Copyright © 2025 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{169472,
        author = {Nandini Sachin Patil and Vaishnavi Chaitanya Shitole and Yash Satyanarayan Kalwar and Raghunandan Rajesh Somani and Dr. S. R. Ganorkar},
        title = {Diabetic Retinopathy Detection using Image Processing and Deep Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {6},
        pages = {1073-1078},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=169472},
        abstract = {Diabetic retinopathy, DR is one of the leading causes of blindness which is the main cause of vision loss early detection and classification of DR is essential for effective treatment and also to reduce the risk of vision loss this study has a new idea for use in automatic detection and staging of diabetic retinopathy using model CNN deep convolutional neural networks, our image preprocessing method involves combining image datasets from three sources, then using a CNN architecture to extract features, and finally using a computer algorithm to classify images into five severity levels. DR. no DR mild moderate DR and the overgrowth technique uses two retinal background datasets that are combined and warped by size standardization and data fusion, we improve our proprietary CNN model that is specially modified to capture key features for full concatenated layer image classification . The model is trained, validated and run on the combined database and the results achieved show good performance and robustness of the evaluation model includes metrics such as accuracy, recall accuracy and f1 score that symbolize its integrity in diagnosing severity level classification dr. this analysis is able to provide an accurate rapid and easily scalable diagnostic tool for physicians that could be used for medical assistance in their clinical practice.},
        keywords = {},
        month = {November},
        }