作者搜索
新闻
  10.5.5
C-DBLP系统正式发布作者研究兴趣及学术活动展示功能，请访问作者页面试用。
  09.7.6
C-DBLP的文献BibTex信息展示功能正式上线，请访问文章详细页面使用。
  09.7.29
C-DBLP系统新增同名区分功能，欢迎大家在作者页面试用。该功能部分使用了清华大学王建勇老师课题组提出的GHOST（GrapH-based framewOrk for name diStincTion）算法，在此表示感谢。
  09.6.2
C-DBLP系统集成了作者的相关图片并在搜索结果页面展示，敬请试用。
  更多>>
 
基于层次MRF的MR图像分割(英文)  BibTex
作者： 张红梅 袁泽剑 蔡忠闽 卞正中
单位： 西安交通大学生命科学与技术学院 陕西西安710049 (张红梅);西安交通大学人工智能与机器人研究所 陕西西安710049 (袁泽剑);西安交通大学系统工程研究所 陕西西安710049 (蔡忠闽);西安交通大学生命科学与技术学院 陕西西安710049(卞正中)
关键词： 层次马尔科夫随机场;有限高斯混合体;图像分割;核磁共振图像;最大后验估计
出处： 软件学报 2002 年 09期
基金： 国家自然科学基金;国家创新研究群体科学基金~~
全文链接： 查看全文>>
摘要：
　　核磁共振图像(MRI)的定量分析在神经疾病的早期治疗中有很重要作用.提出了一种基于层次Markov随机场模型的MRI图像分割新方法.在高层次的标记图象中采用了混合模型,即区域的内部用各向同性均匀MRF来建模,边界用各向异性非均匀MRF来建模.所以方向性被引入到边界信息中,这样可以更准确的表达标记图象的特性;在低层次的像素图像中,不同区域中像素的灰度分布用不同的高斯纹理来描述.分割问题可以被转换成一种最大后验概率估计问题.采用基于直方图的DAEM算法来估计SNFM参数的全局最优值;并基于MRF先验参数的实际意义,提出一种近似的方法来简化这些参数的估计,实验显示该方法能获得更好的结果.
正文快照：
　　Image segmentation is a very important tool in clinical application. It is employed in image guided monitoring, computer intervention. Pathological studies show that many neurological diseases are accompanied by subtle abnormal changes in brain tissues. Q…
Segmentation of MRI Using Hierarchical Markov Random Field
Author： ZHANG Hong-mei1;YUAN Ze-jian2;CAI Zhong-min3;BIAN Zheng-zhong1 1(School of Life Science and Technology;Xian Jiaotong University;Xian 710049;China); 2(Institute of Artificial Intelligence and Robotics;Xian Jiaotong University;Xian 710049;China); 3(Institute of System Engineering;Xian Jiaotong University;Xian 710049;China)
Keywords： hierarchical Markov random field;SFNM;image segmentation;MRI;MAP
Abstract：
　Magnetic Resonance Image (MRI) segmentation plays a major role in the tissue quantitative analysis which benefits the early treatment of neurological diseases. In this paper, a new approach to MRI segmentation based on hierarchical Markov random field (MRF) model is proposed: In higher-level MRF, a new mixture model is presented to describe the label image, that is, the interior of region is modeled by homogenous and isotropic MRF while the boundary is modeled by inhomogeneous and anisotropic MRF. So the orientation is incorporated into the boundary information and the characteristic of label image can be more accurately represented. In lower-level MRF, the different Gauss texture is filled in each region to describe pixel image. Then the segmentation problem is formulated as Maximum a Posterior Probability (MAP) estimation rule. A histogram based DAEM algorithm is used, which is able to find the global optima of the standard finite normal mixture (SFNM) parameters. Based on the meaning of prior MRF parameter, an approximate method is proposed to simplify the estimation of those parameters. Experiments on the pathological MRI show that our approach can achieve better results.