跳到正文
原文
Nature 健康护理主题·· 26 天前AI 评分43

一拍即合合成罕见胃肠道病变:提升诊断准确性和临床培训

One-shot synthesis of rare gastrointestinal lesions improves diagnostic accuracy and clinical training

AI 导读

EndoRare 一拍即合合成罕见胃肠道病变,在四种罕见病中验证,专家认为其临床合理。数据增强显著提升AI分类器真阳性率,同时新手内镜医生在探索性研究中识别能力提高。该框架或为罕见病变教育提供高效工具,需进一步控制验证

正文

Nature Communications (2026) Cite this article

We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.

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.

Acknowledgements

The computations were performed using the CFFF platform of Fudan University.

Funding

S.W. discloses support for the research of this work from the National Key Research and Development Program of China [2024YFF1207500], National Natural Science Foundation of China [62501166], and Shanghai QiYuan Innovation Foundation.

Author information

Author notes

  1. These authors contributed equally: Jia Yu, Yan Zhu, Peiyao Fu.

Authors and Affiliations

  1. Digital Medical Research Center, School of Basic Medical Sciences, Fudan University, Shanghai, China

    Jia Yu & Shuo Wang

  2. Shanghai Institute for Advanced Study of Zhejiang University, Shanghai, China

    Jia Yu, Zhihua Wang & Fei Wu

  3. Shanghai Collaborative Innovation Center of Endoscopy, Shanghai, China

    Jia Yu, Yan Zhu, Peiyao Fu, Tianyi Chen, Quanlin Li, Pinghong Zhou & Shuo Wang

  4. Shanghai Key Laboratory of MICCAI, Shanghai, China

    Jia Yu & Shuo Wang

  5. Endoscopy Centre and Endoscopy Research Institute, Zhongshan Hospital, Fudan University, Shanghai, China

    Yan Zhu, Peiyao Fu, Quanlin Li & Pinghong Zhou

  6. Zhejiang University, Hangzhou, China

    Zhihua Wang & Fei Wu

  7. Data Science Institute, Imperial College London, London, UK

    Shuo Wang

  8. Centre for AI and Decision Sciences, Alliance Manchester Business School, The University of Manchester, Manchester, UK

    Xian Yang

Authors

  1. Jia Yu
  2. Yan Zhu
  3. Peiyao Fu
  4. Tianyi Chen
  5. Zhihua Wang
  6. Fei Wu
  7. Quanlin Li
  8. Pinghong Zhou
  9. Shuo Wang
  10. Xian Yang

Corresponding authors

Correspondence to Pinghong Zhou, Shuo Wang or Xian Yang.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yu, J., Zhu, Y., Fu, P. et al. One-shot synthesis of rare gastrointestinal lesions improves diagnostic accuracy and clinical training. Nat Commun (2026). https://doi.org/10.1038/s41467-026-78492-y

Download citation

  • Received: 01 January 2026

  • Accepted: 22 September 2026

  • Published: 25 October 2026

  • DOI: https://doi.org/10.1038/s41467-026-78492-y

来源:Nature 健康护理主题 · nature.com