Automated 3-D Retinal Layer Segmentation of Macular Optical Coherence Tomography Images With Serous Pigment Epithelial Detachments

• Published in: IEEE transactions on medical imaging Vol. 34; no. 2; pp. 441 - 452
• Main Authors: Fei Shi, Xinjian Chen, Heming Zhao, Weifang Zhu, Dehui Xiang, Enting Gao, Sonka, Milan, Haoyu Chen
• Format: Journal Article
• Language: English
• Published: United States IEEE 01-02-2015
• Subjects: Algorithms; Diseases; Floors; Humans; Image edge detection; Image segmentation; Imaging, Three-Dimensional - methods; Optical coherence tomography (OCT); pigment epithelium detachment (PED); Retina; Retina - anatomy & histology; Retina - pathology; Retinal Detachment - pathology; retinal layer segmentation; Surface morphology; Surface treatment; Tomography, Optical Coherence - methods
• ISSN: 0278-0062; 1558-254X
• DOI: 10.1109/TMI.2014.2359980

Automated retinal layer segmentation of optical coherence tomography (OCT) images has been successful for normal eyes but becomes challenging for eyes with retinal diseases if the retinal morphology experiences critical changes. We propose a method to automatically segment the retinal layers in 3-D OCT data with serous retinal pigment epithelial detachments (PED), which is a prominent feature of many chorioretinal disease processes. The proposed framework consists of the following steps: fast denoising and B-scan alignment, multi-resolution graph search based surface detection, PED region detection and surface correction above the PED region. The proposed technique was evaluated on a dataset with OCT images from 20 subjects diagnosed with PED. The experimental results showed the following. 1) The overall mean unsigned border positioning error for layer segmentation is 7.87±3.36 μm, and is comparable to the mean inter-observer variability ( 7.81±2.56 μm). 2) The true positive volume fraction (TPVF), false positive volume fraction (FPVF) and positive predicative value (PPV) for PED volume segmentation are 87.1%, 0.37%, and 81.2%, respectively. 3) The average running time is 220 s for OCT data of 512 × 64 × 480 voxels.