跳到正文
原文
Nature 健康护理主题·· 2026-10-20AI 评分31

CTL-GAN隐私保护协同迁移学习用于干眼症分类研究

Privacy-preserving collaborative transfer learning with generative adversarial networks (CTL-GAN) for classification of dry eye disease

AI 导读

一项回顾性研究评估CTL-GAN生成合成荧光素角膜图像以提升干眼症多分类分级效果,未交换原始图像。在SMC数据集上,GAN增强使验证准确率从64.2%提升至75.5%;在SYSU数据集上,迁移预训练权重使准确率从41.4%提高至66.3%。

正文

Scientific Reports (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

This study investigated whether a collaborative transfer learning generative adversarial network (CTL-GAN) can generate synthetic fluorescein corneal images and enhance multiclass dry eye disease (DED) grading across institutions. We retrospectively included 1,600 fluorescein-stained anterior segment images from patients with DED at Samsung Medical Center (SMC) and 260 images from the public Sun Yat-sen University (SYSU) dataset, graded on the Oxford scale. A StyleGAN3 generator trained on SMC data produced synthetic images. Pretrained generator weights were transferred to a simulated site represented by the SYSU dataset and fine-tuned on local images, without exchanging raw images. DenseNet classifiers trained with GAN-based augmentation were compared with a benchmark model trained on real images only. GAN-based augmentation improved validation accuracy on SMC data from 64.2% to 75.5%, and transferring pretrained weights increased SYSU validation accuracy from 41.4% to 66.3%. Peak signal-to-noise ratio (PSNR 13.95 ± 1.54 dB), structural similarity index (SSIM 0.428 ± 0.111), and learned perceptual image patch similarity (LPIPS 0.510 ± 0.047) showed low similarity to real images. In a blinded 10-item multiple-choice realism survey, 37 ophthalmologists answered correctly in 28.4% of cases, against a 20% chance level. CTL-GAN indicates that image synthesis from shared generator weights can improve external DED grading without exchanging patient images.

Funding

This work was supported by a National Research Foundation of Korea (NRF) grant funded by the Korean government’s Ministry of Education (NRF-2021R1C1C1007795) to D.H.L., and by NRF grants (RS-2022-NR068758 and NRF-2022M3J6A1063021) and the AI Science Hub program of the Ministry of Science and ICT, Republic of Korea (N10260132), to J.J. The funders had no role in the design and conduct of the study.

Author information

Authors and Affiliations

  1. Graduate School of Future Strategy, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea

    Bongsang Kim, Hokyun Kim & Jiho Cha

  2. Department of Ophthalmology, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Irwon-ro, Gangnam-gu, 06351, Seoul, Republic of Korea

    Yeo Kyoung Won & Dong Hui Lim

  3. SNU Eye Clinic, Seoul, Republic of Korea

    Yeo Kyoung Won

  4. Samsung Advanced Institute for Health Sciences & Technology, Sungkyunkwan University, Seoul, Republic of Korea

    Dong Hui Lim

  5. Department of AI and Future Studies, College of AI, Korea Advanced Institute of Science and Technology, 291 Daehak-ro, Yuseong-gu, Daejeon, 34141, Republic of Korea

    Jooyoung Jeon

Authors

  1. Bongsang Kim
  2. Yeo Kyoung Won
  3. Hokyun Kim
  4. Jiho Cha
  5. Dong Hui Lim
  6. Jooyoung Jeon

Corresponding authors

Correspondence to Dong Hui Lim or Jooyoung Jeon.

Ethics declarations

Competing interests

The authors declare no competing interests.

Ethical statement

This study was approved by the Institutional Review Board of Samsung Medical Center (SMC 2024-11-069). Because of the retrospective nature of the study, the Institutional Review Board of Samsung Medical Center waived the requirement for informed consent. Patients and the public were not involved in the design, conduct, reporting, or dissemination plans of this research.

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

Kim, B., Won, Y.K., Kim, H. et al. Privacy-preserving collaborative transfer learning with generative adversarial networks (CTL-GAN) for classification of dry eye disease. Sci Rep (2026). https://doi.org/10.1038/s41598-026-76373-4

Download citation

  • Received: 19 June 2026

  • Accepted: 13 October 2026

  • Published: 20 October 2026

  • DOI: https://doi.org/10.1038/s41598-026-76373-4

Keywords

来源:Nature 健康护理主题 · nature.com