Locally-adaptive loosely-coupled level sets for retinal layer and fluid segmentation in subjects with central serous retinopathy

Jelena Novosel; Ziyuan Wang; Henk De Jong; Mirjam Van Velthoven; Koen Vermeer; Lucas J. Van Vliet

doi:10.1109/ISBI.2016.7493363

Locally-adaptive loosely-coupled level sets for retinal layer and fluid segmentation in subjects with central serous retinopathy

Jelena Novosel, Ziyuan Wang, Henk De Jong, Mirjam Van Velthoven, Koen Vermeer, Lucas J. Van Vliet

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

34 Citations (Scopus)

Abstract

We present a locally-adaptive approach to segment the fluid and the interfaces between retinal layers in eyes affected by central serous retinopathy based on loosely-coupled level sets. The approach exploits the local attenuation coefficient differences of layers around an interface and introduces auxiliary interfaces to delineate the fluid. Thus, it can handle abrupt attenuation coefficient variations and topology-disrupting anomalies. The method was applied to in-vivo images of retinas acquired by optical coherence tomography. A quantitative comparison with manual annotations shows the method's high accuracy: we obtained a mean absolute deviation for the interfaces of 3.7-8.9 βm (1-2 pixels) and a Dice coefficient for the fluid segmentation of 0.96.

Original language	English
Title of host publication	Proceedings of the 2016 IEEE International Symposium on Biomedical Imaging (ISBI 2016)
Subtitle of host publication	From Nano to Macro
Place of Publication	Piscataway
Publisher	IEEE
Pages	702-705
Number of pages	4
ISBN (Electronic)	978-1-4799-2349-6
ISBN (Print)	978-1-4799-2350-2
DOIs	https://doi.org/10.1109/ISBI.2016.7493363
Publication status	Published - 15 Jun 2016
Event	2016 IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 - Prague, Czech Republic Duration: 13 Apr 2016 → 16 Apr 2016

Conference

Conference	2016 IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016
Country/Territory	Czech Republic
City	Prague
Period	13/04/16 → 16/04/16

Keywords

Attenuation coefficients
OCT

Access to Document

10.1109/ISBI.2016.7493363

Cite this

Novosel, J., Wang, Z., De Jong, H., Van Velthoven, M., Vermeer, K., & Van Vliet, L. J. (2016). Locally-adaptive loosely-coupled level sets for retinal layer and fluid segmentation in subjects with central serous retinopathy. In Proceedings of the 2016 IEEE International Symposium on Biomedical Imaging (ISBI 2016): From Nano to Macro (pp. 702-705). Article 7493363 IEEE. https://doi.org/10.1109/ISBI.2016.7493363

@inproceedings{725c06719177490bb5113ba69e9e8bd4,

title = "Locally-adaptive loosely-coupled level sets for retinal layer and fluid segmentation in subjects with central serous retinopathy",

abstract = "We present a locally-adaptive approach to segment the fluid and the interfaces between retinal layers in eyes affected by central serous retinopathy based on loosely-coupled level sets. The approach exploits the local attenuation coefficient differences of layers around an interface and introduces auxiliary interfaces to delineate the fluid. Thus, it can handle abrupt attenuation coefficient variations and topology-disrupting anomalies. The method was applied to in-vivo images of retinas acquired by optical coherence tomography. A quantitative comparison with manual annotations shows the method's high accuracy: we obtained a mean absolute deviation for the interfaces of 3.7-8.9 βm (1-2 pixels) and a Dice coefficient for the fluid segmentation of 0.96.",

keywords = "Attenuation coefficients, OCT",

author = "Jelena Novosel and Ziyuan Wang and {De Jong}, Henk and {Van Velthoven}, Mirjam and Koen Vermeer and {Van Vliet}, {Lucas J.}",

year = "2016",

month = jun,

day = "15",

doi = "10.1109/ISBI.2016.7493363",

language = "English",

isbn = "978-1-4799-2350-2",

pages = "702--705",

booktitle = "Proceedings of the 2016 IEEE International Symposium on Biomedical Imaging (ISBI 2016)",

publisher = "IEEE",

address = "United States",

note = "2016 IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016 ; Conference date: 13-04-2016 Through 16-04-2016",

