AI-powered analysis of nuclear morphology associated with prognosis in high-grade serous carcinoma

Ovarian carcinoma is a leading driver of cancer-related mortality in women, but predicting long-term survival at diagnosis remains a challenge. The majority of advanced stage cases are of the aggressive high-grade serous carcinoma (HGSC) subtype.

Features of both the tumor microenvironment as well as cancer cell nuclei have both been shown to affect clinical outcome in several cancer types, including ovarian cancer. Here we demonstrate that AI-powered pathology can classify cells and tissue regions in the high-grade serous carcinoma (HGSC) tumor microenvironment, and reveal nuclear morphology associated with patient outcomes, directly from digitized hematoxylin and eosin (H&E)-stained whole slide images (WSI).