Towards interpretable prediction of recurrence risk in breast cancer using pathology foundation models

Kaczmarzyk, Jakub R, Van Alsten, Sarah C, Cozzo, Alyssa J, Gupta, Rajarsi, Koo, Peter K, Troester, Melissa A, Hoadley, Katherine A, Saltz, Joel H (January 2026) Towards interpretable prediction of recurrence risk in breast cancer using pathology foundation models. npj Digital Medicine. ISSN 2398-6352

PDF 10.1038.s41746-025-02334-2.pdf - Published Version Available under License Creative Commons Attribution. Download (3MB)

Abstract

Transcriptomic assays such as the PAM50-based ROR-P score guide recurrence risk stratification in non-metastatic, ER-positive, HER2-negative breast cancer but are not universally accessible. Histopathology is routinely available and may offer a scalable alternative. We introduce MAKO, a benchmarking framework evaluating 12 pathology foundation models and two non-pathology baselines for predicting ROR-P scores from H&E-stained whole-slide images using attention-based multiple instance learning. Foundation models, large neural networks pre-trained on millions of pathology images and adaptable to diverse downstream tasks, were trained and validated on the Carolina Breast Cancer Study and externally tested on TCGA BRCA. Several foundation models outperformed baseline models across classification, regression, and survival tasks. CONCH achieved the highest ROC AUC, while H-optimus-0 and Virchow2 showed the top correlation with continuous ROR-P scores. All pathology models stratified CBCS participants by recurrence similarly to transcriptomic ROR-P. Using the HIPPO interpretability method, we found that tumor regions were necessary and sufficient for high-risk predictions, and we identified candidate tissue biomarkers of recurrence. These results highlight the promise of interpretable, histology-based risk models in precision oncology.

Item Type:	Paper
Subjects:	diseases & disorders > cancer diseases & disorders organs, tissues, organelles, cell types and functions > organs types and functions > breast diseases & disorders > cancer > cancer types > breast cancer organs, tissues, organelles, cell types and functions > organs types and functions organs, tissues, organelles, cell types and functions diseases & disorders > cancer > cancer types
CSHL Authors:	Koo, Peter K Kaczmarzyk, Jakub
Communities:	CSHL labs > Koo Lab
SWORD Depositor:	CSHL Elements
Depositing User:	CSHL Elements
Date:	16 January 2026
Date Deposited:	11 Feb 2026 20:25
Last Modified:	11 Feb 2026 20:25
Related URLs:	Publisher
URI:	https://repository.cshl.edu/id/eprint/42073

Actions (login required)

Administrator's edit/view item