Eyesight AI: An Intelligent Deep Neural Network Based Framework for Detection and Classification of Retinal Diseases through Fundus Image Analysis

Retinal diseases such as diabetic retinopathy, age-related macular degeneration, and glaucoma are among the leading causes of vision impairment and blindness worldwide. Early detection and timely treatment are essential to prevent irreversible damage and improve patient outcomes. This project, EYESIGHT AI, presents an intelligent deep learning-based system designed for the automated detection and classification of retinal diseases using Optical Coherence Tomography (OCT) images. The proposed system utilizes Convolutional Neural Networks (CNNs) to effectively extract complex features from retinal images and accurately identify disease patterns. Prior to model processing, OCT images undergo preprocessing techniques including contrast enhancement and noise reduction to improve image quality and ensure better feature extraction. The enhanced images are then passed through the trained CNN model for classification into different retinal disease categories. To enhance usability and real-world applicability, the system is integrated with a Django-based web interface that allows healthcare professionals to easily upload OCT images and obtain diagnostic predictions in a user-friendly environment. The model is trained and evaluated on standard retinal image datasets, demonstrating reliable performance and high accuracy in disease classification. Overall, EYESIGHT AI serves as a supportive diagnostic tool that can assist medical practitioners in early detection and clinical decision-making. By reducing diagnostic time and improving accuracy, the system contributes to more efficient and accessible eye care, particularly in resource-limited settings.

Convolutional Neural Networks, Optical Coherence Tomography, automated Medical Diagnosis, deep learning, retinal imaging

1. J. Kim, M. Kim, H. Lee, et al., —Smart Contact Lenses for Continuous Intraocular Pressure Monitoring,‖ Nature Communications, vol. 13, no. 1, pp. 1–10, 2022. [Google Scholar] [Crossref]

3. S.R.N.,P.Kumar,andR.Singh,—IoT-BasedGlaucomaMonitoring System Using Machine Learning Techniques,‖ MDPI Engineering Proceedings, vol. 59, no. 1, pp. 1–7, 2024. [Google Scholar] [Crossref]

4. A. T. Duchowski, —A Breadth-First Survey of Eye-Tracking Applications,‖arXiv preprint arXiv: 2412.14848, 2025. [Google Scholar] [Crossref]

5. R. Thakur, S. Gupta, and A. Sharma, —Glaucoma Detection Using Artificial Intelligence Techniques,‖ Scientific Reports, vol. 15, pp. 1–12, 2025. [Google Scholar] [Crossref]

6. Y. Liu, X. Zhang, and L. Wang, —Wearable IoT-Based Eye Monitoring Systems: A Review,‖arXiv preprint arXiv:2410.12303,2024. [Google Scholar] [Crossref]

7. H. Chen, Y. Li, and J. Zhao, —Deep learning-based automated glaucoma detection using retinal fundus images,‖ IEEE Access, vol. 11, pp.45678–45687,2023. [Google Scholar] [Crossref]

8. M. S. Hossain, G. Muhammad, and N. Guizani, —Cloud-assisted industrial internet of things (IIoT) – Enabled framework for health monitoring,‖ IEEE Internet of Things Journal, vol. 7, no. 4, pp. 2936–2945, 2020. [Google Scholar] [Crossref]

9. S. Dua, U. R. Acharya, P. Chowriappa, and S. V. Sree, —Wavelet-based energy features for glaucoma detection in retinal images,‖ IEEE Transactions on Information Technology in Biomedicine, vol. 16, no. 1, pp.80–87,2012. [Google Scholar] [Crossref]

10. A. Esteva, B. Kuprel, R. A. Novoa, et al., —Dermatologist-level classification of skin cancer with deep neural networks,‖ Nature, vol.542, no. 7639, pp. 115–118, 2017. [Google Scholar] [Crossref]

11. D. Poplin, V. Varadarajan, K. Blumer, et al., —Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning,‖NatureBiomedicalEngineering,vol.2,no.3,pp.158–164, 2018. [Google Scholar] [Crossref]

12. G. Quellec, M. Lamard, P. M. Josselin, et al., —Optimal wavelet transform for the detection of microaneurysms in retina photographs,‖ IEEE Transactions on Medical Imaging, vol. 27, no. 9, pp. 1230–1241, 2008. [Google Scholar] [Crossref]

13. V. Gulshan, L. Peng, M. Coram, et al., —Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs,‖ JAMA, vol. 316, no. 22, pp. 2402–2410, 2016. [Google Scholar] [Crossref]

14. D. S. W. Ting, L. Y. L. Cheung, G. Lim, et al., —Development and validation of a deep learning system for diabetic retinopathy and related eye diseases,‖ JAMA, vol. 318, no. 22, pp. 2211–2223, 2017. [Google Scholar] [Crossref]

15. K. He, X. Zhang, S. Ren, and J. Sun, —Deep residual learning for image recognition,‖ in Proceedings of the IEEE Conference onComputer Vision and Pattern Recognition (CVPR), pp. 770–778, 2016. [Google Scholar] [Crossref]

16. O. Ronneberger, P. Fischer, and T. Brox, —U-Net: Convolutional Networks for Biomedical Image Segmentation,‖ in MICCAI, pp. 234–241, 2015. [Google Scholar] [Crossref]

• Migrant Health in Morocco: Between Law and Reality
• CaknaMinda: An Educator-Centred Mobile App for Early Screening of Mental Health and Schizophrenia Risks
• Health System and Nursing Strategies for Enhancing Male Participation in Family Planning: Evidence from Tema General Hospital, Ghana.
• From Īśvara-Praṇidhāna to Parā-Bhakti: Convergent Paths of Aṣṭāṅga Yoga and Bhakti Yoga
• Evidence-Based Psycho-Oncological Interventions: A Multimodal Approach to Supportive Care