EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY 4.0

Comparative analysis of CNN, Transformer, and Mamba-based models for automated eye disease classification from fundus images

Md Ahanaf Arif Khan iD, Sangeeta Biswas iD

PLOS One · 2026

DOI: 10.1371/journal.pone.0360171 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift PLOS One, 2026. Verfasst von Md Ahanaf Arif Khan und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Engineering, Faculty of Engineering, University of Rajshahi, Rajshahi, Bangladesh. Hauptthemen laut MEDLINE: Fundus Oculi, Eye Diseases, Image Processing, Computer-Assisted. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We present a comparative analysis of six models belonging to Convolutional Neural Network (CNN), Transformer, and Mamba families for automated eye disease classification from fundus images under identical experimental conditions. To the best of our knowledge, our work is the first to explore Mamba-based models for automated multi-class eye disease classification from color fundus images. Our analysis suggests that, when evaluated fairly, modern CNN, Transformer, and Mamba-based models provide similar performance for eye disease classification on the Eye Disease Image Dataset (EDID). Along with analyzing individual model performance, we further evaluate performance using a logit-level ensemble of the top three models. The ensemble results imply that these model families capture partially complementary visual features, resulting in a slight performance gain when combined. In both cases, class-wise performance examination indicates that diseases with distinctive structural characteristics are recognized more consistently, while categories with subtle or overlapping features remain challenging. Our implementation, including the training and evaluation pipelines as well as the data splits, is publicly available at https://github.com/ahanaf019/EyeDisease2026 .

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Fundus OculiEye DiseasesImage Processing, Computer-AssistedConvolutional Neural NetworksHumansAlgorithmsNeural Networks, Computer

Autor:innen und Institutionen

  • Department of Computer Science and Engineering, Faculty of Engineering, University of Rajshahi, Rajshahi, Bangladesh.

ORCID-Profile: Md Ahanaf Arif Khan, Sangeeta Biswas

Zitieren

APA

Khan, M. A. A., & Biswas, S. (2026). Comparative analysis of CNN, Transformer, and Mamba-based models for automated eye disease classification from fundus images. PLOS One. https://doi.org/10.1371/journal.pone.0360171

Vancouver

Khan MAA, Biswas S. Comparative analysis of CNN, Transformer, and Mamba-based models for automated eye disease classification from fundus images. PLOS One. 2026. doi:10.1371/journal.pone.0360171

BibTeX
@article{Khan2026,
  author = {Khan, Md Ahanaf Arif and Biswas, Sangeeta},
  title = {Comparative analysis of CNN, Transformer, and Mamba-based models for automated eye disease classification from fundus images},
  journal = {PLOS One},
  year = {2026},
  doi = {10.1371/journal.pone.0360171}
}
Kostenlos starten →