analiza aiqbench
This study reveals that pathology foundation models inadvertently encode acquisition center biases, which propagate directly into downstream whole-slide image classification predictions. The research demonstrates that robustness varies significantly depending on the specific model architecture and multiple instance learning strategy, while standard harmonization techniques like ComBat fail to consistently mitigate these spurious correlations. For developers deploying AI in clinical settings, this highlights the critical need for rigorous bias auditing beyond simple performance metrics to ensure reliable diagnostic outcomes across diverse hospital environments.
Do Center Biases Propagate? Robustness of Pathology Foundation Models in Whole-Slide Image Classification
arXiv:2609.28231v1 Announce Type: cross 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 Cram\'er'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 Cram\'er'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.
Title:Do Center Biases Propagate? Robustness of Pathology Foundation Models in Whole-Slide Image Classification
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.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2609.28231 [cs.CV]
(or arXiv:2609.28231v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2609.28231 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 269 cuvinte
Subiecte conexe
News
Quantum Computing Report · 7 iun. 2026
Does preservation make sense before we know how to revive?
LessWrong · 15 iun. 2026
Presentation: Building Evals for AI Adoption: from Principles to Practice
InfoQ · 29 mai 2026
Microsoft’s AI chief says superintelligence is near, but won’t take your job
The Verge · 8 iun. 2026