Order Preserving and Shape Prior Constrained Intra-retinal Layer Segmentation in Optical Coherence Tomography

We present a probabilistic approach to the segmentation of OCT scans of retinal tissue. By combining discrete exact inference and a global shape prior, accurate segmentations are computed that preserve the physiological order of intra-retinal layers. A major part of the computations can be performed in parallel. The evaluation reveals robustness against speckle noise, shadowing caused by blood vessels, and other scan artifacts.