Please wait a minute...
J4  2011, Vol. 45 Issue (1): 163-167    DOI: 10.3785/j.issn.1008-973X.2011.01.028
电气工程     
扩散张量成像中脑胼胝体结构图像的分割算法
吴占雄1, 朱善安1, 贺斌2
1.浙江大学 电气工程学院,浙江 杭州 310027;  2.Department of Biomedical Engineering, University of Minnesota,
Minnesota 55455, USA
Segmentation of brain corpus callosum using graph cuts algorithm
based on diffusion tensor imaging
WU Zhan-xiong1, ZHU Shan-an1, HE Bin2
1.College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China;
2. Department of Biomedical Engineering, University of Minnesota, Minnesota 55455, USA
 全文: PDF  HTML
摘要:

为了准确地将胼胝体结构从扩散张量图像中分割出来,利用K均值聚类算法把白质从脑内部组织中分割出来.通过定义张量间相似度函数将基于标量空间的图形切割算法拓展到张量空间,根据先验知识选择目标与背景种子集合,以张量相似度为权构造图结构.采用最大流算法对白质纤维束亚结构胼胝体进行分割.对病人脑扩散张量图像(DTI)进行分割,分析边界分割惩罚因子与目标分割种子对分割结果的影响.结果表明,图形切割分割算法能够对胼胝体实现准确的分割.

Abstract:

The segmentation of white matter was got by using K-means algorithm in order to get the accurate segmentation of corpus callosum from diffusion tensor images. Then the graph cuts algorithm was expanded to tensor space by defining similarity function, and the graph structure was constructed with the tensor similarity to the link after the target and the background seed were selected according to priori. The segmentation of corpus callosum was done through the maximum flow method. The influence of border penalty factor and object seeds on the results was analyzed through the segmentation of the diffusion tensor imaging (DTI) dataset. Results show the correctness of graph cuts algorithm for the segmentation of corpus callosum.

出版日期: 2011-03-03
:  Q 64  
基金资助:

 国家自然科学基金资助项目(NSFC-50577055);美国国家卫生研究所资助项目(RO1EB007920);美国国家科学基金资助项目(NSF BES-0602957).

通讯作者: 朱善安, 男, 教授.     E-mail: zsa@zju.edu.cn
作者简介: 吴占雄(1979-), 男, 山东青岛人, 博士生,从事脑电磁研究. E-mail: wuzhanxiong@sohu.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  

引用本文:

吴占雄, 朱善安, 贺斌. 扩散张量成像中脑胼胝体结构图像的分割算法[J]. J4, 2011, 45(1): 163-167.

WU Zhan-xiong, ZHU Shan-an, HE Bin. Segmentation of brain corpus callosum using graph cuts algorithm
based on diffusion tensor imaging. J4, 2011, 45(1): 163-167.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2011.01.028        http://www.zjujournals.com/eng/CN/Y2011/V45/I1/163

[1] DEUTSCH G K, DOUGHERTY R F, BAMMER R, et al. Children’s reading performance is correlated with white matter structure measured by diffusion tensor imaging [J]. Cortex, 2005, 41(3): 354-363.
[2]BIHAN D, MANGIN J F, POUPON C, et al. Diffusion tensor imaging: concepts and applications [J]. Journal of Magnetic Resonance Imaging, 2001, 13(4): 534-546.
[3] HENRIETTA T, RBERT T, MARIANNA Z. Complex fiber visualization [J]. Annales Mathematicae et Informaticae, 2007, 34(1): 103-109.
[4] BASSER P J, MATTIELLO J, BIHAN D. MR diffusion tensor spectroscopy and imaging [J]. Biophysical Journal, 1994, 66(1): 259-267.
[5] 章卫祥, 周秉锋. 一种改进的Graph cuts交互图像分割方法[J]. 影像技术, 2007, 4(1): 22-24.
ZHANG Weixiang, ZHOU Bingfeng. An improved interactive graph cuts for image segmentation [J]. Image Technology, 2007, 4(1): 22-24.
[6] GOLDBERG A, TARJAN R. A new approach to the maximumow problem [J]. Journal of the ACM, 1988, 35(4): 921-940.
[7] BASSER P, MATTIELLO J, BIHAN D. Estimation of the effective selfdiffusion tensor from the NMR spin echo [J]. Journal of Magnetic Resonance, 1994, 103(3): 247-254.
[8] YEATMAN P J, SHACHAR M B, BAMMER R, et al. Using diffusion tensor imaging and fiber tracking to characterize diffuse perinatal white matter [J]. Journal of Child Neurology, 2009, 24(7): 795-800.
[9] DERICHE R, TSCHUMPERLE D, LENGLET C. DTMRI estimation, regularization and fiber tractography [C]∥ Biomedical Imaging: Macro to Nano, IEEE International Symposium.Arlington: IEEE, 2004: 9-12.
[10]  LI Hua, YEZZI A, COHEN L D. Fast 3D brain segmentation using dualfront active contours with optional userinteraction [J]. International Journal of Biomedical Imaging, 2005, 3765:335-345.
[11] MOHAMMAD M K, HAMID S Z, CARO L. Unsupervised MRI segmentation with spatial connectivity [J]. Symposium on Medical Imaging, 2002, 4684: 1742-1750.

[1] 吴占雄,朱善安,BIN He. 基于移动最小二乘法的白质纤维束走向跟踪[J]. J4, 2011, 45(3): 458-461.