Generative adversarial networks accurately reconstruct pan-cancer histology from pathologic, genomic, and radiographic latent features

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."

Authors

Institutions

Publication Details

Journal
Science Advances
Published
2024-11-15
DOI
https://doi.org/10.1126/sciadv.adq0856
Citations
16
Primary Topic
AI in cancer detection
Type
article
Field-Weighted Citation Impact
5.56

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Generative adversarial networks accurately reconstruct pan-cancer histology from pathologic, genomic, and radiographic latent features

J.R. Peterson, Hanna M. Hieromnimon, Qianchen Zhang, James M. Dolezal et al.
16 citations
Science Advances
AI in cancer detection
5.56
article

Generative adversarial networks accurately reconstruct pan-cancer histology from pathologic, genomic, and radiographic latent features

J.R. Peterson, Hanna M. Hieromnimon, Qianchen Zhang, James M. Dolezal, Alexander T. Pearson, Frederick M. Howard, Galina Khramtsova, Sara Kochanny, Jasmine Vickery, Charles M. Perou, Megan Sullivan, Siddhi Ramesh, Brad Feiger, Cheng Fan, Kimberly Cole
article en
16 citations

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."

Science AdvancesVol. 10(46)
University of North Carolina at Chapel Hill (US), NorthShore University HealthSystem (US), Ansys (United States) (US), University of Chicago (US), SimBiotic Software (United States) (US), University of Pennsylvania Health System (US), Geisinger Neuroscience Institute (US)
European Commission, National Cancer Institute
Openalex Percentile: Top 4%
AI in cancer detection
5.56
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.