Abstract
While computational methods have made substantial progress in improving the accuracy and throughput of pathology workflows for diagnostic, prognostic, and genomic prediction, lack of interpretability remains a significant barrier to clinical integration. In this study, we present a novel approach for predicting clinically-relevant molecular phenotypes from histopathology whole-slide images (WSIs) using human-interpretable image features (HIFs). Our method leverages >1.6 million annotations from board-certified pathologists across >5,700 WSIs to train deep learning models for high-resolution tissue classification and cell detection across entire WSIs in five cancer types. Combining cell- and tissue-type models enables computation of 607 HIFs that comprehensively capture specific and biologically-relevant characteristics of multiple tumors. We demonstrate that these HIFs correlate with well-known markers of the tumor microenvironment (TME) and can predict diverse molecular signatures, including immune checkpoint protein expression and homologous recombination deficiency (HRD). Our HIF-based approach provides a novel, quantitative, and interpretable window into the composition and spatial architecture of the TME.
Competing Interest Statement
The authors declare the following competing interests: A.K. and A.H.B. are the cofounders of PathAI, Inc., a company that builds artificial intelligence tools for pathology. J.A.D., W.F.C., J.K.W., S.K.R., M.B.R., A.L., C.M., B.G., V.M., J.K.K., M.C.M., I.N.W., A.T.W., and H.L.E. are currently, or were formerly, employed at PathAI, Inc.