Patch-shuffle-based semi-supervised segmentation of bone computed tomography via consistent learning

Li, X; Peng, Y; Xu, M

Patch-shuffle-based semi-supervised segmentation of bone computed tomography via consistent learning

Li, X Peng, Y Xu, M

Permalink

Publisher:: ELSEVIER SCI LTD
Publication Type:: Journal Article
Citation:: Biomedical Signal Processing and Control, 2023, 80
Issue Date:: 2023-02-01

Closed Access

	Filename	Description	Size
	Patch shuffle based semisupervised segmentation of bone computed tomography via consistent learning.pdf	Published version	2.71 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	Li, X
dc.contributor.author	Peng, Y
dc.contributor.author	Xu, M https://orcid.org/0000-0001-9581-8849
dc.date.accessioned	2024-01-30T04:31:17Z
dc.date.available	2024-01-30T04:31:17Z
dc.date.issued	2023-02-01
dc.identifier.citation	Biomedical Signal Processing and Control, 2023, 80
dc.identifier.issn	1746-8094
dc.identifier.issn	1746-8108
dc.identifier.uri	http://hdl.handle.net/10453/175069
dc.description.abstract	Bone segmentation is essential in Computed Tomography (CT) imaging, which assists physicians in diagnosing, planning operations, and evaluating treatment effects. A recent trend is to apply deep neural networks for bone segmentation in CT slices. However, training a feasible segmentation model often requires a large number of annotated CT slices. The annotation procedure is often laborious and time-consuming. This paper proposed a novel semi-supervised learning method for training a bone segmentation model in CT images. A patch-shuffle-based data augmentation method was proposed by leveraging the unique bone structures in CT. To utilize the unlabeled CT slices, we employed a consistent learning loss between the feature of the original CT slice and the corresponding patch-shuffled CT slice. This encouraged the model to generate the same feature on each corresponding pixel in the two kinds of data. We validated the proposed method on three CT datasets of different image qualities and different anatomies: wrist, foot, chest, head, abdomen, and limb. The experiment results on the three bone CT datasets demonstrated the outperformance of our proposed method over the other semi-supervised methods.
dc.language	English
dc.publisher	ELSEVIER SCI LTD
dc.relation	Department of Industry, Innovation and ScienceICG001467
dc.relation.ispartof	Biomedical Signal Processing and Control
dc.relation.isbasedon	10.1016/j.bspc.2022.104239
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0903 Biomedical Engineering, 0906 Electrical and Electronic Engineering, 1004 Medical Biotechnology
dc.subject.classification	Biomedical Engineering
dc.subject.classification	3006 Food sciences
dc.subject.classification	4003 Biomedical engineering
dc.title	Patch-shuffle-based semi-supervised segmentation of bone computed tomography via consistent learning
dc.type	Journal Article
utslib.citation.volume	80
utslib.for	0903 Biomedical Engineering
utslib.for	0906 Electrical and Electronic Engineering
utslib.for	1004 Medical Biotechnology
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/Strength - INEXT - Innovation in IT Services and Applications
pubs.organisational-group	University of Technology Sydney/Strength - GBDTC - Global Big Data Technologies
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
utslib.copyright.status	closed_access	*
dc.date.updated	2024-01-30T04:31:16Z
pubs.publication-status	Published
pubs.volume	80

Abstract:

Bone segmentation is essential in Computed Tomography (CT) imaging, which assists physicians in diagnosing, planning operations, and evaluating treatment effects. A recent trend is to apply deep neural networks for bone segmentation in CT slices. However, training a feasible segmentation model often requires a large number of annotated CT slices. The annotation procedure is often laborious and time-consuming. This paper proposed a novel semi-supervised learning method for training a bone segmentation model in CT images. A patch-shuffle-based data augmentation method was proposed by leveraging the unique bone structures in CT. To utilize the unlabeled CT slices, we employed a consistent learning loss between the feature of the original CT slice and the corresponding patch-shuffled CT slice. This encouraged the model to generate the same feature on each corresponding pixel in the two kinds of data. We validated the proposed method on three CT datasets of different image qualities and different anatomies: wrist, foot, chest, head, abdomen, and limb. The experiment results on the three bone CT datasets demonstrated the outperformance of our proposed method over the other semi-supervised methods.

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

http://hdl.handle.net/10453/175069