一种改进的非刚性医学图像配准算法  

Improved non-rigid medical image registration algorithm

作　　者：张静亚[1,2] 王加俊[1] 

机构地区：[1]苏州大学电子信息学院,江苏苏州215006 [2]常熟理工学院物理与电子工程学院,江苏常熟215500

出　　处：《计算机应用研究》2015年第4期1261-1264,共4页Application Research of Computers

基　　金：国家自然科学基金资助项目(60871086);江苏省自然科学基金资助项目(BK2008159);江苏省普通高校研究生科研创新计划资助项目(CXZZ11_0099)

摘　　要：非刚性医学图像配准是医学影像处理和应用中重要的研究课题。对传统的基于局部仿射变换的非刚性图像配准模型进行了改进,结合图像的区域灰度信息和切比雪夫低通滤波器幅度特性提出了一种新颖的非刚性医学图像配准算法。该算法采用自适应的局部非线性正则项,比传统算法更好地保持了图像的局部细节和边缘信息,通过结合多分辨率分层细化以及由粗到细的变形技术求解策略,很好地解决了传统配准模型无法对大变形单模态图像或者存在灰度差异的多模态图像之间进行配准的问题。实验证明,该模型和算法可以很好地实现对医学图像的非刚性配准。The non-rigid registration is one of the most important research areas for various medical image analysis tasks and applications. This paper proposed a novel non-rigid image registration algorithm based on the traditional local affine transformation model. In order to protect the image local details and edges,it used an adaptive nonlinear regularization term which took into account the regional statistical intensity information and the magnitude characteristic of the Chebyshev low pass filter. In the framework of the multi-resolution layered refining and coarse-to-fine warping strategy,the proposed algorithm achieved good performance in the registration of mono-modality medical images with relative larger deformations and the fine registration of multi-modality images with intensity variations which couldn＇t be processed by traditional algorithms. The experimental results show that the proposed algorithm is effective for non-rigid medical image registration.

关 键 词：非刚性医学图像配准 局部仿射变换 切比雪夫滤波器 正则项 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]