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

The choroid is an important vascular layer that supplies oxygen and nourishment to the retina. The changes in thickness of the choroid have been hypothesized to relate to a number of retinal diseases in the pathophysiology. In this paper, an automatic method is proposed for segmenting the choroidal layer from macular images by using the level set framework. The three-dimensional nonlinear anisotropic diffusion filter is used to remove all the optical coherence tomography (OCT) imaging artifacts including the speckle noise and to enhance the contrast. The distance regularization 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 neighborhood 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 labeled ground truth. The results show that our method can successfully and accurately estimate the posterior choroidal boundary.

Authors

• Chuang Wang Beihang University, AIsphere Inc.
• Ya Xing Wang
• Yongmin Li

Keywords

• Image segmentation
• Three-dimensional displays
• Level set
• Retina
• Imaging
• Markov random fields
• Image edge detection
• Field Method
• Automatic Segmentation
• Markov Random Field
• Level Set Method
• Random Field Method
• Choroidal Segmentation
• Markov Random Field Method
• Blood Vessels
• Automatic Method
• Segmentation Method
• Retinal Diseases
• Regularization Term
• Image Artifacts
• Optical Coherence Tomography Images
• Speckle Noise
• Choroidal Thickness
• Anisotropic Diffusion
• Posterior Boundary
• Macular Images
• 3D Images
• Gaussian Mixture Model
• Inner Layer
• Retinal Nerve Fiber Layer
• Dice Similarity Coefficient
• Energy Function
• Dirac Delta
• Canny Edge Detection
• Automatic Segmentation Method
• Single Gaussian
• Retinal Pigment Epithelium
• Choroid layer segmentation
• and macular 3D OCT images
• Adult
• Aged
• Aged, 80 and over
• Choroid
• Humans
• Imaging, Three-Dimensional
• Markov Chains
• Middle Aged
• Tomography, Optical Coherence
• Young Adult