Abstract
A robust and fast hybrid method using a shell volume that consists of high contrast voxels with their neighbors is proposed for registering PET and MR/CT brain images. Whereas conventional hybrid methods find the best matched pairs from several manually selected or automatically extracted local regions, our method automatically selects a shell volume in the PET image, and finds the best matched corresponding volume using normalized mutual information (NMI) in overlapping volumes while transforming the shell volume into an MR or CT image. A shell volume not only can reduce irrelevant corresponding voxels between two images during optimization of transformation parameters, but also brings a more robust registration with less computational cost. Experimental results on clinical data sets showed that our method successfully aligned all PET and MR/CT image pairs without losing any diagnostic information, while the conventional registration methods failed in some cases.
Original language | English |
---|---|
Pages (from-to) | 961-977 |
Number of pages | 17 |
Journal | Computers in Biology and Medicine |
Volume | 39 |
Issue number | 11 |
DOIs | |
State | Published - Nov 2009 |
Bibliographical note
Funding Information:This work was supported in part by Grant no. 10028331 from the Medium-term Strategic Technology Development Program of the Ministry of Commerce, Industry and Energy (MOCIE, Korea), in part by Grant no. 10888 from the Seoul Research and Business Development Program, and in part by Grant no. A080199 from the Korea Healthcare technology R&D Project, Ministry for Health, Welfare and Family Affairs. The ICT at Seoul National University provided research facilities for this study.
Keywords
- Brain segmentation
- MR-CT-PET registration
- Multi-modality registration
- Normalized mutual information
- Rigid registration
- Shell