Contrastive Semi-Supervised Learning for Domain Adaptive Segmentation Across Similar Anatomical Structures

doi:10.1109/TMI.2022.3209798

	Contrastive Semi-Supervised Learning for Domain Adaptive Segmentation Across Similar Anatomical Structures
	Gu, Ran 1,2; Zhang, Jingyang3,4 ; Wang, Guotai 1,2; Lei, Wenhui 2,5; Song, Tao 6; Zhang, Xiaofan 2,5; Li, Kang 7; Zhang, Shaoting 2,6
	2023
发表期刊	IEEE TRANSACTIONS ON MEDICAL IMAGING (IF:8.9[JCR-2023],11.3[5-Year])
ISSN	0278-0062
EISSN	1558-254X
卷号	42 期号:1 页码:245-256
发表状态	已发表
DOI	10.1109/TMI.2022.3209798
摘要	Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance for medical image segmentation, yet need plenty of manual annotations for training. Semi-Supervised Learning (SSL) methods are promising to reduce the requirement of annotations, but their performance is still limited when the dataset size and the number of annotated images are small. Leveraging existing annotated datasets with similar anatomical structures to assist training has a potential for improving the model's performance. However, it is further challenged by the cross-anatomy domain shift due to the image modalities and even different organs in the target domain. To solve this problem, we propose Contrastive Semi-supervised learning for Cross Anatomy Domain Adaptation (CS-CADA) that adapts a model to segment similar structures in a target domain, which requires only limited annotations in the target domain by leveraging a set of existing annotated images of similar structures in a source domain. We use Domain-Specific Batch Normalization (DSBN) to individually normalize feature maps for the two anatomical domains, and propose a cross-domain contrastive learning strategy to encourage extracting domain invariant features. They are integrated into a Self-Ensembling Mean-Teacher (SE-MT) framework to exploit unlabeled target domain images with a prediction consistency constraint. Extensive experiments show that our CS-CADA is able to solve the challenging cross-anatomy domain shift problem, achieving accurate segmentation of coronary arteries in X-ray images with the help of retinal vessel images and cardiac MR images with the help of fundus images, respectively, given only a small number of annotations in the target domain. Our code is available at https://github.com/HiLab-git/DAG4MIA. © 1982-2012 IEEE.
关键词	Computer vision Magnetic resonance imaging Medical imaging Neural networks Supervised learning Adaptation models Anatomical structures Annotation Biomedical imaging Contrastive learning Cross-anatomy domain adaptation Domain adaptation Images segmentations Semi-supervised learning Task analysis
URL	查看原文
收录类别	EI ; SCOPUS
语种	英语
出版者	Institute of Electrical and Electronics Engineers Inc.
EI入藏号	20224112878300
EI主题词	Image segmentation
EI分类号	461.1 Biomedical Engineering ; 701.2 Magnetism: Basic Concepts and Phenomena ; 723.5 Computer Applications ; 741.2 Vision ; 746 Imaging Techniques
原始文献类型	Journal article (JA)
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/281941
专题	生物医学工程学院_PI研究组_沈定刚组
通讯作者	Wang, Guotai; Zhang, Shaoting
作者单位	1.University of Electronic Science and Technology of China, School of Mechanical and Electrical Engineering, Chengdu; 611731, China; 2.Shanghai Ai Laboratory, Shanghai; 200240, China; 3.Shanghai Jiao Tong University, School of Biomedical Engineering, Shanghai; 200240, China; 4.ShanghaiTech University, School of Biomedical Engineering, Shanghai; 200240, China; 5.Shanghai Jiao Tong University, School of Electronic Information and Electrical Engineering, Shanghai; 200240, China; 6.SenseTime Research, Shanghai; 200240, China; 7.Sichuan University, West China Hospital, Chengdu; 611731, China
推荐引用方式 GB/T 7714	Gu, Ran,Zhang, Jingyang,Wang, Guotai,et al. Contrastive Semi-Supervised Learning for Domain Adaptive Segmentation Across Similar Anatomical Structures[J]. IEEE TRANSACTIONS ON MEDICAL IMAGING,2023,42(1):245-256.
APA	Gu, Ran.,Zhang, Jingyang.,Wang, Guotai.,Lei, Wenhui.,Song, Tao.,...&Zhang, Shaoting.(2023).Contrastive Semi-Supervised Learning for Domain Adaptive Segmentation Across Similar Anatomical Structures.IEEE TRANSACTIONS ON MEDICAL IMAGING,42(1),245-256.
MLA	Gu, Ran,et al."Contrastive Semi-Supervised Learning for Domain Adaptive Segmentation Across Similar Anatomical Structures".IEEE TRANSACTIONS ON MEDICAL IMAGING 42.1(2023):245-256.