A Generative Model for OCT Retinal Layer Segmentation by Groupwise Curve Alignment

Wenjun Duan, Yuanjie Zheng, Yanhui Ding, Sujuan Hou, Yufang Tang, Yan Xu, Maoling Qin, Jianfeng Wu, Dinggang Shen, Hongsheng Bi

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

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.

Original languageEnglish
JournalIEEE Access
DOIs
Publication statusAccepted/In press - 2018 Apr 16

Fingerprint

Optical tomography
Thickness measurement
Personnel

Keywords

  • Diseases
  • dynamic time warping
  • Electronic mail
  • Heuristic algorithms
  • Image segmentation
  • joint curve matching
  • Manuals
  • Optical Coherence Tomography (OCT)
  • Retina
  • retinal layer segmentation
  • Thickness measurement

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Cite this

Duan, W., Zheng, Y., Ding, Y., Hou, S., Tang, Y., Xu, Y., ... Bi, H. (Accepted/In press). A Generative Model for OCT Retinal Layer Segmentation by Groupwise Curve Alignment. IEEE Access. https://doi.org/10.1109/ACCESS.2018.2825397

A Generative Model for OCT Retinal Layer Segmentation by Groupwise Curve Alignment. / Duan, Wenjun; Zheng, Yuanjie; Ding, Yanhui; Hou, Sujuan; Tang, Yufang; Xu, Yan; Qin, Maoling; Wu, Jianfeng; Shen, Dinggang; Bi, Hongsheng.

In: IEEE Access, 16.04.2018.

Research output: Contribution to journalArticle

Duan, Wenjun ; Zheng, Yuanjie ; Ding, Yanhui ; Hou, Sujuan ; Tang, Yufang ; Xu, Yan ; Qin, Maoling ; Wu, Jianfeng ; Shen, Dinggang ; Bi, Hongsheng. / A Generative Model for OCT Retinal Layer Segmentation by Groupwise Curve Alignment. In: IEEE Access. 2018.
@article{841fd7862e8942e0abc7f754ef9ba1be,
title = "A Generative Model for OCT Retinal Layer Segmentation by Groupwise Curve Alignment",
abstract = "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.",
keywords = "Diseases, dynamic time warping, Electronic mail, Heuristic algorithms, Image segmentation, joint curve matching, Manuals, Optical Coherence Tomography (OCT), Retina, retinal layer segmentation, Thickness measurement",
author = "Wenjun Duan and Yuanjie Zheng and Yanhui Ding and Sujuan Hou and Yufang Tang and Yan Xu and Maoling Qin and Jianfeng Wu and Dinggang Shen and Hongsheng Bi",
year = "2018",
month = "4",
day = "16",
doi = "10.1109/ACCESS.2018.2825397",
language = "English",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

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

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 - Diseases

KW - dynamic time warping

KW - Electronic mail

KW - Heuristic algorithms

KW - Image segmentation

KW - joint curve matching

KW - Manuals

KW - Optical Coherence Tomography (OCT)

KW - Retina

KW - retinal layer segmentation

KW - Thickness measurement

UR - http://www.scopus.com/inward/record.url?scp=85045733688&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045733688&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2018.2825397

DO - 10.1109/ACCESS.2018.2825397

M3 - Article

AN - SCOPUS:85045733688

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

ER -