Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{178591,
        author = {Nishchitha P and Lata Raju Naik and Rakshitha BS and Pooja G},
        title = {DIABETIC RETINOPATHY ANALYSIS WITH DEEP NEURAL NETWORKS},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {3862-3867},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=178591},
        abstract = {The increasing prevalence of diabetic retinopathy (DR), a leading cause of blindness among diabetic patients, necessitates timely and accurate diagnosis. This paper presents a deep learning-based system for automated diabetic retinopathy evaluation using convolutional neural networks (CNNs). High-resolution retinal fundus images are processed through a deep neural architecture to identify and classify the severity of DR. The pipeline includes stages such as image enhancement, normalization, and augmentation to improve model performance. The models are trained and validated on benchmark datasets and evaluated using metrics like accuracy, sensitivity, specificity, and AUC-ROC. Integrated within a Django web application, the system enables real-time diagnosis through a RESTful API developed using Django REST Framework. This solution supports scalable, accurate, and accessible screening of diabetic retinopathy, thereby aiding in early detection and reducing},
        keywords = {Diabetic Retinopathy, Deep Neural Networks, Convolutional Neural Networks (CNN), Medical Image Analysis, Django REST Framework, Automated Diagnosis, Retinal Fundus Images, Real-time Prediction, Image Preprocessing, Healthcare AI},
        month = {May},
        }