this tool to accurately predict stage of SCLC in less than one minute. This system application can allow doctors to better guide their patients' treatments of SCLC.