SSP-REGULARIZER: A STAR SHAPE PRIOR BASED REGULARIZER FOR VESSEL LUMEN SEGMENTATION IN OCT IMAGES

Chen Zhao; HUAIZHONG ZHANG; Junyuan Wang; Fuqiang Liu

doi:10.1109/ICIP46576.2022.9897922

SSP-REGULARIZER: A STAR SHAPE PRIOR BASED REGULARIZER FOR VESSEL LUMEN SEGMENTATION IN OCT IMAGES

Chen Zhao, HUAIZHONG ZHANG, Junyuan Wang, Fuqiang Liu

Computer Science

Tongji University

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding (ISBN) › peer-review

109 Downloads (Pure)

Abstract

Optical coherence tomography (OCT) is widely used in high resolution imaging of biological tissues, which can help diagnose coronary heart disease by segmenting the vessel
lumen at the pixel-level. However, the lumen shape geometry is not well used in the state-of-the-art techniques for OCT image segmentation, especially the data-driven methods, leaving much room for performance improvement if some geometric features could be exploited to provide prior information. Thanks to the star shape geometry of vessel lumen, in this paper, a new Star Shape Prior based Regularizer (SSP-Regularizer) is proposed to improve segmentation performance. To validate its effectiveness, the proposed SSPRegularizer is applied to improve the optimization scheme used in Mask-RCNN for vessel lumen segmentation. Experimental results show that superior performance is achieved
with SSP-Regularizer, indicating its potentials in OCT imagery and optimization schemes.

Original language	English
Title of host publication	2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings
Place of Publication	IEEE
Publisher	IEEE Computer Society
Pages	3106-3110
Number of pages	5
ISBN (Electronic)	9781665496216
ISBN (Print)	9781665496209
DOIs	https://doi.org/10.1109/ICIP46576.2022.9897922
Publication status	Published - 18 Oct 2022

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
ISSN (Print)	1522-4880

Keywords

Star shape prior
vessel lumen segmentation
optical coherence tomography
SSP-Regularizer
Mask-RCNN

Access to Document

10.1109/ICIP46576.2022.9897922

ICIP-finalAccepted author manuscript, 2.88 MBLicence: CC BY-NC-ND

Cite this

Zhao, C., ZHANG, HUAIZHONG., Wang, J., & Liu, F. (2022). SSP-REGULARIZER: A STAR SHAPE PRIOR BASED REGULARIZER FOR VESSEL LUMEN SEGMENTATION IN OCT IMAGES. In 2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings (pp. 3106-3110). (Proceedings - International Conference on Image Processing, ICIP). IEEE Computer Society. https://doi.org/10.1109/ICIP46576.2022.9897922

@inproceedings{4d465439f324497e89106f88b4cef9ae,

title = "SSP-REGULARIZER: A STAR SHAPE PRIOR BASED REGULARIZER FOR VESSEL LUMEN SEGMENTATION IN OCT IMAGES",

abstract = "Optical coherence tomography (OCT) is widely used in high resolution imaging of biological tissues, which can help diagnose coronary heart disease by segmenting the vessellumen at the pixel-level. However, the lumen shape geometry is not well used in the state-of-the-art techniques for OCT image segmentation, especially the data-driven methods, leaving much room for performance improvement if some geometric features could be exploited to provide prior information. Thanks to the star shape geometry of vessel lumen, in this paper, a new Star Shape Prior based Regularizer (SSP-Regularizer) is proposed to improve segmentation performance. To validate its effectiveness, the proposed SSPRegularizer is applied to improve the optimization scheme used in Mask-RCNN for vessel lumen segmentation. Experimental results show that superior performance is achievedwith SSP-Regularizer, indicating its potentials in OCT imagery and optimization schemes.",

keywords = "Star shape prior, vessel lumen segmentation, optical coherence tomography, SSP-Regularizer, Mask-RCNN",

author = "Chen Zhao and HUAIZHONG ZHANG and Junyuan Wang and Fuqiang Liu",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.",

year = "2022",

month = oct,

day = "18",

doi = "10.1109/ICIP46576.2022.9897922",

language = "English",

isbn = "9781665496209",

series = "Proceedings - International Conference on Image Processing, ICIP",

publisher = "IEEE Computer Society",

pages = "3106--3110",

booktitle = "2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings",

address = "United States",

}

Zhao, C, ZHANG, HUAIZHONG, Wang, J & Liu, F 2022, SSP-REGULARIZER: A STAR SHAPE PRIOR BASED REGULARIZER FOR VESSEL LUMEN SEGMENTATION IN OCT IMAGES. in 2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings. Proceedings - International Conference on Image Processing, ICIP, IEEE Computer Society, IEEE, pp. 3106-3110. https://doi.org/10.1109/ICIP46576.2022.9897922

SSP-REGULARIZER: A STAR SHAPE PRIOR BASED REGULARIZER FOR VESSEL LUMEN SEGMENTATION IN OCT IMAGES. / Zhao, Chen; ZHANG, HUAIZHONG; Wang, Junyuan et al.
2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings. IEEE: IEEE Computer Society, 2022. p. 3106-3110 (Proceedings - International Conference on Image Processing, ICIP).

