Sparse High Order Potentials for Extending Multi-Surface Segmentation of OCT Images with Drusen

Abstract

Drusen quantification is important for evaluating age-related macular degeneration (AMD) progress. Most methods for retinal layers segmentation in optical coherence tomography (OCT) depend heavily on prior information. This improves robustness, but also has the downside of increasing surface rigidity. Hence, those algorithms normally smooth drusen borders, as significant local variations are not expected. In this work, we propose to integrate sparse higher order potentials (SHOPs) into a multi-surface segmentation framework to cope with local boundary variations caused by drusen. The algorithm was evaluated in a database of 20 patients with AMD. The mean unsigned error for the inner retinal pigment epithelium (IRPE) and Bruch's membrane (BM) was 5.65 +/- 6.26 and 4.37 +/- 5.25 mu m, respectively. These results are relative to the average of two experts, whose inter-observer variability was 7.30 +/- 6.87 mu m for IRPE and 5.03 +/- 4.37 mu m for BM. The use SHOPs resulted in a successful segmentation of the IRPE. The remaining boundaries were also successfully segmented.