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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kaczmarzyk, Jakub R., Van Alsten, Sarah C., Cozzo, Alyssa J., Gupta, Rajarsi, Koo, Peter K., Troester, Melissa A., Hoadley, Katherine A., Saltz, Joel H.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918125992148992
author Kaczmarzyk, Jakub R.
Van Alsten, Sarah C.
Cozzo, Alyssa J.
Gupta, Rajarsi
Koo, Peter K.
Troester, Melissa A.
Hoadley, Katherine A.
Saltz, Joel H.
author_facet Kaczmarzyk, Jakub R.
Van Alsten, Sarah C.
Cozzo, Alyssa J.
Gupta, Rajarsi
Koo, Peter K.
Troester, Melissa A.
Hoadley, Katherine A.
Saltz, Joel H.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_12025
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle 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.
Tissues and Organs
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.
title Towards interpretable prediction of recurrence risk in breast cancer using pathology foundation models
topic Tissues and Organs
url https://arxiv.org/abs/2508.12025