Human-interpretable image features derived from densely mapped cancer pathology slides predict diverse molecular phenotypes.

ABSTRACT: Computational methods have made substantial progress in improving the accuracy and throughput of pathology workflows for diagnostic, prognostic, and genomic prediction. Still, lack of interpretability remains a significant barrier to clinical integration. We present an approach for predicting clinically-relevant molecular phenotypes from whole-slide histopathology images using human-interpretable image features (HIFs). Our method leverages >1.6 million annotations from board-certified pathologists across >5700 samples to train deep learning models for cell and tissue classification that can exhaustively map whole-slide images at two and four micron-resolution. Cell- and tissue-type model outputs are combined into 607 HIFs that quantify specific and biologically-relevant characteristics acr

SUBMITTER: Diao JA 

PROVIDER: S-EPMC7955068 | biostudies-literature | 2021 Mar

REPOSITORIES: biostudies-literature