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

TL;DR

This study introduces MAKO, a benchmarking framework for evaluating pathology foundation models to predict breast cancer recurrence risk from histology images, demonstrating promising results comparable to transcriptomic assays.

Contribution

The paper presents MAKO, a comprehensive benchmarking framework for pathology models, and shows that histology-based models can effectively predict recurrence risk, offering a scalable alternative to genomic assays.

Findings

Several models outperformed baselines in classification, regression, and survival tasks.

Pathology models stratified patients by recurrence risk similarly to transcriptomic scores.

Tumor regions alone were sufficient for high-risk predictions and potential biomarkers were identified.

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. Models were trained and validated on the Carolina Breast Cancer Study and externally tested on TCGA BRCA. Several foundation models outperformed baselines across classification, regression, and survival tasks. CONCH achieved the highest ROC AUC, while H-optimus-0 and Virchow2 showed top correlation with continuous ROR-P scores. All pathology models stratified CBCS participants by recurrence similarly to transcriptomic ROR-P. 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.