Detection of retinal diseases from OCT images by hybrid-based CNN method

One of the most important organs for human life is undoubtedly the eye. The eye is a window that human beings use to see the outside world. One of the important causes that negatively affect life is the diseases that occur in the retina of the eye. Since diseases in the retina affect visual function and the damage to the retina is irreversible, it is a situation that should be seriously considered. In the case of a timely intervention or a delayed situation, it can cause permanent damage to the eye. Although there are imbalances between the number of doctors needed for the follow-up of these diseases and the number of patients increasing day by day, it has become very difficult to follow these patients. For this reason, it has become possible to detect retinal diseases from Optical Coherence Tomography (OCT) images by using artificial intelligence methods for early diagnosis and life-saving treatments that will begin as a result of helping patients both in terms of time and economy, and on the other hand, facilitating the work of doctors In this study, machine learning, which is a sub-field of artificial intelligence, is a sub-branch of machine learning and using deep learning architectures that have become popular today, Age-Related Macular Degeneration (AMD), Choroid Neovascularization (CNV), Diabetic Macular Edema (DME), Diabetic Retinopathy (DR), Central Serous Retinopathy (CSR), Macular Hole (MH) and Drusen retinal diseases are aimed to detect the disease and classify these images by using the hybrid-based Convolutional neural networks(CNN) method in OCT images.