EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automated Multi-Class Diabetic Retinopathy Classification Using EfficientNet-B2 Based on Color Fundus Images

Abdulrahman Abbas Mukhlif, Oana Geman, Omar Al-Boridi

Journal of Artificial Intelligence in Medical Applications · 2025

DOI: 10.65511/jaima.v1i1.733 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Artificial Intelligence in Medical Applications, 2025. Verfasst von Abdulrahman Abbas Mukhlif und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Diabetic retinopathy (DR) is a leading cause of vision loss worldwide, and early detection is crucial to prevent irreversible blindness. This study aims to develop an effective deep learning framework for the automated multi-class classification of DR severity using color fundus images. We adopt EfficientNet-B2 as the backbone architecture, pre-trained on ImageNet and fine-tuned under various configurations to identify the optimal number of trainable layers. A customized preprocessing pipeline was introduced, incorporating median filtering, contrast enhancement using CLAHE, and circular cropping to emphasize retinal features while removing irrelevant background. To address class imbalance, aggressive data augmentation techniques were applied, resulting in a balanced dataset of 26,000 images across five DR stages. The model was trained and evaluated on a stratified 70:10:20 split of training, validation, and test sets. Among the fine-tuning strategies tested, unfreezing the last 100 layers of EfficientNet-B2 combined with the proposed preprocessing achieved the best performance, with 98.23% accuracy, 98.24% precision, 98.23% recall, and a 98.23% F1-score. These results demonstrate that targeted data preprocessing and selective fine-tuning significantly enhance classification accuracy in DR screening. The results confirm that combining tailored preprocessing with fine-tuned EfficientNet-B2 enables accurate and efficient multi-class DR classification. This framework offers strong potential for reliable, scalable deployment in clinical screening systems.

Zitieren

APA

Mukhlif, A. A., Geman, O., & Al-Boridi, O. (2025). Automated Multi-Class Diabetic Retinopathy Classification Using EfficientNet-B2 Based on Color Fundus Images. Journal of Artificial Intelligence in Medical Applications. https://doi.org/10.65511/jaima.v1i1.733

Vancouver

Mukhlif AA, Geman O, Al-Boridi O. Automated Multi-Class Diabetic Retinopathy Classification Using EfficientNet-B2 Based on Color Fundus Images. Journal of Artificial Intelligence in Medical Applications. 2025. doi:10.65511/jaima.v1i1.733

BibTeX
@article{Mukhlif2025,
  author = {Mukhlif, Abdulrahman Abbas and Geman, Oana and Al-Boridi, Omar},
  title = {Automated Multi-Class Diabetic Retinopathy Classification Using EfficientNet-B2 Based on Color Fundus Images},
  journal = {Journal of Artificial Intelligence in Medical Applications},
  year = {2025},
  doi = {10.65511/jaima.v1i1.733}
}
Kostenlos starten →