Automated segmentation of the choroid in retinal optical coherence tomography images.

The choroid is a tissue layer at the back of the eye, which can be imaged by optical coherence tomography (OCT). Choroidal thickness has been proven to be correlated to several ophthalmic diseases in several studies. In this paper we proposed a novel segmentation technique to address this challenge. This technique firstly automatically segments the inner boundary of the choroid using a two-stage fast active contour model. It secondly allows a real-time human-supervised automated segmentation on the outer boundary of the choroid. Dice similarity coefficient (DSC) was used to evaluate the agreement between manual annotation and our automated measurements on 30 images captured from patients diagnosed with diabetes. The mean DSC value is 92.7% (standard deviation 3.6%) in the range of 85.5% to 98.1%. Results show that this new technique can achieve choroid segmentation with high accuracy.