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{179113,
        author = {Mukktayakka Rajashekhar Desai and Nithina G and Shalini P and Shreya M K and Tejaswini S},
        title = {Automated Detection of Retinopathy of Prematurity Using Convolutional Neural Networks},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {7625-7629},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=179113},
        abstract = {This paper introduces a robust deep learning framework aimed at improving the diagnosis of ocular diseases in low-resource settings, where access to high-quality imaging and expert evaluation is limited. The proposed method employs an ensemble of convolutional neural networks (CNNs) trained using transfer learning on a large-scale dataset comprising 38,727 high-resolution fundus images. The ensemble model is subsequently evaluated on 13,000 low-quality fundus images acquired through cost-efficient retinal imaging devices. Despite being trained solely on high-quality data, the model demonstrates strong generalization and achieves performance comparable to state-of-the-art systems in detecting key ophthalmic conditions such as diabetic retinopathy, optic disc excavation, and vascular anomalies. The results highlight the effectiveness of the transfer learning approach in bridging the domain gap between high- and low-quality imaging, offering a practical and scalable solution for automated retinal disease screening in under-resourced healthcare environments},
        keywords = {},
        month = {May},
        }