{
  "abstract": "Diabetic retinopathy (DR) severity grading from retinal fundus images is challenging because retinal abnormalities vary in size, distribution, and severity. This study evaluates two hybrid architectures, ConvNeXt–MLP-Mixer and ConvNeXt–PoolFormer, for five-class DR classification by combining convolutional feature extraction with global feature mixing. Experiments used the APTOS 2019 Blindness Detection dataset from Kaggle. After exact-duplicate filtering, 3,596 images remained: 2,502 for training, 544 for validation, and 550 for held-out testing. The imbalanced test set comprised five DR severity classes. The proposed models were compared with EfficientNet, Vision Transformer, ConvNeXt, MLP-Mixer, and PoolFormer using accuracy, macro- and weighted F1-scores, and macro- and weighted-average one-versus-rest (OvR) ROC-AUC. ConvNeXt–PoolFormer achieved 82.7% test accuracy and 82.7% weighted F1-score, while ConvNeXt–MLP-Mixer achieved 82.4% accuracy and 82.5% weighted F1-score, with the latter obtaining the highest macro F1-score of 67.5%. Moderate DR showed the clearest class-specific improvement, whereas Severe and Proliferative DR remained difficult to classify. Layer-wise Relevance Propagation (LRP) and Grad-CAM generated post-hoc visual explanation maps for representative predictions. These visualizations were treated as exploratory because they were not independently validated using lesion-level annotations or by clinical experts, including ophthalmologists.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "name": "Mochammad Arya Jadmika"
    },
    {
      "name": "Aris Sugiharto"
    },
    {
      "name": "Dinar Mutiara Kusumo Nugraheni"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/3rp15e3j5nnb1.bib",
  "cited_by": 0,
  "doi": "10.63158/journalisi.v8i5.1863",
  "fulltext_url": "https://journal-isi.org/index.php/isi/article/view/1863",
  "id": "3rp15e3j5nnb1",
  "issns": [
    "2656-5935",
    "2656-4882"
  ],
  "landing_url": "https://doi.org/10.63158/journalisi.v8i5.1863",
  "language": "en",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "lcc",
      "QA1-939"
    ],
    [
      "lcc",
      "QA75.5-76.95"
    ],
    [
      "openalex",
      "2741|Retinal Imaging and Analysis"
    ]
  ],
  "openalex": "W7223351273",
  "pdf_url": "https://journal-isi.org/index.php/isi/article/download/1863/1081",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-24",
  "publisher": "Asosiasi Doktor Sistem Informasi Indonesia",
  "ris": "https://research.draconitic.com/paper/3rp15e3j5nnb1.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T13:44:44Z",
      "native_id": "34475db3f8364ad2b3464c561f91a44a",
      "source": "doaj",
      "url": "https://doi.org/10.63158/journalisi.v8i5.1863"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2741|Retinal Imaging and Analysis",
      "subfield": "imaging"
    }
  ],
  "title": "Interpretable Diabetic Retinopathy Classification Using Hybrid ConvNeXt–MLP-Mixer and ConvNeXt–PoolFormer Architectures",
  "title_text": "Interpretable Diabetic Retinopathy Classification Using Hybrid ConvNeXt–MLP-Mixer and ConvNeXt–PoolFormer Architectures",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T13:44:44Z",
  "url": "https://research.draconitic.com/paper/3rp15e3j5nnb1",
  "venue": "Journal of Information Systems and Informatics",
  "versions": []
}