Paper Info
Title
Graph search: active appearance model based automated segmentation of retinal layers for optic nerve head centered OCT images.
Abstract
In this paper, a novel approach combining the active appearance model (AAM) and graph search is proposed to segment retinal layers for optic nerve head(ONH) centered optical coherence tomography(OCT) images. The method includes two parts: preprocessing and layer segmentation. During the preprocessing phase, images is first filtered for denoising, then the B-scans are flattened. During layer segmentation, the AAM is first used to obtain the coarse segmentation results. Then a multi-resolution GS-AAM algorithm is applied to further refine the results, in which AAM is efficiently integrated into the graph search segmentation process. The proposed method was tested on a dataset which contained113-D SD-OCT images, and compared to the manual tracings of two observers on all the volumetric scans. The overall mean border positioning error for layer segmentation was found to be7.09 +/- 6.18 mu m for normal subjects. It was comparable to the results of traditional graph search method (8.03 +/- 10.47 mu m) and mean inter- observer variability (6.35 +/- 6.93 mu m). The preliminary results demonstrated the feasibility and efficiency of the proposed method.
Year
DOI
Venue
2017
10.1117/12.2250168
Proceedings of SPIE
Keywords
Field
DocType
automated 3-D segmentation,Optical coherence tomography(OCT),retinal layers,Active Appearance Models(AAM),graph search
Noise reduction,Computer vision,Optical coherence tomography,Scale-space segmentation,Segmentation,Computer science,Optics,Active appearance model,Image segmentation,Preprocessor,Artificial intelligence,Optic nerve
Conference
Volume
ISSN
Citations 
10133
0277-786X
1
PageRank 
References 
Authors
0.37
6
7
Name
Order
Citations
PageRank
Enting Gao1272.17
Fei Shi28612.91
Weifang Zhu38515.92
Chao Jin4122.32
Min Sun5156.09
Hao-Yu Chen69715.08
XinJian Chen750253.39