TY - JOUR
T1 - A Generative Model for OCT Retinal Layer Segmentation by Groupwise Curve Alignment
AU - Duan, Wenjun
AU - Zheng, Yuanjie
AU - Ding, Yanhui
AU - Hou, Sujuan
AU - Tang, Yufang
AU - Xu, Yan
AU - Qin, Maoling
AU - Wu, Jianfeng
AU - Shen, Dinggang
AU - Bi, Hongsheng
N1 - Funding Information:
This work was supported in part by the Natural Science Foundation of China under Grant 61572300 and Grant 61702313, in part by the Natural Science Foundation of Shandong Province, China, under Grant ZR2014FM001 and Grant ZR2016FQ20, in part by the Taishan Scholar Program of Shandong Province, China, under Grant TSHW201502038, in part by the Primary Research and Development Plan of Shandong Province under Grant 2017GGX10112, in part by the Postdoctoral Science Foundation of China under Grant 2017M612338, and in part by the Shandong Science and Technology Plan Project under Grant J17KB177.
Publisher Copyright:
© 2013 IEEE.
PY - 2018/4/16
Y1 - 2018/4/16
N2 - Retinal layer segmentation from optical coherence tomography (OCT) is of fundamental importance for measuring retinal layer thicknesses. These thickness measurements have been shown to correlate well with the severity of different ocular diseases; hence, they provide useful diagnostic information concerning diseases. Manual segmentation of retinal layers from OCT remains dominant in ophthalmological clinical practice but has serious drawbacks: it is time consuming, labor intensive, and results in inter/intra-rater variations. Computer aided segmentation has attracted intensive research attention because it holds the potential not only to provide repeatable, quantitative, and objective results but also to reduce the time and effort required to delineate the retinal layers. However, most of the existing computer based retinal layer segmentation techniques focus on segmenting specific layers by exploring their unique characteristics; thus, they can fail to segment a retinal layer that is totally different. In this paper, we propose a generative retinal layer segmentation method based on groupwise curve alignment that combines the capabilities of segmenting different retinal layers into a unified framework. This method is unique for both its accuracy and its ability to segment any retinal layer without any special modifications. We experimentally validate that the proposed method outperforms a representative state-of-the-art technique by using images of both normal healthy eyes and diseased eyes. Our method is potentially useful in a large variety of practical applications involving retinal layer segmentation from OCT.
AB - Retinal layer segmentation from optical coherence tomography (OCT) is of fundamental importance for measuring retinal layer thicknesses. These thickness measurements have been shown to correlate well with the severity of different ocular diseases; hence, they provide useful diagnostic information concerning diseases. Manual segmentation of retinal layers from OCT remains dominant in ophthalmological clinical practice but has serious drawbacks: it is time consuming, labor intensive, and results in inter/intra-rater variations. Computer aided segmentation has attracted intensive research attention because it holds the potential not only to provide repeatable, quantitative, and objective results but also to reduce the time and effort required to delineate the retinal layers. However, most of the existing computer based retinal layer segmentation techniques focus on segmenting specific layers by exploring their unique characteristics; thus, they can fail to segment a retinal layer that is totally different. In this paper, we propose a generative retinal layer segmentation method based on groupwise curve alignment that combines the capabilities of segmenting different retinal layers into a unified framework. This method is unique for both its accuracy and its ability to segment any retinal layer without any special modifications. We experimentally validate that the proposed method outperforms a representative state-of-the-art technique by using images of both normal healthy eyes and diseased eyes. Our method is potentially useful in a large variety of practical applications involving retinal layer segmentation from OCT.
KW - Optical coherence tomography (OCT)
KW - dynamic time warping
KW - joint curve matching
KW - retinal layer segmentation
UR - http://www.scopus.com/inward/record.url?scp=85045733688&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2018.2825397
DO - 10.1109/ACCESS.2018.2825397
M3 - Article
AN - SCOPUS:85045733688
SN - 2169-3536
VL - 6
SP - 25130
EP - 25141
JO - IEEE Access
JF - IEEE Access
ER -