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{184305,
        author = {Shipra Singh and Anita Yadav},
        title = {Retinal Age-related Macular Degeneration Image Classification Using Deep Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {4},
        pages = {821-825},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=184305},
        abstract = {AMD refers to an unusual or irregular damage of the retina. In this project, we leverage deep learning techniques, specifically transfer learning with ResNet-50 to address the critical task of classifying retinal Optical Coherence Tomography (OCT) images for detection of age-related macular degeneration (AMD) and a various disease of retinal damage condition of eyes. We used a ResNet-50 CNN model that was fine-tuned to classify medical images. This model can accurately sort retinal OCT image are classify . To make results more useful for doctors we added Grad-CAM which shows a heatmap highlighting the specific areas of the retina that influenced the model decision. The project is carried out using Python, incorporating the Keras deep learning library for constructing and training neural networks, along with NumPy for performing efficient numerical computations. Google Colab is used as the development environment, offering interactive coding and access to GPU resources. In addition to achieving strong diagnostic performance the integration of Grad-CAM enhances model interpretability by visually highlighting the regions of OCT images that influence the model predictions which is essential for building trust in AI-assisted healthcare. This study demonstrates how explainable deep learning models can assist ophthalmologists in identifying and monitoring AMD at an early stage, which can result in improved outcomes for patients in actual medical environments.},
        keywords = {CNN, Deep Learning, Eye Disease Detection, Grad-CAM},
        month = {September},
        }