An Efficient and Robust Method for Automatically Identifying the Left Ventricular Boundary in Cine Magnetic Resonance Images

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 机器人学研究室

	An Efficient and Robust Method for Automatically Identifying the Left Ventricular Boundary in Cine Magnetic Resonance Images
	Wang ZZ(王振洲)
刊名	IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
	2016
卷号	13 期号:2 页码:536-542
关键词	Deformation flow left ventricle magnetic resonance imaging optical flow segmentation
ISSN号	1545-5955
通讯作者	王振洲
产权排序	1
中文摘要	Efficient and robust identification of the left ventricular borders remains a challenging problem in cardiology. In this paper, we proposed an automatic method to segment the left ventricles and then identify their borders robustly. The proposed method is named as "ABDC" because it utilizes the strengths of four techniques: Automatic threshold selection; Boundary extraction, Deformation flow tracking, and Convex shape modeling. We compared the proposed method with the PDE optical flow method on 1660 images which are obtained from ten complete short-axis cine MRI datasets (five normal subjects and five patients). As it turned out, the proposed method is more efficient and robust than the benchmark in segmenting LV borders. Note to Practitioners-The proposed method is implemented in a user friendly interface software and can be easily used to identify the boundary of the ventricle automatically by practitioners. The boundary of the left ventricle in the first frame of the slice is identified automatically by level set method and then it could be improved if necessary by the practitioner to guarantee accurate input boundary. Then, the rest of the frames are segmented by the proposed method automatically. The automatically identified boundary can be further improved by the practitioners manually and interactively after all the borders are identified.
WOS标题词	Science & Technology ; Technology
类目[WOS]	Automation & Control Systems
研究领域[WOS]	Automation & Control Systems
关键词[WOS]	MR-IMAGES ; SEGMENTATION ; PROPAGATION
收录类别	SCI ; EI
语种	英语
WOS记录号	WOS:000374442300014
内容类型	期刊论文
源URL	[http://ir.sia.cn/handle/173321/18663]
专题	沈阳自动化研究所_机器人学研究室
推荐引用方式 GB/T 7714	Wang ZZ. An Efficient and Robust Method for Automatically Identifying the Left Ventricular Boundary in Cine Magnetic Resonance Images[J]. IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING,2016,13(2):536-542.
APA	Wang ZZ.(2016).An Efficient and Robust Method for Automatically Identifying the Left Ventricular Boundary in Cine Magnetic Resonance Images.IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING,13(2),536-542.
MLA	Wang ZZ."An Efficient and Robust Method for Automatically Identifying the Left Ventricular Boundary in Cine Magnetic Resonance Images".IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 13.2(2016):536-542.