首页 | 本学科首页   官方微博 | 高级检索  
检索        

结合脑图谱和水平集的MR图像分割的研究
引用本文:周震,马斌荣.结合脑图谱和水平集的MR图像分割的研究[J].中国医学物理学杂志,2006,23(5):329-332,344.
作者姓名:周震  马斌荣
作者单位:首都医科大学,生物医学工程学院,北京,100069
摘    要:本文利用脑图谱的先验知识并结合水平集等算法实现对脑MR图像的初步分割。主要步骤:(1)选取数字脑图谱,对图谱进行预处理;(2)实现图谱与脑MR图像的配准;(3)利用图谱提供的轮廓信息对水平集算法进行初始化,完成颅骨和脑脊液的提取以及脑白质和脑灰质的分割。实验结果表明,利用脑图谱提供的信息可有效解决水平集算法初始化问题,缩小求解空间,减少迭代次数,该方法具有较好的鲁棒性。

关 键 词:脑图谱  水平集  MR图像分割
文章编号:1005-202X(2006)05-0329-04
收稿时间:2006-03-10
修稿时间:2006-03-10

Research on Segmentation for MR Image Based Brain Atlas and Level Set
ZHOU Zhen,MA Bin-rong.Research on Segmentation for MR Image Based Brain Atlas and Level Set[J].Chinese Journal of Medical Physics,2006,23(5):329-332,344.
Authors:ZHOU Zhen  MA Bin-rong
Institution:College of Biomedical Engineering Capital University of Medical Sciences, Beijing 100069, China
Abstract:In this paper,a MR image segmentation method was presented by unifying prior knowledge of atlas and level set arithmetic.The main processes:(1) choose a digital brain atlas and preprocess it;(2) perform the atlas and the MR image registration;(3) initialize level set arithmetic based on contour information of the atlas.Realize skull and cerebrospinal(CSF) extraction and achieve gray matter(GM) and white matter(WM) segmentation.Experiment results showed that the problem of level set initializations was solved based on the information of atlas and it could reduce the solution space and iteration.This method is characterized by robustness.
Keywords:brain atlas  level set  MR image segmentation
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号