Deep Learning-Based Multi-Class Classification Approach for Diabetic Eye Diseases

Authors

• Ruqaia Jawd, Department of Informatics Systems Management (ISM), College of Business Informatics, University of Information Technology and Communications, Baghdad, IraqFollow
• Arwa Alqudsi, College of Computer Sciences and Information Technology, University of Anbar, Ramadi, IraqFollow
• Ahmad Sabah, Department of Business Information Technology (BIT), College of Business Informatics, University of Information Technology and Communications, Baghdad, IraqFollow
• Huda Kadhim, Department of Informatics Systems Management (ISM), College of Business Informatics, University of Information Technology and Communications, Baghdad, IraqFollow
• Raja Kadhim, Department of Informatics Systems Management (ISM), College of Business Informatics, University of Information Technology and Communications, Baghdad, IraqFollow
• Hasanain Jalil, Department of Business Information Technology (BIT), College of Business Informatics, University of Information Technology and Communications, Baghdad, Iraq

Corresponding Author

Arwa Alqudsi

Authors ORCID

Ruqaia Jawd: https://orcid.org/0000-0001-8667-2825

Arwa Alqudsi: https://orcid.org/0000-0002-1487-9285

Ahmad Sabah: https://orcid.org/0000-0002-3443-0725

Huda Kadhim: https://orcid.org/0000-0003-2484-1675

Raja Kadhim: https://orcid.org/0000-0002-0231-4113

Hasanain Jalil: https://orcid.org/0009-0009-8128-3068

Document Type

Article

Keywords

Diabetic retinopathy, Cataract, Glaucoma, Deep learning, Convolutional neural networks, Transfer learning

Abstract

Diabetes-related eye diseases are the leading cause of blindness amongst working-age individuals and represent a serious global health concern. Early detection is essential to prevent vision loss. However, current screening techniques face limitations in scalability and accessibility. A deep learning (DL) method for automatically classifying retinal images into four groups—diabetic retinopathy, normal, glaucoma and cataract—is presented in this work. We developed and assessed a convolutional neural network (CNN) model using transfer learning (TL) with EfficientNetB3 as the foundational architecture, utilising a diverse dataset of over 4,000 retinal images collected from various sources. Our model achieved an overall accuracy of 91.3%, with class-specific sensitivities ranging from 87.6% to 94.2% and specificities from 92.1% to 95.8%. The proposed approach focuses on clinically relevant regions for decision-making. This automated approach could significantly enhance early detection capabilities, especially in resource-limited settings and complement existing ophthalmological services to reduce the burden of preventable blindness.

How to Cite This Article

Jawd, Ruqaia; Alqudsi, Arwa; Sabah, Ahmad; Kadhim, Huda; Kadhim, Raja; and Jalil, Hasanain (2026) "Deep Learning-Based Multi-Class Classification Approach for Diabetic Eye Diseases," Mesopotamian Journal of Big Data: Vol. 6: Iss. 1, Article 7.
Available at: https://map.researchcommons.org/mjbd/vol6/iss1/7