基于结构图像表示和微分同胚Demons算法的多模态医学图像配准  

Multi-modal medical image registration based on structural image representation and diffeomorphic Demons algorithm

作　　者：李碧草[1,2,3] 张俊峰[1,2,3] 杨冠羽[1,2,3] 舒华忠[1,2,3] 

机构地区：[1]东南大学影像科学与技术实验室,南京210096 [2]东南大学计算机网络和信息集成教育部重点实验室,南京211189 [3]东南大学中法生物医学信息研究中心,南京210096

出　　处：《东南大学学报（自然科学版）》2015年第5期851-855,共5页Journal of Southeast University：Natural Science Edition

基　　金：国家重点基础研究发展计划(973计划)资助项目(2011CB707904);国家自然科学基金资助项目(61073138;61201344;61271312;81101104)

摘　　要：为了提高多模态医学图像的配准精度,利用参考图像和浮动图像的结构信息,提出了一种基于结构图像表示和微分同胚Demons算法的多模态医学图像配准算法.该算法由结构图像表示和图像配准组成.在结构图像表示阶段,采用Arimoto熵图像来描述参考图像和浮动图像的结构信息,首先计算2幅图像中所有像素点周围指定大小邻域的熵值,然后把计算的熵值作为熵图像中对应点的灰度值以生成2幅熵图像.在图像配准阶段,使用微分同胚Demons配准算法对2幅熵图像进行配准.基于Brainweb数据库中磁共振数据的测试结果表明:与微分同胚Demons算法和基于香农熵的Demons算法相比,利用Arimoto熵表示图像的结构信息可以进一步提高配准精度.In order to improve the registration accuracy of multi-modal medical images,a multi-modal medical image registration algorithm based on structural image representation and diffeomorphic Demons algorithm is proposed by using the structural information of the reference image and the float image.This algorithm contains structural image representation and image registration.In the process of structural image representation,the Arimoto entropy is used to describe the structural information of the reference image and the float image.First,the entropic values of the neighbourhoods with the designed size of all pixel points in the two images are calculated.Then,these entropic values are regarded as the intensity values of the corresponding points in the entropy image and two entropy images can be obtained.In the process of image registration,the diffeomorphic Demons registration approach is used to register these two entropy images.The experimental results of the MRI （magnetic resonance imaging）data in Brainweb database show that applying Arimoto entropy to represent the structural information can further improve the registration accuracy compared with the diffeomorphic Demons algorithm and the Demons method based on Shannon entropy.

关 键 词：Arimoto熵 DEMONS算法 结构图像表示 图像配准 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]