Accurate automatic segmentation of retina layers with emphasis on first layer

The quantification of intra-retinal boundaries in the Optical Coherence Tomography (OCT) is a crucial task to study and diagnose neurological and ocular diseases. Since the manual segmentation of layers is usually a time consuming task and relies on the user, an excessive volume of research has been done to do this job automatically and without interference of the user. Although, generally the same procedure is applied to extract all layers, but finding the RNFL is typically more challenging due to the fact that it may vanish in some parts of the eye, especially close to the fovea. To have general software, besides using common methods such as applying the shortest path algorithm on the global gradient of an image, some extra steps have been taken here to narrow the search area for Dijstra’s algorithm, especially for the second boundary. The result demonstrates high accuracy in segmenting the RNFL that is really important for the diagnosing Glaucoma.