{
  "abstract": "Purpose: Keratitis can be classified as infectious or noninfectious, with infectious keratitis being a major cause of blindness. In this study, multiple deep learning (DL) models were applied to perform six-class classification of corneal lesions, and their diagnostic performance was systematically compared.\n\nMethods: We analyzed 3797 slit-lamp images from six categories: normal cornea, bacterial keratitis, fungal keratitis, viral keratitis, Acanthamoeba keratitis, and non-infectious keratitis. Convolutional neural network (CNN), transformer, self-supervised, and vision–language models were evaluated at image and patient levels using patient-level splits, with clinician comparison on a 240-image test subset.\n\nResults: RegNet had the best image-level performance (accuracy, 76.8%; macro-F1 score, 75.7%; macro-AUC, 0.946), and EfficientNet_B0 had the highest patient-level accuracy (77.5%; macro-F1 score, 76.6%; macro-AUC, 0.954). On the same 240-image subset, RegNet accuracy was 75.4% versus 72.7%, 56.3%, and 44.4% for senior corneal specialists, junior corneal specialists, and junior general ophthalmologists.\n\nConclusions: CNN-based models showed stable performance under the present image-based evaluation pipeline. RegNet achieved the most balanced image-level results, whereas EfficientNet_B0 showed the strongest patient-level performance. On the same 240-image subset, RegNet showed numerically higher accuracy than clinician-group means. However, performance remains insufficient for autonomous diagnosis and requires external and prospective validation.\n\nTranslational Relevance: This comparative DL framework could serve as an adjunctive image-based decision-support tool for six-class keratitis classification after further external and prospective validation, which may assist clinicians in early diagnosis and improve decision making in clinical management.",
  "abstract_shown": true,
  "affiliations": [
    "School of Future Technology, South China University of Technology, Guangzhou, China",
    "Department of Ophthalmology, Eye Hospital, Nanjing Medical University, Nanjing, China",
    "Beijing Institute of Ophthalmology, Beijing Tongren Eye Center, Beijing Tongren Hospital, Capital Medical University, Beijing, China",
    "Pazhou Lab, Guangzhou, China",
    "Shenzhen Eye Hospital, Shenzhen Eye Medical Center, Southern Medical University, Shenzhen, China"
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Qian Tan",
      "orcid": "0009-0001-8774-2319"
    },
    {
      "affs": [
        1
      ],
      "name": "Yingnan Xu"
    },
    {
      "affs": [
        2
      ],
      "name": "Yang Zhang"
    },
    {
      "affs": [
        0
      ],
      "name": "Yuning Wang"
    },
    {
      "affs": [
        0,
        3
      ],
      "name": "Yanwu Xu"
    },
    {
      "affs": [
        4
      ],
      "name": "Weihua Yang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/5zt9a42x3ts3k.bib",
  "cited_by": 0,
  "doi": "10.1167/tvst.15.10.30",
  "fulltext_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13712376/",
  "id": "5zt9a42x3ts3k",
  "issns": [
    "2164-2591"
  ],
  "landing_url": "https://doi.org/10.1167/tvst.15.10.30",
  "language": "en",
  "licence": "CC-BY-NC-ND-4.0",
  "licence_label": "CC BY-NC-ND 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "Artificial Intelligence"
    ],
    [
      "openalex",
      "2731|Ocular Infections and Treatments"
    ]
  ],
  "openalex": "W7223083156",
  "pdf_url": null,
  "pmcid": "PMC13712376",
  "pmid": "42904876",
  "published": "2026-10-21",
  "publisher": "Association for Research in Vision and Ophthalmology",
  "ris": "https://research.draconitic.com/paper/5zt9a42x3ts3k.ris",
  "sources": [
    {
      "first_seen": "2026-10-31T12:22:58Z",
      "native_id": "PMC13712376",
      "source": "pmc",
      "url": "https://doi.org/10.1167/tvst.15.10.30"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2731|Ocular Infections and Treatments",
      "subfield": "general"
    }
  ],
  "title": "Comparative Evaluation of Multiple Deep Learning Models for Six-Class Keratitis Classification",
  "title_text": "Comparative Evaluation of Multiple Deep Learning Models for Six-Class Keratitis Classification",
  "type": "peer-reviewed",
  "updated_at": "2026-10-31T12:22:58Z",
  "url": "https://research.draconitic.com/paper/5zt9a42x3ts3k",
  "venue": "Translational Vision Science & Technology",
  "versions": []
}