Abstract
Segmentation of retinal layers with central serious chorioretinopathy (CSC) in Spectral Domain Optical Coherence Tomography (SD-OCT) images is significant for quantitative analysis including the volume, location and shape of CSC region. In this paper, we present an automatic segmentation method to segment retinal layers based on graph theory and the previous B-scan information. Firstly, the boundaries of Vitreous-ILM (inner limiting membrane), ONL (outer nuclear layer)-IS (photoreceptor inner segments) or LR (lesion region)-RPE (retinal pigment epithelium), and RPE-Choroid are estimated based on graph search model. Next, a flexible search region is constructed by calculating the thickness between Vitreous-ILM and ONL-IS based on the difference between two consecutive B-scans, which is used to refine the ONL-IS. The proposed method was quantitatively evaluated in total of 200 B-scan images from 5 abnormal cubes with CSC and 5 normal cubes, where we choose 20 B-scan images randomly in each cube. Experimental results illustrated that the proposed method can segment retinal layers in SD OCT images with CSC accurately. And the overall mean absolute boundary positioning differences and the overall mean absolute thickness differences compared to manual segmentation results are 3.68 ± 2.96 μm and 5.84 ± 4.78 μm.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
