Towards Robust Foundation Models for Digital Pathology

TL;DR

This paper systematically investigates the robustness of biomedical foundation models in digital pathology, revealing significant vulnerabilities to non-biological features and proposing a framework for their robustification to ensure safe clinical deployment.

Contribution

It introduces PathoROB, a new robustness benchmark with metrics and datasets, and demonstrates the importance of robustness evaluation and improvement for clinical safety.

Findings

All evaluated FMs show robustness deficits.

Robustness differences significantly impact diagnostic accuracy.

Post-hoc robustification reduces, but does not eliminate, errors.

Abstract

Biomedical Foundation Models (FMs) are rapidly transforming AI-enabled healthcare research and entering clinical validation. However, their susceptibility to learning non-biological technical features -- including variations in surgical/endoscopic techniques, laboratory procedures, and scanner hardware -- poses risks for clinical deployment. We present the first systematic investigation of pathology FM robustness to non-biological features. Our work (i) introduces measures to quantify FM robustness, (ii) demonstrates the consequences of limited robustness, and (iii) proposes a framework for FM robustification to mitigate these issues. Specifically, we developed PathoROB, a robustness benchmark with three novel metrics, including the robustness index, and four datasets covering 28 biological classes from 34 medical centers. Our experiments reveal robustness deficits across all 20 evaluated FMs, and substantial robustness differences between them. We found that non-robust FM representations can cause major diagnostic downstream errors and clinical blunders that prevent safe clinical adoption. Using more robust FMs and post-hoc robustification considerably reduced (but did not yet eliminate) the risk of such errors. This work establishes that robustness evaluation is essential for validating pathology FMs before clinical adoption and demonstrates that future FM development must integrate robustness as a core design principle. PathoROB provides a blueprint for assessing robustness across biomedical domains, guiding FM improvement efforts towards more robust, representative, and clinically deployable AI systems that prioritize biological information over technical artifacts.