Automatic Choroidal Layer Segmentation Using Markov Random Field And Level Set Method

Abstract

The choroid is an important vascular layer that supplies oxygen and nourishment to the retina. The changes in thickness of the choroid have been hypothesised to relate to a number of retinal diseases in the pathophysiology. In this work, an automatic method is proposed for segmenting the choroidal layer from macular images by using the level set framework. The 3D nonlinear anisotropic diffusion filter is used to remove all the OCT imaging artifacts including the speckle noise and to enhance the contrast. The distance regularisation and edge constraint terms are embedded into the level set method to avoid the irregular and small regions and keep information about the boundary between the choroid and sclera. Besides, the Markov Random Field method models the region term into the framework by correlating the single pixel likelihood function with neighbour-hood information to compensate for the inhomogeneous texture and avoid the leakage due to the shadows cast by the blood vessels during imaging process. The effectiveness of this method is demonstrated by comparing against other segmentation methods on a dataset with manually labelled ground truth. The results show that our method can successfully and accurately estimate the posterior choroidal boundary.