IMAGE-BASED CELL PLOIDY QUANTIFICATION (ICPQ)

ICPQ is a deep learning-based computational algorithm to characterize and quantify hepatic ploidy for individual patients. To make the whole analysis procedure more accessible for clinical samples, the algorithm can quantify ploidy information using hematoxylin-eosin (H&E) histopathology images. A deep learning model was trained to segment and classify different types of nuclei on H&E histopathology images. Based on the identified hepatocyte nuclei, both cellular and nuclear ploidy are calculated. Using this algorithm, we can establish the total number of hepatocytes and detailed ploidy of each hepatocyte in the region of interest (ROI).