Rapid Multimodal Medical Image Registration and Fusion in 3D conformal radiotherapy treatment planning
In order to realize effectively and efficiently theautomatic registration and fusion of multimodal medical imagesdata in 3D conformal radiotherapy treatment planning (3DCRTP), a rapid image registration and fusion method isproposed in this paper. This proposed registration method isbased on hierarchical adaptive free-form deformation(FFD)algorithm, which can be described as follows: First theROI(region of interest) is extracted by using C-V level setsalgorithm, and feature points are matched automatically which isbased on parallel computing method. Then, the global roughregistration is carried out by employing principal axes algorithm.Next, the automatic fine registration of the multimodal medicalimages is realized by a FFD method based on hierarchical B-splines.Moreover, in order to speed up the calculation of theFFD coefficients, stochastic gradient descent method-SimultaneousPerturbation(SP) and the criteria of maximummutual information entropy are adopted. After the registrationof multimodal images, their sequence images are fused byapplying an image fusion method based on parallel computingand wavelet transform with the fusion rule of combining the localstandard deviation and energy. This study demonstrates thesuperiority of the proposed method.
Bin Li Lianfang Tian Shanxing Ou
School of Automation Science and Engineering South China University of Technology Guangzhou, China Dept.of Radiology and Pediatrics Guangzhou General Hospital of Guangzhou Command Guangzhou, China
国际会议
成都
英文
1-5
2010-06-18（万方平台首次上网日期，不代表论文的发表时间）