{
  "abstract": "Background/Objectives: Retinal fundus photography is the most widely available means of screening for sight-threatening disease, but it is difficult to read: several conditions leave overlapping signs on the same photograph, the features that separate them are often subtle and confined to small regions of the retina, and a single image carries no systemic context, so an automated reader must resolve categories on which experienced clinicians themselves agree only moderately. Methods: We compared five deep learning architectures-EfficientNet-B3, DenseNet-121, ViT-Base/16, Inception-V3, and RETFound ViT-Large-for simultaneous seven-class retinal disease classification on a multi-source fundus image benchmark, in a retrospective computational study using stratified five-fold cross-validation. We pooled 11,223 patient-eye fundus images from three publicly available, de-identified datasets (ODIR-5K, RFMiD, and APTOS 2019) spanning age-related macular degeneration (AMD), cataract, diabetic retinopathy (DR), glaucoma, hypertensive retinopathy, pathological myopia, and normal fundus; the cohort was markedly class-imbalanced (DR, 62.5%; normal, 25.6%; each remaining class < 3%), and no new patient data were collected. Images were deduplicated by MD5 hash and split at the patient level to eliminate data leakage, with a fixed 15% held-out test set and five stratified cross-validation folds; training images received Ben Graham illumination normalization and class-balancing augmentation, while validation and test images were unaugmented. Three ImageNet-pretrained CNNs (EfficientNet-B3, DenseNet-121, Inception-V3), ViT-Base/16, and RETFound ViT-Large (pretrained on 1.6 million retinal photographs via masked autoencoding) were trained; the primary outcome was the five-fold mean weighted-averaged F1 score, pairwise comparisons used paired t-tests on fold-level F1 (df= 4), and Grad-CAM was applied for explainability. Results: EfficientNet-B3 achieved the highest five-fold mean accuracy (95.53%; weighted-F1, 0.9507) and significantly outperformed RETFound ViT-Large (ΔF1=+0.0255; t=9.70; p<0.001), ViT-Base/16 (ΔF1=+0.0075; t=9.20; p<0.001), and Inception-V3 (ΔF1=+0.0103; t=8.38; p<0.001), while performing comparably to DenseNet-121 (t=2.24; p=0.089); Grad-CAM showed clinically plausible activation localization for the CNN architectures. Conclusions: A compact, resource-efficient CNN thus matched or exceeded a substantially larger retinal foundation model and Vision Transformers, indicating that larger domain-specific foundation models are not inherently superior for heterogeneous retinal screening; because such compact models run on commodity hardware, they may offer more practical screening solutions for community, rural, and resource-limited settings where ophthalmologist coverage is scarcest. External validity across imaging sources and populations remains unproven, underscoring that prospective, multicenter validation must precede clinical deployment. A provenance audit of this pooled cohort subsequently found it confounded. The audit identified five failure modes, three of them decisive: image width alone reproduced the diabetic retinopathy label at 99.98% accuracy using no retinal pixels, source and label were almost perfectly dependent with a Cramér's V of 0.9996, and diabetic retinopathy recall was exactly 1.0000 for all five architectures. The cohort was rebuilt from a single source with per-eye labels, and nine architectures were retrained under one protocol with external validation. The corrected headline is a macro-AUC of 0.930 internally and 0.978 externally, with a macro-F1 of 0.686. No architecture is declared superior, and the pooled-cohort conclusion does not stand.",
  "abstract_shown": true,
  "affiliations": [
    "College of Computer Science and Engineering, University of Ha'il, Ha'il 81411, Saudi Arabia."
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 2,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Majid Alutaibi"
    },
    {
      "affs": [
        0
      ],
      "name": "Meshari Alazmi",
      "orcid": "0000-0001-9074-1029"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/49awvpzhc0830.bib",
  "cited_by": 0,
  "doi": "10.3390/diagnostics16193109",
  "fulltext_url": "https://europepmc.org/articles/PMC13664116",
  "id": "49awvpzhc0830",
  "issns": [
    "2075-4418"
  ],
  "landing_url": "https://europepmc.org/article/MED/42882265",
  "language": "eng",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2741|Retinal Imaging and Analysis"
    ]
  ],
  "openalex": "W7214150997",
  "pdf_url": "https://europepmc.org/articles/PMC13664116?pdf=render",
  "pmcid": "PMC13664116",
  "pmid": "42882265",
  "published": "2026-09-24",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/49awvpzhc0830.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:19:16Z",
      "native_id": "MED:42882265",
      "source": "europepmc",
      "url": "https://europepmc.org/article/MED/42882265"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2741|Retinal Imaging and Analysis",
      "subfield": "imaging"
    }
  ],
  "title": "Comparative Evaluation of EfficientNet-B3, Vision Transformers, and RETFound for Seven-Category Retinopathy Fundus Image Classification.",
  "title_text": "Comparative Evaluation of EfficientNet-B3, Vision Transformers, and RETFound for Seven-Category Retinopathy Fundus Image Classification.",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:19:16Z",
  "url": "https://research.draconitic.com/paper/49awvpzhc0830",
  "venue": "Diagnostics (Basel, Switzerland)",
  "versions": []
}