SHORTEST PATH WITH BACKTRACKING BASED AUTOMATIC LAYER SEGMENTATION IN PATHOLOGICAL RETINAL OPTICAL COHERENCE TOMOGRAPHY

Optical coherence tomography (OCT) is one of the most prevalent techniques for ophthalmic diagnosis. Retinal layer segmentation is very crucial for doctors to diagnose and study retinal diseases. However, manual segmentation is often a time-consuming and subjective process. A number of methods have been proposed for layer segmentation on retinal OCT images, but these methods are not suit for retinal pathological OCT images. In this work, we propose a new method for layers (two layers, inner limiting membrane, outer segments-retinal pigment epithelium) segmentation in pathological retinal OCT images using shortest path algorithm enhanced with backtracking and direction consistency. To quantitate the performance of the proposed method, we compared method to three segmentation methods. The experimental result shows that our method is more suited for retinal OCT images in pathological and achieves better result than the state-of-the-art methods.