PET-MR images registration using support vector machine

Author

Zhang, Zhao ; Zhang, Su ; Zhang, Chen-Xi ; Li, Yan ; Chen, Ya-Zhu

Author_Institution

Biomed. Instrum. Inst., Shanghai Jiao Tong Univ., China

Volume

6

fYear

2005

fDate

18-21 Aug. 2005

Firstpage

3719

Abstract

Application of registration methods to PET and MR images is very important in diagnosis and treatment. We describe PET-MR registration method that incorporates prior joint intensity distribution between the two imaging modalities based on registered training images. The prior joint intensity distribution is modeled by support vector machine. Results demonstrate that this method is a fast registration method with sub-voxel registration accuracy.

Keywords

biomedical MRI; estimation theory; image registration; medical image processing; positron emission tomography; support vector machines; PET-MR images registration; joint intensity distribution; subvoxel registration accuracy; support vector machine; Biomedical imaging; Equations; Image registration; Image segmentation; Instruments; Machine learning; Medical diagnostic imaging; Medical treatment; Positron emission tomography; Support vector machines; Density Estimation; Joint Intensity Distribution; Registration; Support Vector Machine;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics, 2005. Proceedings of 2005 International Conference on

Conference_Location

Guangzhou, China

Print_ISBN

0-7803-9091-1

Type

conf

DOI

10.1109/ICMLC.2005.1527587

Filename

1527587