RCPS: Rectified Contrastive Pseudo Supervision for Semi-Supervised Medical Image Segmentation

doi:10.1109/JBHI.2023.3322590

	RCPS: Rectified Contrastive Pseudo Supervision for Semi-Supervised Medical Image Segmentation
	Zhao, Xiangyu 1; Qi, Zengxin 2,3,4,5; Wang, Sheng 1; Wang, Qian6,7 ; Wu, Xuehai 2,3,4,5; Mao, Ying 2,3,4,5; Zhang, Lichi 1
	2023
发表期刊	IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS (IF:6.7[JCR-2023],7.1[5-Year])
ISSN	2168-2208
EISSN	2168-2208
卷号	PP 期号:99 页码:1-11
发表状态	已发表
DOI	10.1109/JBHI.2023.3322590
摘要	Medical image segmentation methods are generally designed as fully-supervised to guarantee model performance, which requires a significant amount of expert annotated samples that are high-cost and laborious. Semi-supervised image segmentation can alleviate the problem by utilizing a large number of unlabeled images along with limited labeled images. However, learning a robust representation from numerous unlabeled images remains challenging due to potential noise in pseudo labels and insufficient class separability in feature space, which undermines the performance of current semi-supervised segmentation approaches. To address the issues above, we propose a novel semi-supervised segmentation method named as Rectified Contrastive Pseudo Supervision (RCPS), which combines a rectified pseudo supervision and voxel-level contrastive learning to improve the effectiveness of semi-supervised segmentation. Particularly, we design a novel rectification strategy for the pseudo supervision method based on uncertainty estimation and consistency regularization to reduce the noise influence in pseudo labels. Furthermore, we introduce a bidirectional voxel contrastive loss in the network to ensure intra-class consistency and inter-class contrast in feature space, which increases class separability in the segmentation. The proposed RCPS segmentation method has been validated on two public datasets and an in-house clinical dataset. Experimental results reveal that the proposed method yields better segmentation performance compared with the state-of-the-art methods in semi-supervised medical image segmentation. The source code is available at https://github.com/hsiangyuzhao/RCPS. IEEE
关键词	Medical image segmentation semi-supervised learning contrastive learning pseudo supervision
URL	查看原文
收录类别	EI ; SCI
语种	英语
WOS研究方向	Computer Science ; Mathematical & Computational Biology ; Medical Informatics
WOS类目	Computer Science, Information Systems ; Computer Science, Interdisciplinary Applications ; Mathematical & Computational Biology ; Medical Informatics
WOS记录号	WOS:001139615300045
出版者	Institute of Electrical and Electronics Engineers Inc.
EI入藏号	20234314967010
EI主题词	Image segmentation
EI分类号	461.1 Biomedical Engineering ; 746 Imaging Techniques ; 912.4 Personnel ; 922.1 Probability Theory
原始文献类型	Article in Press
来源库	IEEE
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/337729
专题	生物医学工程学院生物医学工程学院_PI研究组_王乾组
通讯作者	Mao, Ying; Zhang, Lichi
作者单位	1.Shanghai Jiao Tong Univ, Sch Biomed Engn, Shanghai 200030, Peoples R China 2.Fudan Univ, Huashan Hosp, Shanghai Med Coll, Dept Neurosurg, Shanghai 200040, Peoples R China 3.Natl Ctr Neurol Disorders, Shanghai 200040, Peoples R China 4.Shanghai Key Lab Brain Funct & Restorat & Neural, Shanghai 200040, Peoples R China 5.Fudan Univ, Sch Basic Med Sci, MOE Frontiers Ctr Brain Sci, State Key Lab Med Neurobiol,Inst Brain Sci, Shanghai 200040, Peoples R China 6.ShanghaiTech Univ, Sch Biomed Engn, Shanghai 201210, Peoples R China 7.Shanghai Clin Res & Trial Ctr, Shanghai 201210, Peoples R China
推荐引用方式 GB/T 7714	Zhao, Xiangyu,Qi, Zengxin,Wang, Sheng,et al. RCPS: Rectified Contrastive Pseudo Supervision for Semi-Supervised Medical Image Segmentation[J]. IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS,2023,PP(99):1-11.
APA	Zhao, Xiangyu.,Qi, Zengxin.,Wang, Sheng.,Wang, Qian.,Wu, Xuehai.,...&Zhang, Lichi.(2023).RCPS: Rectified Contrastive Pseudo Supervision for Semi-Supervised Medical Image Segmentation.IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS,PP(99),1-11.
MLA	Zhao, Xiangyu,et al."RCPS: Rectified Contrastive Pseudo Supervision for Semi-Supervised Medical Image Segmentation".IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS PP.99(2023):1-11.