Breast Fibroglandular Tissue Segmentation for Automated BPE Quantification with Iterative Cycle-consistent Semi-supervised Learning

doi:10.1109/TMI.2023.3319646

	Breast Fibroglandular Tissue Segmentation for Automated BPE Quantification with Iterative Cycle-consistent Semi-supervised Learning
	Jiadong Zhang1 ; Zhiming Cui1 ; Luping Zhou 2; Yiqun Sun 3; Zhenhui Li 4; Zaiyi Liu 5; Dinggang Shen1
	2023
发表期刊	IEEE TRANSACTIONS ON MEDICAL IMAGING (IF:8.9[JCR-2023],11.3[5-Year])
ISSN	1558-254X
EISSN	1558-254X
卷号	PP 期号:99 页码:3944-3955
发表状态	已发表
DOI	10.1109/TMI.2023.3319646
摘要	Background Parenchymal Enhancement (BPE) quantification in Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) plays a pivotal role in clinical breast cancer diagnosis and prognosis. However, the emerging deep learning-based breast fibroglandular tissue segmentation, a crucial step in automated BPE quantification, often suffers from limited training samples with accurate annotations. To address this challenge, we propose a novel iterative cycle-consistent semi-supervised framework to leverage segmentation performance by using a large amount of paired pre-/post-contrast images without annotations. Specifically, we design the reconstruction network, cascaded with the segmentation network, to learn a mapping from the pre-contrast images and segmentation predictions to the post-contrast images. Thus, we can implicitly use the reconstruction task to explore the inter-relationship between these two-phase images, which in return guides the segmentation task. Moreover, the reconstructed post-contrast images across multiple auto-context modeling-based iterations can be viewed as new augmentations, facilitating cycle-consistent constraints across each segmentation output. Extensive experiments on two datasets with various data distributions show great segmentation and BPE quantification accuracy compared with other state-of-the-art semi-supervised methods. Importantly, our method achieves 11.80 times of quantification accuracy improvement along with 10 times faster, compared with clinical physicians, demonstrating its potential for automated BPE quantification. The code is available at https://github.com/ZhangJD-ong/Iterative-Cycle-consistent-Semi-supervised-Learning-for-fibroglandular-tissue-segmentation. © 1982-2012 IEEE.
关键词	Breast Tissue Segmentation Automated Background Parenchymal Enhancement (BPE) Quantification Semi-supervised Learning
URL	查看原文
收录类别	EI
语种	英语
出版者	Institute of Electrical and Electronics Engineers Inc.
EI入藏号	20234014843273
EI主题词	Magnetic resonance imaging
EI分类号	461.1 Biomedical Engineering ; 461.2 Biological Materials and Tissue Engineering ; 461.4 Ergonomics and Human Factors Engineering ; 701.2 Magnetism: Basic Concepts and Phenomena ; 731 Automatic Control Principles and Applications ; 746 Imaging Techniques ; 921.6 Numerical Methods
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/333385
专题	生物医学工程学院信息科学与技术学院_硕士生生物医学工程学院_PI研究组_沈定刚组生物医学工程学院_PI研究组_崔智铭组
作者单位	1.School of Biomedical Engineering, ShanghaiTech University, Shanghai, China 2.School of Electrical and Information Engineering, The University of Sydney, Australia 3.Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, China 4.Department of Radiology, Third Affiliated Hospital of Kunming Medical University, Yunnan Cancer Hospital, China 5.Department of Radiology, Guangdong Provincial People’s Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
第一作者单位	生物医学工程学院
第一作者的第一单位	生物医学工程学院
推荐引用方式 GB/T 7714	Jiadong Zhang,Zhiming Cui,Luping Zhou,et al. Breast Fibroglandular Tissue Segmentation for Automated BPE Quantification with Iterative Cycle-consistent Semi-supervised Learning[J]. IEEE TRANSACTIONS ON MEDICAL IMAGING,2023,PP(99):3944-3955.
APA	Jiadong Zhang.,Zhiming Cui.,Luping Zhou.,Yiqun Sun.,Zhenhui Li.,...&Dinggang Shen.(2023).Breast Fibroglandular Tissue Segmentation for Automated BPE Quantification with Iterative Cycle-consistent Semi-supervised Learning.IEEE TRANSACTIONS ON MEDICAL IMAGING,PP(99),3944-3955.
MLA	Jiadong Zhang,et al."Breast Fibroglandular Tissue Segmentation for Automated BPE Quantification with Iterative Cycle-consistent Semi-supervised Learning".IEEE TRANSACTIONS ON MEDICAL IMAGING PP.99(2023):3944-3955.