{
  "abstract": "Automated whole-slide image (WSI) analysis for cervical squamous cell carcinoma (CSCC) is challenged by limited pathological specificity in general models and poor cross-center generalization. We propose CSCC-PAG (pre-training, adaptation, generalization), a framework integrating domain-specific pre-training with self-supervised domain adaptation. Utilizing 8,041 CSCC WSIs, we applied the self-supervised pre-training for CSCC (SPC) feature extractor, which significantly outperforms pan-cancer baselines in the typing, grading, and segmentation tasks. To address domain shift, we developed representative sample domain adaptation (RSDA), combining masked autoencoders (MAEs) with a k-means buffer strategy for label-free adaptation. The results demonstrate that SPC captures fine-grained CSCC morphology, while RSDA effectively recovers performance degradation across centers without requiring target-domain annotations. This study provides a comprehensive solution for automated CSCC diagnosis, covering the entire pipeline from large-scale pre-training to few-shot generalized deployment, demonstrating its immense potential for real-world clinical implementation.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": "Article",
  "arxiv": null,
  "author_total": 18,
  "authors": [
    {
      "name": "Zirui Huang",
      "orcid": "0009-0001-2816-8134"
    },
    {
      "name": "Ye Liu"
    },
    {
      "name": "Saihui Jin"
    },
    {
      "name": "Yizhi Wang"
    },
    {
      "name": "Mingxi Fu"
    },
    {
      "name": "Jingli Ouyang"
    },
    {
      "name": "Deshui Yu"
    },
    {
      "name": "Taojie Zhu"
    },
    {
      "name": "Fanyi Zeng"
    },
    {
      "name": "Xinyi Pan"
    },
    {
      "name": "Jiatong Ye"
    },
    {
      "name": "Juanjuan Wang"
    },
    {
      "name": "Xiaobo He"
    },
    {
      "name": "Xiao Cheng"
    },
    {
      "name": "Ming Zhao"
    },
    {
      "name": "Yonghong He"
    },
    {
      "name": "Hongfeng Zhang"
    },
    {
      "name": "Bin Hu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/72vty5p6067j6.bib",
  "cited_by": 0,
  "doi": "10.1016/j.isci.2026.117744",
  "fulltext_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13696214/",
  "id": "72vty5p6067j6",
  "issns": [
    "2589-0042"
  ],
  "landing_url": "https://www.cell.com/iscience/fulltext/S2589-0042(26)03125-1",
  "language": "en",
  "licence": "CC-BY-NC-ND-4.0",
  "licence_label": "CC BY-NC-ND 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "Article"
    ],
    [
      "heading",
      "Health sciences"
    ],
    [
      "heading",
      "Internal medicine"
    ],
    [
      "heading",
      "Medicine"
    ],
    [
      "heading",
      "Oncology"
    ],
    [
      "heading",
      "Pathology"
    ],
    [
      "openalex",
      "1702|AI in cancer detection"
    ]
  ],
  "openalex": "W7222751950",
  "pdf_url": "https://europepmc.org/articles/PMC13696214?pdf=render",
  "pmcid": "PMC13696214",
  "pmid": "42935755",
  "published": "2026-10-16",
  "publisher": "Elsevier",
  "ris": "https://research.draconitic.com/paper/72vty5p6067j6.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:16Z",
      "native_id": "10.1016/j.isci.2026.117744",
      "source": "feed-cell",
      "url": "https://www.cell.com/iscience/fulltext/S2589-0042(26)03125-1"
    },
    {
      "first_seen": "2026-10-30T12:17:36Z",
      "native_id": "PMC13696214",
      "source": "pmc",
      "url": "https://doi.org/10.1016/j.isci.2026.117744"
    },
    {
      "first_seen": "2026-10-30T12:17:49Z",
      "native_id": "10.1016/j.isci.2026.117744",
      "source": "crossref",
      "url": "https://linkinghub.elsevier.com/retrieve/pii/S2589004226031251"
    },
    {
      "first_seen": "2026-10-30T12:22:12Z",
      "native_id": "MED:42935755",
      "source": "europepmc",
      "url": "https://europepmc.org/article/MED/42935755"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "heading:Oncology",
      "subfield": "oncology"
    }
  ],
  "title": "Enhancing cervical squamous cell carcinoma diagnosis under distribution shift via domain-adaptive representation learning",
  "title_text": "Enhancing cervical squamous cell carcinoma diagnosis under distribution shift via domain-adaptive representation learning",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:33:35Z",
  "url": "https://research.draconitic.com/paper/72vty5p6067j6",
  "venue": "iScience",
  "versions": []
}