Disease Detection Using Retina Images Using Deep Learning Techniques

Author

Yashas N K, Manoj H S, Abhishek S, Naveen Kumar, Shivaraj Veerappa Banakar


Abstract

 Retinal diseases, including Diabetic Retinopathy, Glaucoma, Diabetic Macular Edema, and Cataract, are among the leading causes of vision impairment and blindness worldwide. Early diagnosis is essential for preventing irreversible vision loss and improving patient outcomes. Recent advancements in Artificial Intelligence (AI) and Deep Learning (DL) have enabled the development of automated retinal disease detection systems that assist ophthalmologists in accurate and timely diagnosis. This survey paper presents a comprehensive review of recent AI-driven approaches for retinal disease detection using retinal fundus and Optical Coherence Tomography (OCT) images. It examines various Deep Learning techniques, including Convo-lutional Neural Networks (CNNs), Transfer Learning models, Vision Transformers (ViTs), EfficientNet, ResNet50, and hybrid architectures employed for retinal image analysis and disease classification. The survey also analyzes image preprocessing techniques, feature extraction methods, and classification strate-gies that enhance the performance of automated retinal disease detection systems. A comparative analysis of existing studies is presented to evaluate their methodologies, major contributions, and limitations. Furthermore, the survey identifies key research gaps, including high computational complexity, limited multi-disease classification, and challenges associated with image qual-ity variations. Based on these findings, the paper highlights the need for efficient and robust Deep Learning frameworks capable of accurately detecting multiple retinal diseases while supporting reliable clinical decision-making and improving accessibility to automated eye disease screening.


Keywords

Retinal Disease Detection, Artificial Intelligence, Deep Learning, Convolutional Neural Networks (CNN), Transfer Learning, Vision Transformer (ViT), Fundus Images,



Full Text:

Download Paper PDF


References


  • A. Rodriguez, H. AlMarzouqi, and P. Liatsis, “Multi-label Retinal Classification,” IEEE Journal of Biomedical and Health Informatics, 2022.
  • Patel, A. Sharma, and S. Kumar, “Cataract Detection using Deep Learning,” IEEE Access, 2022.
  • Kumar, S. Patel, and M. Shah, “Lightweight CNN for Retinal Disease Detection,” in Proc. IEEE Int. Conf. AI in Healthcare, 2025.
  • Singh, P. Verma, and R. Gupta, “WaveNet-SF Retinal Detection,” in Proc. IEEE Int. Conf. Medical Imaging, 2025.
  • Sharma and P. Rao, “Smart Retinal Disease Detection Using AI,” IEEE Access, 2024.
  • Zhao, H. Li, and J. Wang, “Hybrid Deep Learning Model for Eye Disease Detection,” IEEE Access, 2024.
  • Smith, A. Brown, and M. Taylor, “Anomaly Detection and Biomarkers Localization in Retinal Images,” in Proc. IEEE EMBC, 2024.
  • Chen, Y. Zhao, and H. Wang, “Retinal Disease Vision Transformer,” IEEE Journal of Biomedical and Health Informatics, 2024.
  • R. Dubey, S. Singh, and R. K. Chaudhuri, “Lightweight CNN Retinal Detection,” IEEE Access, 2023.
  • Wilson, P. Harris, and K. Lee, “Deep Learning Applications in Retinal Diseases,” in Proc. IEEE Healthcare Innovations Conference, 2023.
  • Lyu, I. E. Toubal, and K. Palaniappan, “Multi-Expert Retinal Detec-tion,” in Proc. IEEE EMBC, 2022.
  • C. S. Tang, S. S. Teoh, H. Ibrahim, and Z. Embong, “Smartphone Retinal Detection App,” in Proc. IEEE EMBC, 2022.
  • Zhang, X. Chen, and L. Wu, “Retinal Feature Representation Learn-ing,” in Proc. IEEE ICIP, 2022.
  • Gupta, N. Mehta, and P. Sharma, “Retinal Anomaly Detection,” in Proc. IEEE ISBI, 2022.
  • Zhang, Z. Ji, Q. Chen et al., “CycleGAN Retinal Pathology Detec-tion,” IEEE Journal of Biomedical and Health Informatics, 2022.
  • Kamble, A. Srivastava, and N. Singhal, “LADeN Macular Disease Detection,” in Proc. IEEE ISBI, 2022.
  • Baharlouei, H. Rabbani, and G. Plonka, “OCT Retinal Abnormality Detection,” in Proc. IEEE EMBC, 2022.
  • Hao, T. Shen, X. Zhu et al., “Retinal Structure Detection in OCTA Images,” IEEE Transactions on Medical Imaging, 2022.
  • Goutam, M. F. Hashmi, Z. W. Geem, and N. D. Bokde, “Deep Learning Retinal Diagnosis Review,” IEEE Access, 2022.
  • Wang, H. Chen, and X. Li, “OCT-Trans Retinal Classification,” in Proc. IEEE ISBI, 2025.

 

 

 

 

Share your valuable work from Social Media Buttons