Retinal diseases such as choroidal neovascularization (CNV), diabetic macular edema (DME), and drusen are among the leading causes of vision loss worldwide, requiring early and accurate diagnosis to prevent irreversible damage. Optical Coherence Tomography (OCT) provides high-resolution imaging of retinal structures, making it a valuable tool in ophthalmological diagnosis. This study presents a novel artificial intelligence (AI)-supported computer-aided diagnostic system for the real-time classification of retinal diseases using OCT images. The proposed system integrates a DenseNet-201 deep learning model with a hash-based data integrity mechanism and a user-friendly interface for clinical deployment. The DenseNet-201 model achieved superior performance with an accuracy of 94.42%, an F1-score of 0.9442, and an AUC of 1.00, outperforming other widely used models such as GoogleNet, ResNet50, and EfficientNetB0. Unlike existing systems, our approach includes automatic image validation, eliminates data redundancy through hashing, and is optimized for practical use via the Gradio interface. These features address major limitations in prior studies, such as a lack of real-time capability, data inconsistency, and insufficient clinical integration. The system not only improves diagnostic accuracy but also reduces clinician workload, ensuring faster and more reliable decision-making in retinal disease detection. This work demonstrates the feasibility of deploying AI-powered diagnostic tools in real-world ophthalmic settings and lays the groundwork for future development of integrated, scalable healthcare solutions. Index Terms—Retinal Diseases, Optical Coherence Tomography (OCT), Artificial Intelligence (AI), Deep Learning, Computer-Aided Diagnosis, Clinical Decision Support System, Real-Time Classification, Medical Image Analysis, DenseNet-201, GoogleNet, ResNet50, EfficientNetB0, Gradio Interface
Memiş et al. (Wed,) studied this question.