Generative Adversarial Networks Accurately Reconstruct Pan-Cancer Histology from Pathologic, Genomic, and Radiographic Latent Features
F. M. Howard, H. Hieromnimon, S. Ramesh, J. Dolezal, S. Kochanny, Q. Zhang, B. Feiger, J. Peterson, C. Fan, C. Perou, J. M. Vickery, M. Sullivan, K. Cole, G. Khramtsova, A. T. Pearson
This paper introduces HistoXGAN, a GAN that reconstructs cancer histology from latent features, showing it retains tumor grade, histologic subtype, and gene expression patterns across 29 cancer types.
bioRxiv · Mar 22, 2024Cancer Biology