Enhancing Diabetic Retinopathy Diagnosis with Deep Neural Networks

DR is a critical microvascular secondary complication of diabetes, and if not identified in time, it often leads to irreversible blindness. Traditional screening techniques rely on manual fundus examination, which is not only time-consuming but mostly unavailable in under-resourced settings. This work, therefore, calls for the use of computer-aided detection and classification using fundus images of the retina. In this analysis, pre-trained Convolutional Neural Networks like ResNet50, VGG16, DenseNet, MobileNet, and EfficientNet have been fine-tuned, with image enhancement using contrast and data augmentation to emphasize subtle retinal lesions like microaneurysms and exudates. Experimental results indicated that ResNet performed best among the systems with an accuracy of 74%, thus outperforming others in classifying DR into multiple severity stages. For ease of access, this system is designed for deployment through a lightweight web-based application with real-time prediction, visualization of results, and personalized suggestions for treatment. Furthermore, this paper discusses the integration of Vision Transformers for improved lesion detection at the fine-grain level. This work contributes toward SDG 3 - Good Health and Well-being, as it proposes a scalable, accurate, affordable DR screening that would otherwise reduce clinical burden and improve healthcare equity.