Semi-supervised anatomical landmark detection via shape-regulated self-training

doi:10.1016/j.neucom.2021.10.109

	Semi-supervised anatomical landmark detection via shape-regulated self-training
	Chen, Runnan 1; Ma, Yuexin2 ; Liu, Lingjie 3; Chen, Nenglun 1; Cui, Zhiming 1; Wei, Guodong 4; Wang, Wenping 5
	2022-01-30
发表期刊	NEUROCOMPUTING
ISSN	0925-2312
EISSN	1872-8286
卷号	471 页码:335-345
发表状态	已发表
DOI	10.1016/j.neucom.2021.10.109
摘要	Well-annotated medical images are costly and sometimes even impossible to acquire, hindering landmark detection accuracy to some extent. Semi-supervised learning alleviates the reliance on large-scale annotated data by exploiting the unlabeled data to understand the population structure of anatomical landmarks. The global shape constraint is the inherent property of anatomical landmarks that provides valuable guidance for more consistent pseudo labelling of the unlabeled data, which is ignored in the previously semi-supervised methods. In this paper, we propose a model-agnostic shape-regulated self-training framework for semi-supervised landmark detection by fully considering the global shape constraint. Specifically, to ensure pseudo labels are reliable and consistent, a PCA-based shape model adjusts pseudo labels and eliminate abnormal ones. A novel Region Attention loss to make the network automatically focus on the structure consistent regions around pseudo labels. Extensive experiments show that our approach outperforms other semi-supervised methods and achieves the relative improvement of 3.8%, 6.1% and 6.3% on three medical image datasets. Furthermore, our framework is flexible and can be used as a plug-and-play module integrated into most superviseüd methods to improve performance further. © 2021 Elsevier B.V.
关键词	Image enhancement Medical imaging Population statistics Anatomical landmarks Detection accuracy Global shapes Landmark detection PCA Self-training Semi-supervised Semi-supervised method Shape constraints Unlabeled data
URL	查看原文
收录类别	EI ; SCIE ; SCI
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000761836100005
出版者	Elsevier B.V.
EI入藏号	20214911283240
EI主题词	Supervised learning
EI分类号	461.1 Biomedical Engineering ; 746 Imaging Techniques
原始文献类型	Journal article (JA)
Scopus 记录号	2-s2.0-85120475828
来源库	Scopus
引用统计
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/135758
专题	信息科学与技术学院_PI研究组_马月昕
通讯作者	Wang, Wenping
作者单位	1.Univ Hong Kong, Hong Kong, Peoples R China 2.ShanghaiTech Univ, Shanghai, Peoples R China 3.Max Planck Inst Informat, Saarbrucken, Germany 4.South China Univ Technol, Guangzhou, Peoples R China 5.Texas A&M Univ, College Stn, TX 77843 USA
推荐引用方式 GB/T 7714	Chen, Runnan,Ma, Yuexin,Liu, Lingjie,et al. Semi-supervised anatomical landmark detection via shape-regulated self-training[J]. NEUROCOMPUTING,2022,471:335-345.
APA	Chen, Runnan.,Ma, Yuexin.,Liu, Lingjie.,Chen, Nenglun.,Cui, Zhiming.,...&Wang, Wenping.(2022).Semi-supervised anatomical landmark detection via shape-regulated self-training.NEUROCOMPUTING,471,335-345.
MLA	Chen, Runnan,et al."Semi-supervised anatomical landmark detection via shape-regulated self-training".NEUROCOMPUTING 471(2022):335-345.