Do Center Biases Propagate? Robustness of Pathology Foundation Models in Whole-Slide Image Classification

2026-09-23

AI Summary

研究评估了病理基础模型在全切片图像分类中的中心偏差传播问题，使用Cramér's V量化类-中心相关性，并测试了ComBat作为增强鲁棒性的策略。

Abstract

Pathology foundation models (PFMs) have transformed computational pathology through powerful representation learning from histopathological images. PFMs provide rich, discriminative representations for whole slide image (WSI) analysis, enabling tasks such as slide-level classification under multiple instance learning (MIL). However, these representations may also encode non-biological signals associated with acquisition centers, potentially introducing spurious shortcuts into downstream predictions. In this work, we evaluate center-associated robustness in WSI classification using a controlled training setting with increasing class-center correlations quantified by Cramér's V. We benchmark six PFMs across four datasets and two MIL aggregators, while evaluating ComBat as a robustification strategy. We further introduce the Area Under the Cramér's V Curve (AUCC) to jointly capture absolute classification performance and its degradation as spurious correlation increases. Results show that center-related information encoded by PFMs propagates to WSI-level predictions, with robustness depending on both the PFM representation and MIL aggregation strategy. Additionally, ComBat harmonization does not provide consistent robustness gains across datasets.

Problem

• Pathology Foundation Models
• Whole-Slide Image Classification
• Center Biases
• Robustness
• Spurious Correlations

Innovation

• Pathology Foundation Models
• Whole-Slide Image Classification
• Cramér's V
• Area Under the Cramér's V Curve (AUCC)
• Multiple Instance Learning (MIL)