A neural network approach to retinal layer boundary identification from optical coherence tomography images

Abstract

In this paper, we propose a method by which the boundaries of retinal layers in optical coherence tomography (OCT) images can be identified from a simple initial user input. The proposed method is a neural network approach in which the neural networks are trained to identify points within each layer, from which, the boundaries between the retinal layers are estimated. This method focuses on training neural networks to identify layers themselves, instead of boundaries, because the available date is richer and more cohesive as compared to boundary identification. Results are presented, demonstrating the effectiveness of this method.