基于自适应自由变形法和梯度下降法的胸部多模医学图像配准  

Thorax multimodal medical image registration based on adaptive free-form deformation and gradient descent

作　　者：李彬[1] 欧陕兴[2] 田联房[1] 余霞[1] 

机构地区：[1]华南理工大学自动化科学与工程学院,广州510640 [2]广州军区广州总医院放射科,广州510010

出　　处：《计算机应用研究》2009年第10期3978-3982,共5页Application Research of Computers

基　　金：国家自然科学基金资助项目(30570458);广东省自然科学基金博士启动资助项目(8451064101000631)

摘　　要：为了实现胸部多模态医学图像的自动配准,提出了一种基于层次B样条自适应自由变形法和梯度下降法的配准方法。首先采用GVF Snake与Canny算子实现边缘提取,并自动配对特征点;接着,采用矩主轴法对多模医学图像进行全局粗配准;最后,基于层次B样条自适应自由变形法对多模态医学图像进行自动细配准,并且采用梯度下降法以及最大信息熵准则加速求自由变形系数。实验证明该方法不仅效率高,而且配准效果好。In order to realize the automatic registration of thorax multimodal medical images, this paper proposed an image registration method based on hierarchical adaptive free-form deformation and gradient descent. Firstly, extracted the edge of thorax by GVF Snake algorithm and Canny operator, and matched feature points automatically. Then, modeled the global coarse registration of thorax muhimodal medical images by principal axes algorithm. Finally, realized the local fine registration of thorax multimodal medical images by a free-form deformation（FFD） based on hierarchical B-splines. Moreover, generated the FFD parameters rapidly by gradient descent and maximization of mutual information. Experiments demonstrate the good performance of the proposed method.

关 键 词：自适应自由变形法 多模图像配准 层次B样条 梯度下降 最大互信息熵 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] R319[自动化与计算机技术—计算机科学与技术]