Artificial Intelligence Guided Diagnosis Based on Optical Coherence Tomography Images

This article underlines the impact of artificial intelligence in ophthalmology, presenting a way of interpreting optical coherence tomography images using deep learning. The idea was mainly generated by the necessity of an automated diagnosis support system for ocular diseases. The proposed application aims to provide a new approach for the classification of these images through a perspective which refers to three types of ophthalmological conditions: choroidal neovascularization, diabetic macular edema and age-related macular degeneration. To achieve this task, a convolutional neural network was created and trained. Having an accuracy of 89%, it can be a reliable tool, helping physicians with suggestions for diagnosis.