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{183676,
        author = {santhosh SG and Raziya sultana},
        title = {EyeNet: Automated Retinal Image Evaluation for Diabetic Retinopathy Detection},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {3},
        pages = {2677-2684},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=183676},
        abstract = {Diabetic retinopathy is among the diabetes mellitus, which is a serious complication among the diabetes mellitus, leading to the increasing the loss of vision if it is not detected and treated early. If the retinal images are graded manually according to the extremity of disease DR, then it needs the experts such as ophthalmologists and more time, which limits screening accessibility, especially in the areas of limited resources. This paper represents EyeNet, an automated system which is based on deep learning is designed to split the images of retinal fundus into five different stages of Diabetic Retinopathy that is: no Dr, mild Dr, moderate Dr, severe Dr, and proliferative retinopathy. EyeNet utilizes Convolutional Neural Networks that is CNNs to effectively extracts the similar features of the images and perform the accurate classification into multiple classes. The model is trained on large-scale publicly on the available datasets with proper pre-processing and augmentation methods applied to address data imbalance and variability. EyeNet achievements of competitive performance against recent state of the art approaches can be demonstrated using metrics which shows the accuracy of evaluation, precision, recall, and F1- score. This system goals to support and help the health care professionals such as ophthalmologists by providing fast, reliable Diabetic Retinopathy screening to get timely intervention, ultimately decreasing the risk of blindness and improving patient’s outcomes at scale.},
        keywords = {Convolution Neural Networks (CNN), Diabetic Retinopathy (DR), Disease classification, Flask, Retinal Image Analysis, Vision.},
        month = {August},
        }