2009-28: Retinal layer segmentation in SD OCT images
Investigator Initiated Research
Inclusion open since 1-1-2010
SD OCT is capable of producing three-dimensional scans of the retina. The resulting data sets are very large, which makes them difficult to analyze without further processing. In many cases, interpretation of these volumetric scans requires segmentation of the data, i.e., providing a tissue label to each point in the volume. Based on the segmentation, metrics such as layer thickness or distances between layers can be defined. Examples of diseases requiring such analyses are glaucoma (NFL thickness), DRPE (photoreceptors) and retinal dystrophies such as RPE65-LCA (photoreceptor, RPE). Current SD OCT devices (Spectralis, Optovue) only provide limited segmentation of the retinal layers, while for experimental OCT systems, no generally applicable segmentation algorithms exist. Objective of this study is the development of algorithms for automatic segmentation of various retinal layers in SD OCT images. The development of such algorithms for determining the NFL thickness of glaucoma patients. The development of such algorithms for determining the fitness of the photoreceptor layer in DRPE and LCA patients with RPE65 mutations.