Benchmarking Pathology Foundation Models for Breast Cancer Survival Prediction

TL;DR

This study benchmarks pathology foundation models for breast cancer survival prediction, demonstrating generational improvements and highlighting the efficiency of compact models with external validation across large cohorts.

Contribution

It provides the first large-scale, externally validated benchmark of PFMs for breast cancer survival prediction, comparing multiple models and emphasizing practical deployment insights.

Findings

H-optimus-1 achieves the best survival prediction performance.

Second-generation PFMs outperform first-generation models.

Compact H0-mini model slightly outperforms larger teacher models despite fewer parameters.

Abstract

Pathology foundation models (PFMs) have recently emerged as powerful pretrained encoders for computational pathology, enabling transfer learning across a wide range of downstream tasks. However, systematic comparisons of these models for clinically meaningful prediction problems remain limited, especially in the context of survival prediction under external validation. In this study, we benchmark widely used and recently proposed PFMs for breast cancer survival prediction from whole-slide histopathology images. Using a standardized pipeline based on patch-level feature extraction and a unified survival modeling framework, we evaluate model representations across three independent clinical cohorts comprising more than 5,400 patients with long-term follow-up. Models are trained on one cohort and evaluated on two independent external cohorts, enabling a rigorous assessment of cross-dataset generalization. Overall, H-optimus-1 achieves the strongest survival prediction performance. More broadly, we observe consistent generational improvements across model families, with second-generation PFMs outperforming their first-generation counterparts. However, absolute performance differences between many recent PFMs remain modest, suggesting diminishing returns from further scaling of pretraining data or model size alone. Notably, the compact distilled model H0-mini slightly outperforms its larger teacher model H-optimus-0, despite using fewer than 8% of the parameters and enabling significantly faster feature extraction. Together, these results provide the first large-scale, externally validated benchmark of PFMs for breast cancer survival prediction, and offer practical guidance for efficient deployment of PFMs in clinical workflows.