Automatic optic disc detection in OCT slices via low-rank reconstruction.

Abstract

Optic disc measurements provide useful diagnostic information as they have correlations with certain eye diseases. In this paper, we provide an automatic method for detecting the optic disc in a single OCT slice. Our method is developed from the observation that the retinal pigment epithelium (RPE) which bounds the optic disc has a low-rank appearance structure that differs from areas within the disc. To detect the disc, our method acquires from the OCT image an RPE appearance model that is specific to the individual and imaging conditions, by learning a low-rank dictionary from image areas known to be part of the RPE according to priors on ocular anatomy. The edge of the RPE, where the optic disc is located, is then found by traversing the retinal layer containing the RPE, reconstructing local appearance with the low-rank model, and detecting the point at which appearance starts to deviate (i.e., increased reconstruction error). To aid in this detection, we also introduce a geometrical constraint called the distance bias that accounts for the smooth shape of the RPE. Experiments demonstrate that our method outperforms other OCT techniques in localizing the optic disc and estimating disc width. Moreover, we also show the potential usage of our method on optic disc area detection in 3-D OCT volumes.