{
  "abstract": "Cervical cytology screening relies on the visual assessment of nuclear and cellular morphology across thousands of cells per slide, a labor-intensive task that could benefit from quantitative computational support. Here we present CytoLens, a modular deep learning system that detects and counts nuclei, delineates nuclei and whole cells, measures the nuclear-to-cell area ratio (N:C), classifies cells from multifocal images and scores candidate abnormality. We trained and tested each module on a public dataset matched to its task, without pooling datasets. CytoLens detected nuclei with an F1 score of 0.931 (95% confidence interval (CI), 0.914-0.946) and counted 75 of 100 fields to within one nucleus. Point-prompted segmentation achieved mean Dice coefficients of 0.901 for nuclei and 0.847 for whole cells and, without retraining, transferred to a second dataset in which measured N:C increased with lesion grade in parallel with expert outlines. Multifocal hierarchical classification reached a mean accuracy of 0.947 across four Bethesda-aligned categories, and abnormality scores ranked annotated abnormal candidates with an area under the receiver operating characteristic curve (AUROC) of 0.865. These results support the evaluation of CytoLens on patient-linked clinical specimens.",
  "abstract_shown": true,
  "affiliations": [
    "Ulsan National Institute of Science and Technology (UNIST), Ulsan, Republic of Korea"
  ],
  "article_type": "PUBLISHAHEADOFPRINT",
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "K. Lee"
    },
    {
      "name": "R. J. Yoon"
    },
    {
      "affs": [
        0
      ],
      "name": "R. S. Lee"
    },
    {
      "affs": [
        0
      ],
      "name": "D. Lee"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/a546e3317x2mb.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.13.26365471",
  "fulltext_url": "https://www.medrxiv.org/content/10.64898/2026.10.13.26365471v1.full",
  "id": "a546e3317x2mb",
  "issns": [],
  "landing_url": "https://www.medrxiv.org/content/10.64898/2026.10.13.26365471v1",
  "language": null,
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "medrxiv",
      "pathology"
    ],
    [
      "openalex",
      "1702|AI in cancer detection"
    ]
  ],
  "openalex": "W7222209648",
  "pdf_url": "https://www.medrxiv.org/content/10.64898/2026.10.13.26365471v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-13",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/a546e3317x2mb.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:20:58Z",
      "native_id": "10.64898/2026.10.13.26365471",
      "source": "medrxiv",
      "url": "https://www.medrxiv.org/content/10.64898/2026.10.13.26365471v1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "medrxiv:pathology",
      "subfield": "general"
    }
  ],
  "title": "CytoLens: a modular deep learning system for quantitative cervical cytology",
  "title_text": "CytoLens: a modular deep learning system for quantitative cervical cytology",
  "type": "preprint",
  "updated_at": "2026-10-30T12:20:58Z",
  "url": "https://research.draconitic.com/paper/a546e3317x2mb",
  "venue": "medRxiv",
  "versions": []
}