Open Access iconOpen Access

ARTICLE

crossmark

Deep Learning Empowered Diagnosis of Diabetic Retinopathy

by Mustafa Youldash1, Atta Rahman2,*, Manar Alsayed1, Abrar Sebiany1, Joury Alzayat1, Noor Aljishi1, Ghaida Alshammari1, Mona Alqahtani1

1 Department of Computer Engineering, College of Computer Science and Information Technology, Imam Abdulrahman Bin Faisal University, P.O. Box 1982, Dammam, 31441, Saudi Arabia
2 Department of Computer Science, College of Computer Science and Information Technology, Imam Abdulrahman Bin Faisal University, P.O. Box 1982, Dammam, 31441, Saudi Arabia

* Corresponding Author: Atta Rahman. Email: email

Intelligent Automation & Soft Computing 2025, 40, 125-143. https://doi.org/10.32604/iasc.2025.058509

Abstract

Diabetic retinopathy (DR) is a complication of diabetes that can lead to reduced vision or even blindness if left untreated. Therefore, early and accurate detection of this disease is crucial for diabetic patients to prevent vision loss. This study aims to develop a deep-learning approach for the early and precise diagnosis of DR, as manual detection can be time-consuming, costly, and prone to human error. The classification task is divided into two groups for binary classification: patients with DR (diagnoses 1–4) and those without DR (diagnosis 0). For multi-class classification, the categories are no DR, mild DR, moderate DR, severe DR, and proliferative diabetic retinopathy (PDR). To achieve this, the proposed model utilizes two pre-trained convolutional neural networks (CNNs), specifically ResNet50 and DenseNet-121. Both models were trained and evaluated on fundus images sourced from the widely recognized APTOS dataset, a publicly available resource., and achieved impressive training and testing accuracies. For binary classification, DenseNet-121 achieved an accuracy of 98.1%, while ResNet50 attained an accuracy of 97.4%. In multi-class classification for DR, DenseNet-121 achieved an accuracy of 82.0%, and ResNet50 reached an accuracy of 80.8%. The results are promising and comparable to state-of-the-art techniques in the literature for both binary and multi-label classification of DR.

Keywords


Cite This Article

APA Style
Youldash, M., Rahman, A., Alsayed, M., Sebiany, A., Alzayat, J. et al. (2025). Deep learning empowered diagnosis of diabetic retinopathy. Intelligent Automation & Soft Computing, 40(1), 125–143. https://doi.org/10.32604/iasc.2025.058509
Vancouver Style
Youldash M, Rahman A, Alsayed M, Sebiany A, Alzayat J, Aljishi N, et al. Deep learning empowered diagnosis of diabetic retinopathy. Intell Automat Soft Comput. 2025;40(1):125–143. https://doi.org/10.32604/iasc.2025.058509
IEEE Style
M. Youldash et al., “Deep Learning Empowered Diagnosis of Diabetic Retinopathy,” Intell. Automat. Soft Comput., vol. 40, no. 1, pp. 125–143, 2025. https://doi.org/10.32604/iasc.2025.058509



cc Copyright © 2025 The Author(s). Published by Tech Science Press.
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 297

    View

  • 80

    Download

  • 0

    Like

Share Link