{
  "abstract": "Rare gastrointestinal lesions are infrequently encountered in routine endoscopy, limiting data for developing reliable artificial intelligence (AI) models and training novice clinicians. Here we present EndoRare, a one-shot, retraining-free generative framework that synthesizes diverse lesion exemplars from a single reference image. Using language-guided concept disentanglement, EndoRare separates pathognomonic lesion features from non-diagnostic attributes, encoding the former into a learnable prototype embedding while varying the latter to ensure diversity. We validate EndoRare across four rare pathologies: calcifying fibrous tumor, juvenile polyposis syndrome, familial adenomatous polyposis, and Peutz-Jeghers syndrome. Experts judge the synthetic images clinically plausible, and data augmentation significantly improves downstream AI classifiers, increasing true positive rates at low false-positive rates. In an exploratory reader study, exposure to EndoRare-generated cases is associated with improved image-level recognition by novice endoscopists. These findings support the potential use of EndoRare as a data-efficient tool for rare-lesion education and motivate prospective controlled validation.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 10,
  "authors": [
    {
      "name": "Jia Yu",
      "orcid": "0009-0003-9135-7602"
    },
    {
      "name": "Yan Zhu"
    },
    {
      "name": "Peiyao Fu"
    },
    {
      "name": "Tianyi Chen"
    },
    {
      "name": "Zhihua Wang",
      "orcid": "0000-0002-1593-1321"
    },
    {
      "name": "Fei Wu",
      "orcid": "0000-0003-2139-8807"
    },
    {
      "name": "Quanlin Li",
      "orcid": "0000-0002-9108-8786"
    },
    {
      "name": "Pinghong Zhou",
      "orcid": "0000-0002-5434-0540"
    },
    {
      "name": "Shuo Wang",
      "orcid": "0000-0002-2947-8783"
    },
    {
      "name": "Xian Yang",
      "orcid": "0000-0002-1496-8923"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/4zcj2arsp96c4.bib",
  "cited_by": 0,
  "doi": "10.1038/s41467-026-78492-y",
  "fulltext_url": null,
  "id": "4zcj2arsp96c4",
  "issns": [
    "2041-1723"
  ],
  "landing_url": "https://www.nature.com/articles/s41467-026-78492-y",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2718|Artificial Intelligence in Healthcare and Education"
    ]
  ],
  "openalex": "W7117994713",
  "pdf_url": "https://www.nature.com/articles/s41467-026-78492-y_reference.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-25",
  "publisher": "Springer Science and Business Media LLC",
  "ris": "https://research.draconitic.com/paper/4zcj2arsp96c4.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:39Z",
      "native_id": "10.1038/s41467-026-78492-y",
      "source": "crossref",
      "url": "https://www.nature.com/articles/s41467-026-78492-y"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2718|Artificial Intelligence in Healthcare and Education",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "One-shot synthesis of rare gastrointestinal lesions improves diagnostic accuracy and clinical training",
  "title_text": "One-shot synthesis of rare gastrointestinal lesions improves diagnostic accuracy and clinical training",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:17:39Z",
  "url": "https://research.draconitic.com/paper/4zcj2arsp96c4",
  "venue": "Nature Communications",
  "versions": []
}