Nature Cancer Исследования рака

A multimodal foundation model for molecular and morphologic data in oncology

Vaidya, Anurag, Zhang, Andrew, Jaume, Guillaume, Song, Andrew H., Ding, Tong, Wagner, Sophia J., Lu, Ming Y., Robertson, Harry, Williamson, Drew F. K., Doucet, Paul, Almagro-Perez, Cristina, Chen, Richard J., ElHarouni, Dina, Ayoub, Georges, Bossi, Connor, Ligon, Keith L., Patrick, Ellis, Beltran, Himisha, Macconaill, Laura, Lindeman, Neal, Sholl, Lynette, Gerber, Georg K., Le, Long Phi, Mahmood, Faisal
Springer Nature · 2026-11-01 · DOI 10.1038/s43018-026-01252-w

Аннотация

Foundation models are advancing computational pathology by transferring knowledge from large datasets to diagnostic, prognostic and treatment response tasks. Most existing models, however, either operate at the patch level or learn slide-level representations using image-based objectives, coarse tissue labels or pathology reports that vary across institutions and reflect the subjectivity inherent in narrative reporting. Here we introduce THREADS, which instead learns general-purpose whole-slide representations by aligning tissue morphology with genomic or transcriptomic profiles. THREADS was pretrained on over 47,000 hematoxylin-and-eosin-stained tissue sections and evaluated across 107 oncology tasks spanning cancer subtyping and grading, tumor microenvironment characterization, treatment response prediction and survival analysis. THREADS consistently outperformed leading whole-slide foundation models and supervised baselines while demonstrating strong transfer across external cohorts and high label efficiency. These findings establish molecularly guided pretraining as an effective strategy for learning general-purpose whole-slide representations and motivate future extensions incorporating additional molecular, spatial and clinical modalities. Vaidya et al. present THREADS, a foundation model leveraging multimodal data and driven by tissue molecular composition features to perform with high efficiency and demonstrating generalizability across clinical oncology tasks.

Читать у издателя →