{
  "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.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "name": "Bongsang Kim"
    },
    {
      "name": "Yeo Kyoung Won"
    },
    {
      "name": "Hokyun Kim"
    },
    {
      "name": "Jiho Cha"
    },
    {
      "name": "Dong Hui Lim"
    },
    {
      "name": "Jooyoung Jeon"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/5zqjcgasy0rmj.bib",
  "cited_by": 0,
  "doi": "10.1038/s41598-026-76373-4",
  "fulltext_url": null,
  "id": "5zqjcgasy0rmj",
  "issns": [
    "2045-2322"
  ],
  "landing_url": "https://www.nature.com/articles/s41598-026-76373-4",
  "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",
      "2739|Ocular Surface and Contact Lens"
    ]
  ],
  "openalex": "W7223008819",
  "pdf_url": "https://www.nature.com/articles/s41598-026-76373-4_reference.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-20",
  "publisher": "Springer Science and Business Media LLC",
  "ris": "https://research.draconitic.com/paper/5zqjcgasy0rmj.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:31Z",
      "native_id": "10.1038/s41598-026-76373-4",
      "source": "crossref",
      "url": "https://www.nature.com/articles/s41598-026-76373-4"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2739|Ocular Surface and Contact Lens",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "Privacy-preserving collaborative transfer learning with generative adversarial networks (CTL-GAN) for classification of dry eye disease",
  "title_text": "Privacy-preserving collaborative transfer learning with generative adversarial networks (CTL-GAN) for classification of dry eye disease",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:17:31Z",
  "url": "https://research.draconitic.com/paper/5zqjcgasy0rmj",
  "venue": "Scientific Reports",
  "versions": []
}