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{206248,
        author = {GOURIKRISHNA O S},
        title = {RetinaVision: An Efficient Deep Learning Framework for Automated Multi-Disease Retinal Image Classification Using MobileNetV2},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {2},
        pages = {752-757},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=206248},
        abstract = {Early identification of retinal diseases is crucial in order to prevent any vision-related impairment and also decrease the chances of permanent blindness. Nevertheless, manual analysis of retinal fundus images is both time-consuming and difficult for inexperienced ophthalmologists; thus, performing large-scale screening is problematic. In this paper, RetinaVision is proposed as an intelligent deep learning solution for the automation of retinal disease classification based on retinal fundus images. The proposed system uses the MobileNetV2 architecture with transfer learning for the fast and effective classification of several kinds of retinal diseases from the RFMiD (Retinal Fundus Multi-Disease Image Dataset). Input images are pre-processed, namely, they are resized, normalized, and also augmented in order to make the model more robust and generalizable. Training of the model is performed by means of the Adam optimization algorithm using the Binary Cross-Entropy loss function for multi-label classification. Experimental evaluation shows that the suggested approach is capable of achieving high-classification performance with an overall accuracy equal to 97.09% and a precision, recall, and F1-score of 80.73%, 41.33%, and 54.67%, respectively, on the test dataset. Thus, RetinaVision provides an affordable, fast, and accurate solution for helping ophthalmologists with diagnosing retinal diseases.},
        keywords = {Artificial Intelligence, Deep Learning, MobileNetV2, Multi-Label Classification, RFMiD Dataset, Retinal Disease Detection, RetinaVision, Transfer Learning.},
        month = {July},
        }