19 May 2014 Automated retinal layer segmentation and characterization
Author Affiliations +
Abstract
Spectral Domain Optical Coherence Tomography (SD-OCT) is a valuable diagnostic tool in both clinical and research settings. The depth-resolved intensity profiles generated by light backscattered from discrete layers of the retina provide a non-invasive method of investigating progressive diseases and injury within the eye. This study demonstrates the application of steerable convolution filters capable of automatically separating gradient orientations to identify edges and delineate tissue boundaries. The edge maps were recombined to measure thickness of individual retinal layers. This technique was successfully applied to longitudinally monitor changes in retinal morphology in a mouse model of laser-induced choroidal neovascularization (CNV) and human data from age-related macular degeneration patients. The steerable filters allow for direct segmentation of noisy images, while novel recombination of weaker segmentations allow for denoising post-segmentation. The segmentation before denoising strategy allows the rapid detection of thin retinal layers even under suboptimal imaging conditions.
© (2014) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jonathan Luisi, Jonathan Luisi, David Briley, David Briley, Adam Boretsky, Adam Boretsky, Massoud Motamedi, Massoud Motamedi, } "Automated retinal layer segmentation and characterization", Proc. SPIE 9155, Translational Biophotonics, 91551N (19 May 2014); doi: 10.1117/12.2057814; https://doi.org/10.1117/12.2057814
PROCEEDINGS
10 PAGES


SHARE
Back to Top