Nayak Badrinath, Dr. G. Purna Chandar Rao 03 07 Diabetic retinopathy is one of the leading causes of vision impairment among people with diabetes making early diagnosis essential for preventing permanent blindness Manual examination of retinal fundus images is timeconsuming and depends heavily on the expertise of ophthalmologists This study presents a lesionguided hybrid deep learning framework for the automatic detection of diabetic retinopathy from retinal images The proposed approach combines the feature extraction capability of Convolutional Neural Networks CNN with the discriminative strength of a hybrid deep learning architecture to identify retinal lesions such as microaneurysms hemorrhages and exudates Before training the retinal images are preprocessed and enhanced to improve image quality and reduce noise Data augmentation is applied to address class imbalance and improve the models generalization ability Experimental results demonstrate that the proposed framework achieves higher classification accuracy precision recall and F1score compared with conventional deep learning models The developed system offers a reliable and efficient computeraided solution for early diabetic retinopathy screening supporting ophthalmologists in making faster and more accurate clinical decisions Copyright (c) Journal of Science Engineering Technology and Management Science. All rights reserved 2026