Multi-layer fast level set segmentation for macular OCT

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Segmenting optical coherence tomography (OCT) images of the retina is important in the diagnosis, staging, and tracking of ophthalmological diseases. Whereas automatic segmentation methods are typically much faster than manual segmentation, they may still take several minutes to segment a three-dimensional macular scan, and this can be prohibitive for routine clinical application. In this paper, we propose a fast, multi-layer macular OCT segmentation method based on a fast level set method. In our framework, the boundary evolution operations are computationally fast, are specific to each boundary between retinal layers, guarantee proper layer ordering, and avoid level set computation during evolution. Subvoxel resolution is achieved by reconstructing the level set functions after convergence. Experiments demonstrate that our method reduces the computation expense by 90% compared to graph-based methods and produces comparable accuracy to both graph-based and level set retinal OCT segmentation methods.

Original languageEnglish (US)
Title of host publication2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018
PublisherIEEE Computer Society
Pages1445-1448
Number of pages4
Volume2018-April
ISBN (Electronic)9781538636367
DOIs
StatePublished - May 23 2018
Event15th IEEE International Symposium on Biomedical Imaging, ISBI 2018 - Washington, United States
Duration: Apr 4 2018Apr 7 2018

Other

Other15th IEEE International Symposium on Biomedical Imaging, ISBI 2018
CountryUnited States
CityWashington
Period4/4/184/7/18

Fingerprint

Optical tomography
Optical Coherence Tomography
Retina
Experiments

Keywords

  • Fast level set method
  • Multi-object segmentation
  • OCT
  • Topology preservation

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Liu, Y., Carass, A., Solomon, S., Saidha, S., Calabresi, P., & Prince, J. L. (2018). Multi-layer fast level set segmentation for macular OCT. In 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018 (Vol. 2018-April, pp. 1445-1448). IEEE Computer Society. https://doi.org/10.1109/ISBI.2018.8363844

Multi-layer fast level set segmentation for macular OCT. / Liu, Yihao; Carass, Aaron; Solomon, Sharon; Saidha, Shiv; Calabresi, Peter; Prince, Jerry Ladd.

2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. Vol. 2018-April IEEE Computer Society, 2018. p. 1445-1448.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Liu, Y, Carass, A, Solomon, S, Saidha, S, Calabresi, P & Prince, JL 2018, Multi-layer fast level set segmentation for macular OCT. in 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. vol. 2018-April, IEEE Computer Society, pp. 1445-1448, 15th IEEE International Symposium on Biomedical Imaging, ISBI 2018, Washington, United States, 4/4/18. https://doi.org/10.1109/ISBI.2018.8363844
Liu Y, Carass A, Solomon S, Saidha S, Calabresi P, Prince JL. Multi-layer fast level set segmentation for macular OCT. In 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. Vol. 2018-April. IEEE Computer Society. 2018. p. 1445-1448 https://doi.org/10.1109/ISBI.2018.8363844
Liu, Yihao ; Carass, Aaron ; Solomon, Sharon ; Saidha, Shiv ; Calabresi, Peter ; Prince, Jerry Ladd. / Multi-layer fast level set segmentation for macular OCT. 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. Vol. 2018-April IEEE Computer Society, 2018. pp. 1445-1448
@inproceedings{f0c99cdef6f049ba9e87251eef235703,
title = "Multi-layer fast level set segmentation for macular OCT",
abstract = "Segmenting optical coherence tomography (OCT) images of the retina is important in the diagnosis, staging, and tracking of ophthalmological diseases. Whereas automatic segmentation methods are typically much faster than manual segmentation, they may still take several minutes to segment a three-dimensional macular scan, and this can be prohibitive for routine clinical application. In this paper, we propose a fast, multi-layer macular OCT segmentation method based on a fast level set method. In our framework, the boundary evolution operations are computationally fast, are specific to each boundary between retinal layers, guarantee proper layer ordering, and avoid level set computation during evolution. Subvoxel resolution is achieved by reconstructing the level set functions after convergence. Experiments demonstrate that our method reduces the computation expense by 90{\%} compared to graph-based methods and produces comparable accuracy to both graph-based and level set retinal OCT segmentation methods.",
keywords = "Fast level set method, Multi-object segmentation, OCT, Topology preservation",
author = "Yihao Liu and Aaron Carass and Sharon Solomon and Shiv Saidha and Peter Calabresi and Prince, {Jerry Ladd}",
year = "2018",
month = "5",
day = "23",
doi = "10.1109/ISBI.2018.8363844",
language = "English (US)",
volume = "2018-April",
pages = "1445--1448",
booktitle = "2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Multi-layer fast level set segmentation for macular OCT

AU - Liu, Yihao

AU - Carass, Aaron

AU - Solomon, Sharon

AU - Saidha, Shiv

AU - Calabresi, Peter

AU - Prince, Jerry Ladd

PY - 2018/5/23

Y1 - 2018/5/23

N2 - Segmenting optical coherence tomography (OCT) images of the retina is important in the diagnosis, staging, and tracking of ophthalmological diseases. Whereas automatic segmentation methods are typically much faster than manual segmentation, they may still take several minutes to segment a three-dimensional macular scan, and this can be prohibitive for routine clinical application. In this paper, we propose a fast, multi-layer macular OCT segmentation method based on a fast level set method. In our framework, the boundary evolution operations are computationally fast, are specific to each boundary between retinal layers, guarantee proper layer ordering, and avoid level set computation during evolution. Subvoxel resolution is achieved by reconstructing the level set functions after convergence. Experiments demonstrate that our method reduces the computation expense by 90% compared to graph-based methods and produces comparable accuracy to both graph-based and level set retinal OCT segmentation methods.

AB - Segmenting optical coherence tomography (OCT) images of the retina is important in the diagnosis, staging, and tracking of ophthalmological diseases. Whereas automatic segmentation methods are typically much faster than manual segmentation, they may still take several minutes to segment a three-dimensional macular scan, and this can be prohibitive for routine clinical application. In this paper, we propose a fast, multi-layer macular OCT segmentation method based on a fast level set method. In our framework, the boundary evolution operations are computationally fast, are specific to each boundary between retinal layers, guarantee proper layer ordering, and avoid level set computation during evolution. Subvoxel resolution is achieved by reconstructing the level set functions after convergence. Experiments demonstrate that our method reduces the computation expense by 90% compared to graph-based methods and produces comparable accuracy to both graph-based and level set retinal OCT segmentation methods.

KW - Fast level set method

KW - Multi-object segmentation

KW - OCT

KW - Topology preservation

UR - http://www.scopus.com/inward/record.url?scp=85048125753&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048125753&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2018.8363844

DO - 10.1109/ISBI.2018.8363844

M3 - Conference contribution

AN - SCOPUS:85048125753

VL - 2018-April

SP - 1445

EP - 1448

BT - 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018

PB - IEEE Computer Society

ER -