摘要
在心脏成像技术中,磁共振成像(Magnetic Resonance Imaging,MRI)因具有非侵入、无辐射、高分辨率等优点应用最为广泛。心脏结构与功能量化分析以左心室精准分割为前提。因此,设计有效算法实现左心室精准分割对心血管疾病早期诊断乃至预防具有重要意义。近几年作为流行方法之一,主动轮廓模型(Active Contour Model,ACM)在左心室分割方面取得很大进步。本文综述了近10年来主动轮廓模型基于心脏短轴MRI影像分割左心室的研究成果。据算法性质不同,本文将对以梯度矢量流为代表的参数主动轮廓模型的改进算法和以水平集为代表的几何主动轮廓模型的改进算法进行分别综述。最后对算法性能进行比较,并提出今后主动轮廓模型分割左心室算法的研究趋势和挑战,以使读者充分了解技术现状与未来发展趋势。
Among cardiac imaging technologies, magnetic resonance imaging （MRI） is the most widely applied due to its advantages of non-invasiveness, non-radiation and high resolution. Accurate segmentation of the left ventricle is the key to quantitative analysis of cardiac structure and function. Therefore, the design of effective algorithms to achieve accurate segmentation of left ventricular is of great signifcance for the early diagnosis and even prevention of cardiovascular diseases. As one of the popular methods, the active contour model （ACM） indicates superior performances in medical image segmentation in recent years. This review summarized the research results of ACM segmentation of left ventricular based on short axis MRI in recent 10 years. According to the different representations of the contour curves, ACM was divided into the parametric and geometric active contours. According to the characteristic of algorithms, improved algorithms of parametric ACM represented by Gradient Vector Flow and improved algorithms of geometric ACM represented by Level Set were mainly reviewed respectively. Finally, the performances of the algorithms were compared, and the research trends and challenges of the ACM segmentation of left ventricular algorithm were proposed, so that readers can systematically understand the status of existing technologies and future development trend.
作者
徐阳
徐礼胜
罗洋
冯朝路
康颖
杨本强
XU Yang;XU Lisheng;LUO Yang;FENG Chaolu;KANG Ying;YANG Benqiang(a.Sino-Dutch Biomedical and Information Engineering School,b.Key Laboratory of Medical Image Computing,Ministry of Education,c.School of Computer Science and Engineering,Northeastern University,Shenyang Liaoning 110169,China;Anshan Normal College,Anshan Liaoning 114016,China;Department of Radiology,General Hospital of Shenyang Military Region,Shenyang Liaoning 110016,China)
出处
《中国医疗设备》
2018年第8期1-6,14,共7页
China Medical Devices
基金
国家自然科学基金项目(61773110
61374015
61602101)
中央高校基本科研业务费探索导向重点项目(N161904002)
关键词
主动轮廓模型
左心室
磁共振成像
GVF模型
水平集
active contour model
left ventricle
magnetic resonance image
gradient vector flow
level set
