Automated boundary detection of the optic disc and layer segmentation of the peripapillary retina in volumetric structural and angiographic optical coherence tomography

Pengxiao Zang, Simon S. Gao, Thomas Hwang, Christina Flaxel, David Wilson, John Morrison, David Huang, Dengwang Li, Jia Yali

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

To improve optic disc boundary detection and peripapillary retinal layer segmentation, we propose an automated approach for structural and angiographic optical coherence tomography. The algorithm was performed on radial cross-sectional B-scans. The disc boundary was detected by searching for the position of Bruch’s membrane opening, and retinal layer boundaries were detected using a dynamic programming-based graph search algorithm on each B-scan without the disc region. A comparison of the disc boundary using our method with that determined by manual delineation showed good accuracy, with an average Dice similarity coefficient ≥0.90 in healthy eyes and eyes with diabetic retinopathy and glaucoma. The layer segmentation accuracy in the same cases was on average less than one pixel (3.13 μm).

Original languageEnglish (US)
Article number#282471
Pages (from-to)1306-1318
Number of pages13
JournalBiomedical Optics Express
Volume8
Issue number3
DOIs
StatePublished - Mar 1 2017

Fingerprint

retina
edge detection
Optic Disk
Optical Coherence Tomography
Retina
tomography
optics
Bruch Membrane
Diabetic Retinopathy
Glaucoma
glaucoma
dynamic programming
delineation
boundary layers
pixels
membranes
coefficients

ASJC Scopus subject areas

  • Biotechnology
  • Atomic and Molecular Physics, and Optics

Cite this

@article{3816cbde5c4749de9ab57412994bd68c,
title = "Automated boundary detection of the optic disc and layer segmentation of the peripapillary retina in volumetric structural and angiographic optical coherence tomography",
abstract = "To improve optic disc boundary detection and peripapillary retinal layer segmentation, we propose an automated approach for structural and angiographic optical coherence tomography. The algorithm was performed on radial cross-sectional B-scans. The disc boundary was detected by searching for the position of Bruch’s membrane opening, and retinal layer boundaries were detected using a dynamic programming-based graph search algorithm on each B-scan without the disc region. A comparison of the disc boundary using our method with that determined by manual delineation showed good accuracy, with an average Dice similarity coefficient ≥0.90 in healthy eyes and eyes with diabetic retinopathy and glaucoma. The layer segmentation accuracy in the same cases was on average less than one pixel (3.13 μm).",
author = "Pengxiao Zang and Gao, {Simon S.} and Thomas Hwang and Christina Flaxel and David Wilson and John Morrison and David Huang and Dengwang Li and Jia Yali",
year = "2017",
month = "3",
day = "1",
doi = "10.1364/BOE.8.001306",
language = "English (US)",
volume = "8",
pages = "1306--1318",
journal = "Biomedical Optics Express",
issn = "2156-7085",
publisher = "The Optical Society",
number = "3",

}

TY - JOUR

T1 - Automated boundary detection of the optic disc and layer segmentation of the peripapillary retina in volumetric structural and angiographic optical coherence tomography

AU - Zang, Pengxiao

AU - Gao, Simon S.

AU - Hwang, Thomas

AU - Flaxel, Christina

AU - Wilson, David

AU - Morrison, John

AU - Huang, David

AU - Li, Dengwang

AU - Yali, Jia

PY - 2017/3/1

Y1 - 2017/3/1

N2 - To improve optic disc boundary detection and peripapillary retinal layer segmentation, we propose an automated approach for structural and angiographic optical coherence tomography. The algorithm was performed on radial cross-sectional B-scans. The disc boundary was detected by searching for the position of Bruch’s membrane opening, and retinal layer boundaries were detected using a dynamic programming-based graph search algorithm on each B-scan without the disc region. A comparison of the disc boundary using our method with that determined by manual delineation showed good accuracy, with an average Dice similarity coefficient ≥0.90 in healthy eyes and eyes with diabetic retinopathy and glaucoma. The layer segmentation accuracy in the same cases was on average less than one pixel (3.13 μm).

AB - To improve optic disc boundary detection and peripapillary retinal layer segmentation, we propose an automated approach for structural and angiographic optical coherence tomography. The algorithm was performed on radial cross-sectional B-scans. The disc boundary was detected by searching for the position of Bruch’s membrane opening, and retinal layer boundaries were detected using a dynamic programming-based graph search algorithm on each B-scan without the disc region. A comparison of the disc boundary using our method with that determined by manual delineation showed good accuracy, with an average Dice similarity coefficient ≥0.90 in healthy eyes and eyes with diabetic retinopathy and glaucoma. The layer segmentation accuracy in the same cases was on average less than one pixel (3.13 μm).

UR - http://www.scopus.com/inward/record.url?scp=85016145674&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016145674&partnerID=8YFLogxK

U2 - 10.1364/BOE.8.001306

DO - 10.1364/BOE.8.001306

M3 - Article

AN - SCOPUS:85016145674

VL - 8

SP - 1306

EP - 1318

JO - Biomedical Optics Express

JF - Biomedical Optics Express

SN - 2156-7085

IS - 3

M1 - #282471

ER -