Metraipolis › archive › dc_7fc8b19bd00c

Do Center Biases Propagate? Robustness of Pathology Foundation Models in Whole-Slide Image Classification — arXiv:2609.28231

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.28231
License (as archived)
CC0-1.0
Archived
2026-10-08T09:13:25.799Z
SHA-256 of the archived text
ae7926886872176d2959e52da3182b56541ba6ca2a5477c770bf392d309715f4
Stable URL of this page
https://metraipolis.com/documento/dc_7fc8b19bd00c

How to cite

Do Center Biases Propagate? Robustness of Pathology Foundation Models in Whole-Slide Image Classification — arXiv:2609.28231 — arXiv (en), https://arxiv.org/abs/2609.28231 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7fc8b19bd00c (Metraipolis archive dc_7fc8b19bd00c, sha256 ae7926886872176d2959e52da3182b56541ba6ca2a5477c770bf392d309715f4)
BibTeX
@misc{dc7fc8b19bd00c,
  title = {Do Center Biases Propagate? Robustness of Pathology Foundation Models in Whole-Slide Image Classification — arXiv:2609.28231},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.28231},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7fc8b19bd00c; sha256 ae7926886872176d2959e52da3182b56541ba6ca2a5477c770bf392d309715f4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28231. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.28231 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T08:13:26.758Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).