{
  "abstract": "Pathologists examine tissue sections across multiple magnifications and slides, integrating morphological information to establish a diagnosis. In contrast, most pathology foundation models encode thousands of image patches from a single representative (\"best\") slide and aggregate their features, limiting multiscale and patient-level contextual integration. Here we introduce WILSON, a vision-language foundation model that represents whole-slide images and multi-slide cases through multi-magnification composites. Trained on approximately 189,000 slides spanning 42 organs and 838 diagnostic entities, WILSON enables patient-level analysis, multimodal retrieval and diagnostic text generation. Without task-specific training, WILSON outperformed a dedicated case-level model (macro-F1, 0.52 versus 0.38) and matched substantially larger slide-level models while requiring 400-1,350 times fewer computational operations. End-to-end fine-tuning improved breast cancer subtyping and stromal lymphocyte grading. WILSON also surpassed PRISM in image-text retrieval (recall@1, 75.6% versus 58.1%) and generated diagnostic descriptions that received higher ratings from five board-certified pathologists than competing models. These findings demonstrate that compact, multiscale representations can support computationally efficient, clinically grounded pathology foundation models.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.25123",
  "author_total": 20,
  "authors": [
    {
      "name": "Saghir Alfasly"
    },
    {
      "name": "Wataru Uegami"
    },
    {
      "name": "Sobhan Hemati"
    },
    {
      "name": "Wenchao Han"
    },
    {
      "name": "Xiaojia Tang"
    },
    {
      "name": "Kevin Thompson"
    },
    {
      "name": "Daniel Stone"
    },
    {
      "name": "Ghazal Alabtah"
    },
    {
      "name": "Chris Hartley"
    },
    {
      "name": "Chady Meroueh"
    },
    {
      "name": "John C. Cheville"
    },
    {
      "name": "Thomas J. Flotte"
    },
    {
      "name": "Saba Yasir"
    },
    {
      "name": "Michael R. Lucas"
    },
    {
      "name": "Eric W. Klee"
    },
    {
      "name": "Cheryl L. Willman"
    },
    {
      "name": "Judy C. Boughey"
    },
    {
      "name": "Matthew P. Goetz"
    },
    {
      "name": "Krishna R. Kalari"
    },
    {
      "name": "H. R. Tizhoosh"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/ay3dwabeaeg91.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.25123",
  "fulltext_url": null,
  "id": "ay3dwabeaeg91",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.25123",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "cs.CV"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "eess.IV"
    ],
    [
      "arxiv",
      "q-bio.QM"
    ],
    [
      "openalex",
      "1702|AI in cancer detection"
    ]
  ],
  "openalex": "W7214103582",
  "pdf_url": "https://arxiv.org/pdf/2609.25123",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-18",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/ay3dwabeaeg91.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:31:01Z",
      "native_id": "2609.25123",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.25123"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.QM",
      "subfield": "bioinformatics"
    }
  ],
  "title": "WILSON - Multi-magnification composites as a foundation for patient-level pathology analysis and diagnostic text generation",
  "title_text": "WILSON - Multi-magnification composites as a foundation for patient-level pathology analysis and diagnostic text generation",
  "type": "preprint",
  "updated_at": "2026-10-30T12:33:50Z",
  "url": "https://research.draconitic.com/paper/ay3dwabeaeg91",
  "venue": "arXiv",
  "versions": []
}