}

Novosel, J, Wang, Z, De Jong, H, Van Velthoven, M, Vermeer, K & Van Vliet, LJ 2016, Locally-adaptive loosely-coupled level sets for retinal layer and fluid segmentation in subjects with central serous retinopathy. in Proceedings of the 2016 IEEE International Symposium on Biomedical Imaging (ISBI 2016): From Nano to Macro., 7493363, IEEE, Piscataway, pp. 702-705, 2016 IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016, Prague, Czech Republic, 13/04/16. https://doi.org/10.1109/ISBI.2016.7493363

Locally-adaptive loosely-coupled level sets for retinal layer and fluid segmentation in subjects with central serous retinopathy. / Novosel, Jelena; Wang, Ziyuan; De Jong, Henk et al.
Proceedings of the 2016 IEEE International Symposium on Biomedical Imaging (ISBI 2016): From Nano to Macro. Piscataway: IEEE, 2016. p. 702-705 7493363.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Locally-adaptive loosely-coupled level sets for retinal layer and fluid segmentation in subjects with central serous retinopathy

AU - Novosel, Jelena

AU - Wang, Ziyuan

AU - De Jong, Henk

AU - Van Velthoven, Mirjam

AU - Vermeer, Koen

AU - Van Vliet, Lucas J.

PY - 2016/6/15

Y1 - 2016/6/15

N2 - We present a locally-adaptive approach to segment the fluid and the interfaces between retinal layers in eyes affected by central serous retinopathy based on loosely-coupled level sets. The approach exploits the local attenuation coefficient differences of layers around an interface and introduces auxiliary interfaces to delineate the fluid. Thus, it can handle abrupt attenuation coefficient variations and topology-disrupting anomalies. The method was applied to in-vivo images of retinas acquired by optical coherence tomography. A quantitative comparison with manual annotations shows the method's high accuracy: we obtained a mean absolute deviation for the interfaces of 3.7-8.9 βm (1-2 pixels) and a Dice coefficient for the fluid segmentation of 0.96.

AB - We present a locally-adaptive approach to segment the fluid and the interfaces between retinal layers in eyes affected by central serous retinopathy based on loosely-coupled level sets. The approach exploits the local attenuation coefficient differences of layers around an interface and introduces auxiliary interfaces to delineate the fluid. Thus, it can handle abrupt attenuation coefficient variations and topology-disrupting anomalies. The method was applied to in-vivo images of retinas acquired by optical coherence tomography. A quantitative comparison with manual annotations shows the method's high accuracy: we obtained a mean absolute deviation for the interfaces of 3.7-8.9 βm (1-2 pixels) and a Dice coefficient for the fluid segmentation of 0.96.

KW - Attenuation coefficients

KW - OCT

U2 - 10.1109/ISBI.2016.7493363

DO - 10.1109/ISBI.2016.7493363

M3 - Conference contribution

AN - SCOPUS:84978431947

SN - 978-1-4799-2350-2

SP - 702

EP - 705

BT - Proceedings of the 2016 IEEE International Symposium on Biomedical Imaging (ISBI 2016)

PB - IEEE

CY - Piscataway

T2 - 2016 IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016

Y2 - 13 April 2016 through 16 April 2016

ER -

Novosel J, Wang Z, De Jong H, Van Velthoven M, Vermeer K, Van Vliet LJ. Locally-adaptive loosely-coupled level sets for retinal layer and fluid segmentation in subjects with central serous retinopathy. In Proceedings of the 2016 IEEE International Symposium on Biomedical Imaging (ISBI 2016): From Nano to Macro. Piscataway: IEEE. 2016. p. 702-705. 7493363 doi: 10.1109/ISBI.2016.7493363

Locally-adaptive loosely-coupled level sets for retinal layer and fluid segmentation in subjects with central serous retinopathy

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this