Dual-task ultrasound spine transverse vertebrae segmentation network with contour regularization.

Lyu, J; Bi, X; Banerjee, Sunetra; Huang, Z; Leung, FHF; Lee, TT-Y; Yang, D-D; Zheng, Y-P; Ling, SH

Dual-task ultrasound spine transverse vertebrae segmentation network with contour regularization.

Lyu, J Bi, X Banerjee, Sunetra Huang, Z Leung, FHF Lee, TT-Y Yang, D-D Zheng, Y-P Ling, SH

Permalink

Publisher:: PERGAMON-ELSEVIER SCIENCE LTD
Publication Type:: Journal Article
Citation:: Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society, 2021, 89, pp. 101896
Issue Date:: 2021-04

Closed Access

	Filename	Description	Size
	Dual task_juan.pdf	Published version	5.39 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Lyu, J
dc.contributor.author	Bi, X
dc.contributor.author	Banerjee, Sunetra
dc.contributor.author	Huang, Z
dc.contributor.author	Leung, FHF
dc.contributor.author	Lee, TT-Y
dc.contributor.author	Yang, D-D
dc.contributor.author	Zheng, Y-P
dc.contributor.author	Ling, SH
dc.date.accessioned	2021-09-13T02:45:10Z
dc.date.available	2021-03-06
dc.date.available	2021-09-13T02:45:10Z
dc.date.issued	2021-04
dc.identifier.citation	Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society, 2021, 89, pp. 101896
dc.identifier.issn	0895-6111
dc.identifier.issn	1879-0771
dc.identifier.uri	http://hdl.handle.net/10453/150504
dc.description.abstract	3D ultrasound imaging has become one of the common diagnosis ways to assess scoliosis since it is radiation-free, real-time, and low-cost. Spine curvature angle measurement is an important step to assess scoliosis precisely. One way to calculate the angle is using the vertebrae features of the 2-D coronal images to identify the most tilted vertebrae. To do the measurement, the segmentation of the transverse vertebrae is an important step. In this paper, we propose a dual-task ultrasound transverse vertebrae segmentation network (D-TVNet) based on U-Net. First, we arrange an auxiliary shape regularization network to learn the contour segmentation of the bones. It improves the boundary segmentation and anti-interference ability of the U-Net by fusing some of the features of the auxiliary task and the main task. Then, we introduce the atrous spatial pyramid pooling (ASPP) module to the end of the down-sampling stage of the main task stream to improve the relative feature extraction ability. To further improve the boundary segmentation, we extendedly fuse the down-sampling output features of the auxiliary network in the ASPP. The experiment results show that the proposed D-TVNet achieves the best dice score of 86.68% and the mean dice score of 86.17% based on cross-validation, which is an improvement of 5.17% over the baseline U-Net. An automatic ultrasound spine bone segmentation network with promising results has been achieved.
dc.format	Print-Electronic
dc.language	eng
dc.publisher	PERGAMON-ELSEVIER SCIENCE LTD
dc.relation.ispartof	Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society
dc.relation.isbasedon	10.1016/j.compmedimag.2021.101896
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0903 Biomedical Engineering, 1103 Clinical Sciences
dc.subject.classification	Nuclear Medicine & Medical Imaging
dc.title	Dual-task ultrasound spine transverse vertebrae segmentation network with contour regularization.
dc.type	Journal Article
utslib.citation.volume	89
utslib.location.activity	United States
utslib.for	0903 Biomedical Engineering
utslib.for	1103 Clinical Sciences
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Biomedical Engineering
utslib.copyright.status	closed_access	*
dc.date.updated	2021-09-13T02:45:04Z
pubs.publication-status	Published
pubs.volume	89

Abstract:

3D ultrasound imaging has become one of the common diagnosis ways to assess scoliosis since it is radiation-free, real-time, and low-cost. Spine curvature angle measurement is an important step to assess scoliosis precisely. One way to calculate the angle is using the vertebrae features of the 2-D coronal images to identify the most tilted vertebrae. To do the measurement, the segmentation of the transverse vertebrae is an important step. In this paper, we propose a dual-task ultrasound transverse vertebrae segmentation network (D-TVNet) based on U-Net. First, we arrange an auxiliary shape regularization network to learn the contour segmentation of the bones. It improves the boundary segmentation and anti-interference ability of the U-Net by fusing some of the features of the auxiliary task and the main task. Then, we introduce the atrous spatial pyramid pooling (ASPP) module to the end of the down-sampling stage of the main task stream to improve the relative feature extraction ability. To further improve the boundary segmentation, we extendedly fuse the down-sampling output features of the auxiliary network in the ASPP. The experiment results show that the proposed D-TVNet achieves the best dice score of 86.68% and the mean dice score of 86.17% based on cross-validation, which is an improvement of 5.17% over the baseline U-Net. An automatic ultrasound spine bone segmentation network with promising results has been achieved.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/150504