Abstract :

Diabetic Retinopathy (DR) Is A Severe Complication Of Diabetes That Can Lead To Vision Loss If Not De- Tected And Treated Early. Traditional Diagnosis In- Volves Manual Examination Of Retinal Fundus Images By Ophthalmologists, Which Is Often Time-consuming And Prone To Subjectivity. This Paper Presents An Automated And Efficient Solution For DR Detection And Severity Classification By Employing An Ensemble Of Advanced Deep Learning Models, Including DenseNet, InceptionV3, ResNet, And MobileNet. The Proposed System Follows A Hierarchical Classification Approach, Where The Presence Of DR Is First Determined, Fol- Lowed By Classification Into Four Severity Levels: Mild, Moderate, Severe, And Proliferative. Attention-based Feature Fusion, Transfer Learning, And Optimization Strategies Such As SMOTE And Focal Loss Are Utilized To Enhance Accuracy, Address Data Imbalance, And Ensure Robustness. A Web-based Interface Is Developed Using Django To Allow Seamless Interaction For Healthcare Professionals. This System Is Optimized For Real-time Clinical Deployment, Offering Scalable, Accurate, And Reliable Support For Early DR Diagnosis. Keywords: Diabetic Retinopathy, Deep Learning, Con- Volutional Neural Networks, InceptionV3, DenseNet, ResNet, MobileNet, Classification, Feature Fusion, SMOTE, Focal Loss, Django.

Published:

17-7-2025

Issue:

Vol. 25 No. 7 (2025)

Page Nos:

506 - 514

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite