Generative adversarial networks accurately reconstruct pan-cancer histology from pathologic, genomic, and radiographic latent features
Frederick M. Howard, Hanna M. Hieromnimon, Siddhi Ramesh, James M. Dolezal, Sara Kochanny, Qianchen Zhang, Brad Feiger, J.R. Peterson, Cheng Fan, Charles M. Perou, Jasmine Vickery, Megan Sullivan, Kimberly Cole, Galina Khramtsova, Alexander T. Pearson
Abstract
Artificial intelligence models have been increasingly used in the analysis of tumor histology to perform tasks ranging from routine classification to identification of molecular features. These approaches distill cancer histologic images into high-level features, which are used in predictions, but understanding the biologic meaning of such features remains challenging. We present and validate a custom generative adversarial network-HistoXGAN-capable of reconstructing representative histology using feature vectors produced by common feature extractors. We evaluate HistoXGAN across 29 cancer subtypes and demonstrate that reconstructed images retain information regarding tumor grade, histologic subtype, and gene expression patterns. We leverage HistoXGAN to illustrate the underlying histologic features for deep learning models for actionable mutations, identify model reliance on histologic batch effect in predictions, and demonstrate accurate reconstruction of tumor histology from radiographic imaging for a "virtual biopsy."