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding (ISBN) › peer-review

TY - GEN

T1 - SSP-REGULARIZER: A STAR SHAPE PRIOR BASED REGULARIZER FOR VESSEL LUMEN SEGMENTATION IN OCT IMAGES

AU - Zhao, Chen

AU - ZHANG, HUAIZHONG

AU - Wang, Junyuan

AU - Liu, Fuqiang

PY - 2022/10/18

Y1 - 2022/10/18

N2 - Optical coherence tomography (OCT) is widely used in high resolution imaging of biological tissues, which can help diagnose coronary heart disease by segmenting the vessellumen at the pixel-level. However, the lumen shape geometry is not well used in the state-of-the-art techniques for OCT image segmentation, especially the data-driven methods, leaving much room for performance improvement if some geometric features could be exploited to provide prior information. Thanks to the star shape geometry of vessel lumen, in this paper, a new Star Shape Prior based Regularizer (SSP-Regularizer) is proposed to improve segmentation performance. To validate its effectiveness, the proposed SSPRegularizer is applied to improve the optimization scheme used in Mask-RCNN for vessel lumen segmentation. Experimental results show that superior performance is achievedwith SSP-Regularizer, indicating its potentials in OCT imagery and optimization schemes.

AB - Optical coherence tomography (OCT) is widely used in high resolution imaging of biological tissues, which can help diagnose coronary heart disease by segmenting the vessellumen at the pixel-level. However, the lumen shape geometry is not well used in the state-of-the-art techniques for OCT image segmentation, especially the data-driven methods, leaving much room for performance improvement if some geometric features could be exploited to provide prior information. Thanks to the star shape geometry of vessel lumen, in this paper, a new Star Shape Prior based Regularizer (SSP-Regularizer) is proposed to improve segmentation performance. To validate its effectiveness, the proposed SSPRegularizer is applied to improve the optimization scheme used in Mask-RCNN for vessel lumen segmentation. Experimental results show that superior performance is achievedwith SSP-Regularizer, indicating its potentials in OCT imagery and optimization schemes.

KW - Star shape prior

KW - vessel lumen segmentation

KW - optical coherence tomography

KW - SSP-Regularizer

KW - Mask-RCNN

UR - https://ieeexplore.ieee.org/document/9897922

UR - http://www.scopus.com/inward/record.url?scp=85146695494&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85146695494&partnerID=8YFLogxK

U2 - 10.1109/ICIP46576.2022.9897922

DO - 10.1109/ICIP46576.2022.9897922

M3 - Conference proceeding (ISBN)

SN - 9781665496209

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 3106

EP - 3110

BT - 2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings

PB - IEEE Computer Society

CY - IEEE

ER -

Zhao C, ZHANG HUAIZHONG, Wang J, Liu F. SSP-REGULARIZER: A STAR SHAPE PRIOR BASED REGULARIZER FOR VESSEL LUMEN SEGMENTATION IN OCT IMAGES. In 2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings. IEEE: IEEE Computer Society. 2022. p. 3106-3110. (Proceedings - International Conference on Image Processing, ICIP). Epub 2022 Oct 18. doi: 10.1109/ICIP46576.2022.9897922

SSP-REGULARIZER: A STAR SHAPE PRIOR BASED REGULARIZER FOR VESSEL LUMEN SEGMENTATION IN OCT IMAGES

Abstract

Publication series

Keywords

Access to Document

Other files and links

Fingerprint

Exploration and Enhancement of Land Management Strategies Using Hyperspectral Imagery and Big Data Analytics

Cite this

SSP-REGULARIZER: A STAR SHAPE PRIOR BASED REGULARIZER FOR VESSEL LUMEN SEGMENTATION IN OCT IMAGES

Abstract

Publication series

Keywords

Access to Document

Other files and links

Fingerprint

Projects

Exploration and Enhancement of Land Management Strategies Using Hyperspectral Imagery and Big Data Analytics

Cite this