Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{191564,
        author = {shiva},
        title = {Automated Diabetic Eye Disease Diagnosis Using Deep Neural Networks},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {7024-7031},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=191564},
        abstract = {Diabetic eye diseases such as diabetic retinopathy, diabetic macular edema, cataract, and glaucoma are among the leading causes of vision impairment worldwide. Early detection of these conditions is crucial to prevent irreversible vision loss; however, traditional diagnosis relies heavily on manual examination by ophthalmologists, which is time-consuming and limited by the availability of specialists. To address this challenge, this project proposes DeepDiabetic, an automated deep learning–based system for the identification and classification of diabetic eye diseases using retinal fundus images. The system utilizes a multi-source dataset consisting of 5,899 retinal images and applies advanced deep learning models including EfficientNetB0, VGG16, ResNet152V2, and hybrid architectures integrated with GRU and BiGRU. Comprehensive preprocessing, data augmentation, and model optimization techniques are employed to improve accuracy and generalization. Experimental evaluation shows that EfficientNetB0 achieves the highest classification accuracy of approximately 98%, outperforming other models.},
        keywords = {Diabetic Eye Diseases, Deep Learning, Diabetic Retinopathy, Retinal Fundus Images, EfficientNetB0, Multi-Class Classification, Automated Disease Detection, Medical Image Analysis, Early Diagnosis, Clinical Decision Support.},
        month = {January},
        }