AN AI-DRIVEN OPHTHALMIC HEALTHCARE FRAMEWORK FOR AUTOMATED DIABETIC RETINOPATHY SCREENING AND SEVERITY ASSESSMENT
Malla Reddy College of Engineering and Technology (MRCET), Hyderabad, Telangana, India
DOI: 
SHARE THIS ARTICLE
DOWNLOAD ARTICLE
REVIEW REPORT
CITE THIS ARTICLE
This study presents an AI-driven ophthalmic healthcare framework for automated diabetic retinopathy (DR) screening and severity assessment using deep learning techniques. The proposed framework integrates image preprocessing, retinal vessel feature extraction, ResNet50, EfficientNet, and a vessel-guided attention mechanism to classify retinal images into five severity grades: No DR, Mild, Moderate, Severe, and Proliferative DR. Grad-CAM provides visual explanations to support the interpretation of model predictions. The framework aims to improve screening efficiency, classification consistency, and early identification of retinal abnormalities. Comparative evaluation using accuracy, precision, recall, and macro-F1 score can help determine the effectiveness of the proposed approach. However, its reliability must be established through experiments on actual test data and independent clinical datasets before practical deployment.
Keywords
Article Information
Article Metrics
HOW TO CITE
Copy
Ishma, S. (2026). An AI-Driven Ophthalmic Healthcare Framework for Automated Diabetic Retinopathy Screening and Severity Assessment. International Journal of Science, Strategic Management and Technology, 02(02), 1-9. https://doi.org/10.55041/ijsmt.v2i2.014
Ishma, Shaik. "An AI-Driven Ophthalmic Healthcare Framework for Automated Diabetic Retinopathy Screening and Severity Assessment." International Journal of Science, Strategic Management and Technology, vol. 02, no. 02, 2026, pp. 1-9. doi:https://doi.org/10.55041/ijsmt.v2i2.014.
Ishma, Shaik. "An AI-Driven Ophthalmic Healthcare Framework for Automated Diabetic Retinopathy Screening and Severity Assessment." International Journal of Science, Strategic Management and Technology 02, no. 02 (2026): 1-9. https://doi.org/https://doi.org/10.55041/ijsmt.v2i2.014.
References
[2] T. Araújo et al., “DR|GRADUATE: Uncertainty-aware deep learning-based diabetic retinopathy grading in eye fundus images,” Medical Image Analysis, vol. 63, Art. no. 101715, 2020. doi: 10.1016/j.media.2020.101715.
[3] K. Shankar et al., “Hyperparameter tuning deep learning for diabetic retinopathy fundus image classification,” IEEE Access, vol. 8, pp. 118164–118173, 2020. doi: 10.1109/ACCESS.2020.3005152.
[4] X. Li et al., “CANet: Cross-disease attention network for joint diabetic retinopathy and diabetic macular edema grading,” IEEE Transactions on Medical Imaging, vol. 39, no. 5, pp. 1483–1493, 2020. doi: 10.1109/TMI.2019.2951844.
[5] B. Tymchenko, P. Marchenko, and D. Spodarets, “Deep learning approach to diabetic retinopathy detection,” in Proc. 9th International Conference on Pattern Recognition Applications and Methods (ICPRAM), 2020. doi: 10.5220/0008970805010509.
[6] N. Tsiknakis et al., “Deep learning for diabetic retinopathy detection and classification based on fundus images: A review,” Computers in Biology and Medicine, vol. 135, Art. no. 104599, 2021. doi: 10.1016/j.compbiomed.2021.104599.
[7] S. Shekar, N. Satpute, and A. Gupta, “Review on diabetic retinopathy with deep learning methods,” Journal of Medical Imaging, vol. 8, no. 6, Art. no. 060901, 2021. doi: 10.1117/1.JMI.8.6.060901.
[8] Z. Khan et al., “Diabetic retinopathy detection using VGG-NIN: A deep learning architecture,” IEEE Access, vol. 9, pp. 61408–61416, 2021. doi: 10.1109/ACCESS.2021.3074422.
[9] J. Grauslund, “Diabetic retinopathy screening in the emerging era of artificial intelligence,” Diabetologia, vol. 65, no. 9, pp. 1415–1423, 2022. doi: 10.1007/s00125-022-05727-0.
[10] S. Zafar, H. Mahjoub, N. Mehta, A. Domalpally, and R. Channa, “Artificial intelligence algorithms in diabetic retinopathy screening,” Current Diabetes Reports, vol. 22, no. 6, pp. 267–274, 2022. doi: 10.1007/s11892-022-01467-y.
Ethics and Compliance
Indexed In
Similar Articles
Previous Article
