Modeling the Probabilistic Distribution of Unlabeled Data for One-shot Medical Image Segmentation

Ding, Y; Yu, X; Yang, Y

Modeling the Probabilistic Distribution of Unlabeled Data for One-shot Medical Image Segmentation

Ding, Y Yu, X Yang, Y

Permalink

Publisher:: AAAI
Publication Type:: Conference Proceeding
Citation:: 2021, 35, (2), pp. 1246-1254
Issue Date:: 2021

Closed Access

	Filename	Description	Size
	16212-Article Text-19706-1-2-20210518.pdf	Published version	1.75 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	Ding, Y
dc.contributor.author	Yu, X
dc.contributor.author	Yang, Y https://orcid.org/0000-0002-0512-880X
dc.date	2021-02-02
dc.date.accessioned	2022-07-03T21:31:52Z
dc.date.available	2022-07-03T21:31:52Z
dc.date.issued	2021
dc.identifier.citation	2021, 35, (2), pp. 1246-1254
dc.identifier.isbn	978-1-57735-866-4
dc.identifier.issn	2159-5399
dc.identifier.issn	2374-3468
dc.identifier.uri	http://hdl.handle.net/10453/158571
dc.description.abstract	Existing image segmentation networks mainly leverage large-scale labeled datasets to attain high accuracy. However, labeling medical images is very expensive since it requires sophisticated expert knowledge. Thus, it is more desirable to employ only a few labeled data in pursuing high segmentation performance. In this paper, we develop a data augmentation method for one-shot brain magnetic resonance imaging (MRI) image segmentation which exploits only one labeled MRI image (named atlas) and a few unlabeled images. In particular, we propose to learn the probability distributions of deformations (including shapes and intensities) of different unlabeled MRI images with respect to the atlas via 3D variational autoencoders (VAEs). In this manner, our method is able to exploit the learned distributions of image deformations to generate new authentic brain MRI images, and the number of generated samples will be sufficient to train a deep segmentation network. Furthermore, we introduce a new standard segmentation benchmark to evaluate the generalization performance of a segmentation network through a cross-dataset setting (collected from different sources). Extensive experiments demonstrate that our method outperforms the state-of-the-art one-shot medical segmentation methods. Our code has been released at https://github.com/dyh127/Modeling-the-Probabilistic-Distribution-of-Unlabeled-Data.
dc.language	en
dc.publisher	AAAI
dc.relation.ispartof	Conference on Artificial Intelligence
dc.relation.ispartofseries	Proceedings of the AAAI Conference on Artificial Intelligence
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Modeling the Probabilistic Distribution of Unlabeled Data for One-shot Medical Image Segmentation
dc.type	Conference Proceeding
utslib.citation.volume	35
utslib.location.activity	Virtual
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 - AAII - Australian Artificial Intelligence Institute
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2022-07-03T21:31:50Z
pubs.finish-date	2021-02-09
pubs.issue	2
pubs.place-of-publication	USA
pubs.publication-status	Published
pubs.start-date	2021-02-02
pubs.volume	35
utslib.citation.issue	2
dc.location	USA

Abstract:

Existing image segmentation networks mainly leverage large-scale labeled datasets to attain high accuracy. However, labeling medical images is very expensive since it requires sophisticated expert knowledge. Thus, it is more desirable to employ only a few labeled data in pursuing high segmentation performance. In this paper, we develop a data augmentation method for one-shot brain magnetic resonance imaging (MRI) image segmentation which exploits only one labeled MRI image (named atlas) and a few unlabeled images. In particular, we propose to learn the probability distributions of deformations (including shapes and intensities) of different unlabeled MRI images with respect to the atlas via 3D variational autoencoders (VAEs). In this manner, our method is able to exploit the learned distributions of image deformations to generate new authentic brain MRI images, and the number of generated samples will be sufficient to train a deep segmentation network. Furthermore, we introduce a new standard segmentation benchmark to evaluate the generalization performance of a segmentation network through a cross-dataset setting (collected from different sources). Extensive experiments demonstrate that our method outperforms the state-of-the-art one-shot medical segmentation methods. Our code has been released at https://github.com/dyh127/Modeling-the-Probabilistic-Distribution-of-Unlabeled-Data.

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

http://hdl.handle.net/10453/158571