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{175963,
        author = {Mitali B. Yadav and Chaya R. Jadhav and Rachna Somkunwar},
        title = {Diabetic Retinopathy Detection: AI-Based Approaches, Challenges, and Emerging Trends},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {4620-4625},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=175963},
        abstract = {Diabetic retinopathy (DR) is a serious diabetic com- plication that may result in blindness if not identified and treated in its initial phases. As diabetes has become a growing global condition, the need for DR screening has increased significantly, resulting in a lack of medical experts skilled enough to carry out timely and precise diagnoses with fundus images. Deep learning- based automated screening techniques have thus become a very viable answer in filling this void, promising a high level of accuracy and efficiency in detecting DR. The latest developments in deep learning have enabled the creation of multitask learning-based models for DR screening that utilize sophisticated image preprocessing methods like automated greyscale conversion and Gaussian blur. The preprocessing methods increase image contrast, enhance feature extraction, and emphasize pathological features critical for DR classification. These models, trained on large fundus image databases, can accurately classify DR and evaluate its severity, facilitating early diagnosis and intervention. The incorporation of automatic image enhancement methods into deep learning models has been shown to have enhanced classification performance, as verified by experimental results. This paper discusses how deep learning can be applied in DR screening, highlighting its potential in improving diagnostic effectiveness as well as in response to the growing need for early detection measures.},
        keywords = {Deep Learning, Feature Extraction, Diabetic Retinopathy, Convolutional Neural Network, Classification, Image Preprocessing},
        month = {April},
        }