Metraipolis › archive › dc_ca3107dd82ec

With foundation-model features, aggregator complexity does not improve cross-hospital discrimination in gastric whole-slide image classification — arXiv:2610.41328

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41328
License (as archived)
CC0-1.0
Archived
2026-11-03T07:33:14.206Z
SHA-256 of the archived text
5cfdef6642132427b2b3291edd6d964f61e2169ef5c228c08640780e813882b2
Stable URL of this page
https://metraipolis.com/documento/dc_ca3107dd82ec

How to cite

With foundation-model features, aggregator complexity does not improve cross-hospital discrimination in gastric whole-slide image classification — arXiv:2610.41328 — arXiv (en), https://arxiv.org/abs/2610.41328 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ca3107dd82ec (Metraipolis archive dc_ca3107dd82ec, sha256 5cfdef6642132427b2b3291edd6d964f61e2169ef5c228c08640780e813882b2)
BibTeX
@misc{dcca3107dd82ec,
  title = {With foundation-model features, aggregator complexity does not improve cross-hospital discrimination in gastric whole-slide image classification — arXiv:2610.41328},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41328},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ca3107dd82ec; sha256 5cfdef6642132427b2b3291edd6d964f61e2169ef5c228c08640780e813882b2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41328. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Whole-slide image classifiers are usually developed within one hospital and often go untested at unseen hospitals. We assembled 5,036 haematoxylin-and-eosin-stained gastric slides from five Korean hospitals, scanned at 20x and 40x, and compared multiple-instance learning aggregators under leave-one-hospital-out validation on frozen pathology foundation-model features. A hierarchical patch-region-slide graph aggregator (CHIME-MIL) with site alignment and two-scale fusion reached a mean area under the receiver operating characteristic curve (AUC) of 0.837, above six conventional attention and transformer aggregators trained without these steps. Under a matched recipe it did not exceed attention-based pooling, and global max pooling given the same alignment and fusion was better (AUC 0.855, P = 0.0002). The alignment, which subtracts each hospital's mean feature vector without labels, onboarded a new hospital from ten unlabelled slides and cost 0.002 AUC without held-out-hospital data, but its accuracy gains were small and inconsistent. The model had low top-label calibration error (0.053) but under-confident malignancy probabilities, and removing its most-attended patches lowered the malignancy probability far more than removing random patches. With these features, more complex aggregators did not improve discrimination; what a deployable system adds is label-free onboarding, calibration checks and auditable evidence.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Image and Video Processing (eess.IV) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.41328 — 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 2026-11-03T07:29:33.721Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).