REVIEW ON DEEP VISION FOR EARLY DETECTION OF DIABETIC RETINOPATHY USING MACHINE LEARNING
DOI: 
SHARE THIS ARTICLE
DOWNLOAD ARTICLE
REVIEW REPORT
CITE THIS ARTICLE
Diabetic Retinopathy (DR) is one of the most severe microvascular complications of diabetes mellitus and a leading cause of preventable blindness worldwide. Early diagnosis and timely treatment are critical, as DR often progresses asymptomatically until irreversible retinal damage occurs. Conventional diagnosis relies on manual examination of retinal fundus images by ophthalmologists, which is time-consuming, costly, and subject to inter-observer variability. Recent advancements in computer-aided diagnosis have demonstrated that machine learning, particularly deep learning, can significantly enhance the accuracy and efficiency of DR detection. Convolutional Neural Networks (CNNs) have emerged as the most effective approach for automated analysis of fundus images due to their capability to learn hierarchical and discriminative features directly from raw data. This review presents a comprehensive analysis of recent deep learning–based methods for diabetic retinopathy detection, classification, and severity grading. Key aspects such as preprocessing techniques, network architectures, publicly available datasets, and evaluation metrics are discussed. Furthermore, existing challenges including dataset imbalance, lack of interpretability, and limited clinical deployment are highlighted. The review also identifies emerging trends and future research directions aimed at developing robust, explainable, and scalable DR screening systems suitable for real-world clinical applications.
Keywords
Article Information
Article Metrics
HOW TO CITE
Copy
Padmagiriwar, T. D. (2026). Review on Deep Vision for Early Detection of Diabetic Retinopathy using Machine Learning. International Journal of Science, Strategic Management and Technology, 02(04). https://doi.org/10.55041/ijsmt.v2i4.412
Padmagiriwar, Tushar. "Review on Deep Vision for Early Detection of Diabetic Retinopathy using Machine Learning." International Journal of Science, Strategic Management and Technology, vol. 02, no. 04, 2026, pp. . doi:https://doi.org/10.55041/ijsmt.v2i4.412.
Padmagiriwar, Tushar. "Review on Deep Vision for Early Detection of Diabetic Retinopathy using Machine Learning." International Journal of Science, Strategic Management and Technology 02, no. 04 (2026). https://doi.org/https://doi.org/10.55041/ijsmt.v2i4.412.
References
2.Bhulakshmi, S. K. Mohanty, and R. Dash, “A systematic review on diabetic retinopathy detection and classification based on deep learning techniques,” PeerJ Computer Science, vol. 10, e1947, 2024, doi: 10.7717/peerj-cs.1947.
3.Naz, M. I. Razzak, A. Shakoor, and A. Mehmood, “Diabetic retinopathy detection using supervised and unsupervised deep learning methods: A systematic review,” Artificial Intelligence Review, vol. 57, no. 3, pp. 1–45, 2024, doi: 10.1007/s10462-024-10770-x.
4.Dejene, “Diabetic retinopathy screening using machine learning: A review,” BMC Biomedical Engineering, vol. 5, no. 1, pp. 1–15, 2025, doi: 10.1186/s42490-025-00098-0.
5.Nadeem, S. I. Malik, M. A. Khan, et al., “Deep learning for diabetic retinopathy analysis: A survey,” Sensors, vol. 22, no. 18, pp. 6780, 2022, doi: 10.3390/s22186780.
6.Muthusamy and S. Palani, “Deep learning models for diabetic retinopathy classification: A review,” International Journal of Intelligent Systems and Machine Learning, vol. 16, no. 2, pp. 145–162, 2024.
7.Aghabeigi Alooghareh, H. Abrishami, and A. Shafiei, “Deep learning for comprehensive retinal disease analysis: Trends and challenges,” Bioengineering, vol. 12, no. 8, pp. 840, 2025, doi: 10.3390/bioengineering12080840.
8.Alyoubi, W. Shalash, and M. F. Abulkhair, “Diabetic retinopathy detection through deep learning techniques: A review,” Informatics in Medicine Unlocked, vol. 20, pp. 100377, 2020, doi: 10.1016/j.imu.2020.100377.
9.Gautam, “Deep learning-based diabetic retinopathy detection and classification: A comprehensive review,” Journal of Medical Imaging and Health Informatics, vol. 15, no. 1, pp. 1–18, 2025.
10.Lestari, “Validity of artificial intelligence for diabetic retinopathy screening: A review,” International Journal of Retina, vol. 6, no. 2, pp. 85–94, 2023, doi: 10.35479/ijretina.2023.241.
Ethics and Compliance
Indexed In
Similar Articles
Previous Article
