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{197980,
        author = {Divya Bharti and Bharathi K and Rajveer Singh Katoch and Ratnesh Prakash Yadav and Sriya Alla},
        title = {Retinal OCT Disease classification using CNN},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {8030-8038},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=197980},
        abstract = {Retinal Optical Coherence Tomography (OCT) is a non-invasive imaging technique widely used for diagnosing retinal disorders. Manual analysis of OCT scans is often labor-intensive and subject to inter-observer variability, highlighting the need for automated diagnostic systems. This study proposes a deep learning-based approach for retinal disease classification using a Convolutional Neural Network (CNN) model. The CNN architecture is designed to automatically extract hierarchical spatial features from OCT images, enabling accurate differentiation among four retinal conditions: Diabetic Macular Edema (DME), Age-related Macular Degeneration (AMD), Drusen, and Normal retina. The proposed model effectively learns discriminative features of pathological and healthy retinal layers, achieving robust classification performance. Experimental results demonstrate that the CNN-based system provides reliable and efficient disease detection, supporting ophthalmologists in early diagnosis and clinical decision-making.},
        keywords = {Optical Coherence Tomography (OCT), ResNet18, Multi-Modal Fusion, Grad-CAM, Weighted Cross-Entropy, Retinal Disease Classification},
        month = {April},
        }