A Novel Automatic Registration Method for Serial Brain Images
10.3969/j.issn.1005-202X.2005.02.003
- VernacularTitle:一种新颖的序列图像自动配准方法
- Author:
Guiping JIANG
;
Zhexing LIU
;
Shuxiang LI
- Publication Type:Journal Article
- Keywords:
serial images;
registration;
thresholding;
counting;
mutual information;
Powell algorithm
- From:
Chinese Journal of Medical Physics
2005;22(2):441-447
- CountryChina
- Language:Chinese
-
Abstract:
Registration of serial images plays an increasingly important role in medicine. A novel registration method used for serial images matching is proposed, which is based on the joint histogram. After thresholding the two images to be registered, the joint histogram is divided into four separate regions. Then the criterion function is defined as bin counting in a specific region of the joint histogram, which simplifies the computation of the criteria function greatly and speeds up the alignment process significantly. We choose the Powell optimization algorithm to calculate the registration parameters. The comparison of the results from both mutual information and our method shows that the new method based on segmentation and counting is a fast, simple, efficient and accurate registration method.
