The increasing prevalence of retinal diseases ne-cessitates accurate and automated diagnostic tools to support clinical decision-making. This study introduces DeepRetina, a fine-tuned InceptionV3-based deep learning model, designed to classify Optical Coherence Tomography (OCT) images into four categories: Normal, Choroidal Neovascularization (CNV), Dia-betic Macular Edema (DME), and Drusen. DeepRetina enhances the standard InceptionV3 architecture by incorporating three pairs of fully connected layers with ReLU activation, batch normalization, and dropout to refine feature representation and improve classification accuracy. The model was validated on the OCT19 dataset, achieving a remarkable classification accuracy of 99.76%, highlighting its potential as a reliable diagnostic assistant. By automating the analysis of OCT images, DeepRetina reduces clinicians’ workload, facilitates early detection, and minimizes the risk of vision loss for patients. This approach underscores the efficacy of advanced deep learning techniques in revolutionizing retinal disease diagnosis.