Metraipolis › archive › dc_c8a278376461
WILSON - a pathology foundation model framework for patient-level analysis and diagnostic text generation — arXiv:2609.25123
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.25123
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T13:46:05.339Z
- SHA-256 of the archived text
77f92d088b1905dd6634d59a3c0f5cd195c858423c089ebe38717a6d437c8abd- Stable URL of this page
https://metraipolis.com/documento/dc_c8a278376461
How to cite
WILSON - a pathology foundation model framework for patient-level analysis and diagnostic text generation — arXiv:2609.25123 — arXiv (en), https://arxiv.org/abs/2609.25123 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c8a278376461 (Metraipolis archive dc_c8a278376461, sha256 77f92d088b1905dd6634d59a3c0f5cd195c858423c089ebe38717a6d437c8abd)
BibTeX
@misc{dcc8a278376461,
title = {WILSON - a pathology foundation model framework for patient-level analysis and diagnostic text generation — arXiv:2609.25123},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.25123},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c8a278376461; sha256 77f92d088b1905dd6634d59a3c0f5cd195c858423c089ebe38717a6d437c8abd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25123. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Pathologists integrate morphology across magnifications and across the slides of a patient case, whereas pathology foundation models encode thousands of tiles from single slides and aggregate their features. Here we present WILSON, a vision--language foundation model that represents whole-slide images and multi-slide cases as single multi-magnification composite images, trained on approximately 189k slides from Mayo Clinic spanning 42 organs and 829 diagnostic entities using pathology reports as supervision. Without task-specific training, WILSON exceeded a dedicated case-level model on all internal cohorts (macro-F1 0.52 versus 0.38) and matched slide-level models up to 9.4 times larger at 272- to 2,155-fold lower compute. End-to-end fine-tuning on 508 triple-negative breast cancer cases improved histologic subtyping and stromal tumor-infiltrating lymphocyte grading by 0.16 and 0.11 macro-F1. WILSON retrieved matching diagnostic text at 75.6% recall@1 (PRISM, 58.1%) and generated captions closer to report-derived references than PRISM and PRISM2 on the internal cohort and on most external comparisons. Composite images thus offer a compact, clinically aligned computational unit for pathology. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.AI). Categorie arXiv: Quantitative Methods (q-bio.QM) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Image and Video Processing (eess.IV). Pagina del lavoro: https://arxiv.org/abs/2609.25123 — 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 2026-10-08T13:18:38.200Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).