{
  "abstract": "Pathology foundation models provide reusable representations for computational pathology, but staining- and scanner-induced variation may compromise the robustness and reproducibility of embedding-based analyses across acquisition settings. Stain normalisation is widely used to mitigate such colour variation, yet whether it improves retrieval with modern self-supervised pathology encoders remains unclear. We test whether stain normalisation improves cross-scanner and cross-staining image retrieval using the PLISM whole-slide image subset, comprising 13 co-registered images of serial sections prepared under different staining conditions and digitised using seven scanners (91 whole-slide images). We sample 400 matched locations across the 91 images, yielding 36,400 tile instances. We compare two DINOv2-based encoders, Phikon-v2 (1,024-dimensional) and Midnight-12k (3,072-dimensional), with Reinhard and Macenko normalisation against an unnormalised baseline. Performance is measured using paired top-1 nearest-neighbour retrieval accuracy in two settings: cross-scanner retrieval of the same physical section digitised by different scanners, and cross-staining retrieval across co-registered images of serial sections, which differ in staining condition and may also contain section-level morphological variation. Neither normalisation method consistently improves top-1 retrieval relative to no normalisation, while Macenko reduces accuracy by up to 18.3 percentage points. An exploratory UMAP of unnormalised Midnight-12k slide-level mean embeddings showed partial overlap between scanner groups in a two-dimensional projection. These results challenge the routine use of stain normalisation in foundation-model retrieval pipelines and support validating preprocessing choices for each encoder and retrieval setting.",
  "abstract_shown": true,
  "affiliations": [
    "University College London"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "name": "Y. Meng"
    },
    {
      "name": "B. Chai"
    },
    {
      "affs": [
        0
      ],
      "name": "T. Chakraborti"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/69m7fnwchst9q.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.13.758918",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.10.13.758918v1.full",
  "id": "69m7fnwchst9q",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.10.13.758918v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "pathology"
    ],
    [
      "openalex",
      "1702|AI in cancer detection"
    ]
  ],
  "openalex": "W7222994822",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.10.13.758918v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-13",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/69m7fnwchst9q.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:28:40Z",
      "native_id": "10.64898/2026.10.13.758918",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.10.13.758918v1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "biorxiv:pathology",
      "subfield": "general"
    }
  ],
  "title": "Stain Normalisation Does Not Consistently Improve Matched-Location Retrieval with Pathology Foundation Models",
  "title_text": "Stain Normalisation Does Not Consistently Improve Matched-Location Retrieval with Pathology Foundation Models",
  "type": "preprint",
  "updated_at": "2026-10-30T12:28:40Z",
  "url": "https://research.draconitic.com/paper/69m7fnwchst9q",
  "venue": "bioRxiv",
  "versions": []
}