Multiscale deformable registration of noisy medical images
Multiscale image registration techniques are presented for the reg-istration of medical images using deformable registration models. The tech-niques are particularly effective for registration problems in which one or bothof the images to be registered contains significant levels of noise. A briefov...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2007-12-01
|
| Series: | Mathematical Biosciences and Engineering |
| Subjects: | |
| Online Access: | https://www.aimspress.com/article/doi/10.3934/mbe.2008.5.125 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Multiscale image registration techniques are presented for the reg-istration of medical images using deformable registration models. The tech-niques are particularly effective for registration problems in which one or bothof the images to be registered contains significant levels of noise. A briefoverview of existing deformable registration techniques is presented, and exper-iments using B-spline free-form deformation registration models demonstratethat ordinary deformable registration techniques fail to produce accurate re-sults in the presence of significant levels of noise. The hierarchical multiscaleimage decomposition described in E. Tadmor, S. Nezzar, and L. Vese's, ''Amultiscale image representation using hierarchical (BV,L2) decompositions''(Multiscale Modeling and Simulations, 2 (2004): 4, pp. 554-579) is reviewed,and multiscale image registration algorithms are developed based on the mul-tiscale decomposition. Accurate registration of noisy images is achieved byobtaining a hierarchical multiscale decomposition of the images and iterativelyregistering the resulting components. This approach enables a successful reg-istration of images that contain noise levels well beyond the level at whichordinary deformable registration fails. Numerous image registration experi-ments demonstrate the accuracy and efficiency of the multiscale registrationtechniques. |
|---|---|
| ISSN: | 1551-0018 |