Generative Adversarial Networks Accurately Reconstruct Pan-Cancer Histology from Pathologic, Genomic, and Radiographic Latent Features
Frederick Matthew Howard, Hanna M. Hieromnimon, Siddhi Ramesh, James M. Dolezal, Sara E. Kochanny, Qianchen Zhang, Brad Feiger, Joseph Peterson, Cheng Fan, Charles M. Perou, Jasmine Vickery, Megan Sullivan, Kimberly Cole, Galina F. Khramtsova, Alexander 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.
Science Advances · Nov 15, 2024Peer-reviewedCancer Biology