MACULA OCT Disease Images Classification using Deep Learning Techniques

This study explores the transformative impact of deep learning techniques, particularly in ophthalmology, on medical image analysis, with a specific focus on the automated classification of macula optical coherence tomography (OCT) images to differentiate various retinal diseases. The investigated diseases include Age-Related Macular Degeneration (AMD), Choroidal Neovascularization (CNV), Diabetic Macular Edema (DME), Diabetic Retinopathy (DR), Central Serous Retinopathy (CSR), Macular Hole (MH), Exudative Neovascularization (DRSUEN), and NORMAL macula. Employing convolutional neural network (CNN) architectures like ManualNet, AlexNet, and ResNet, the study demonstrates varied accuracy levels, with ResNet achieving the highest accuracy at 90%. The results highlight the effectiveness of deep learning in accurately classifying macula OCT images, showcasing its potential as a reliable tool for early disease detection and treatment, ultimately contributing to improved diagnostic efficiency for various macular diseases.