Peer-Reviewed Publication
Sci Adv2024;10(46):eadq0856.November 15, 2024Journal Article
Generative adversarial networks accurately reconstruct pan-cancer histology from pathologic, genomic, and radiographic latent features.
Frederick M Howard1, Hanna M Hieromnimon1, Siddhi Ramesh1, James Dolezal2, Sara Kochanny1, Qianchen Zhang1, Brad Feiger3, Joseph Peterson3, Cheng Fan4, Charles M Perou4, Jasmine Vickery5, Megan Sullivan6, Kimberly Cole7, Galina Khramtsova7, Alexander T Pearson1
1Department of Medicine, University of Chicago, Chicago, IL, USA.
2Geisinger Cancer Institute, Danville, PA, USA.
3SimBioSys, Chicago, IL, USA.
4Lineberger Comprehensive Cancer Center, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA.
5Department of Pathology, University of Pennsylvania Health System, Pennsylvania, PA, USA.
6Department of Pathology, NorthShore University HealthSystem, Evanston, IL, USA.
7Department of Pathology, University of Chicago, Chicago, IL, USA.
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 cu…
Create a free account to keep reading
Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.
Want unlimited research access? See Pro plans