自动化学报2016，Vol.42Issue(9)：1413-1420,8.DOI:10.16383/j.aas.2016.c150608
一种面向医学图像非刚性配准的多维特征度量方法
A Metric Method Using Multidimensional Features for Nonrigid Registration of Medical Images
摘要
Abstract
Nonrigid registration of medical images has great significance for accurate diagnosis and therapy in clinic. It is difficult to register the images containing large deformation of ob ject region and data anisotropy. According to this problem, an algorithm of nonrigid registration based on joint Renyi α-entropy is proposed in this paper, which combines global features with local features. Firstly, minimum spanning tree is employed for construction of joint Renyiα-entropy. A new metric is built on multidimensional features. And then, the analytical derivative of the new metric with respect to the parameters of deformation model is derived, in order to find the optima by a stochastic gradient descent method. Finally, Canny feature and gradient orientation feature of images are merged into the new metric, which implements nonrigid registration including global and local features. Experiments are performed on 36 cervical magnetic resonance (MR) image pairs. Compared to the traditional mutual information and correlation coefficient, the registration accuracy is improved significantly. It also manifests that the proposed method is able to overcome the adverse effects of local intensity inhomogeneity, and provides scientific evidence for accurate diagnosis and therapy in clinic, due to reducing mismatch in some degree.关键词
非刚性配准/联合Renyiα-entropy/最小距离树/局部特征/自由形变模型Key words
Nonrigid registration/joint Renyi α-entropy/minimum spanning tree/local feature/free-form deformation model引用本文复制引用
陆雪松,涂圣贤,张素..一种面向医学图像非刚性配准的多维特征度量方法[J].自动化学报,2016,42(9):1413-1420,8.基金项目
国家自然科学基金(61002046),国家民委科研项目(14ZNZ024)资助Supported by National Natural Science Foundation of China (61002046) and Scientific Research Projects by the State Ethnic Affairs Commission of China (14ZNZ024) （61002046）
