Learning best features for deformable registration of MR brains
- PMID: 16685958
- DOI: 10.1007/11566489_23
Learning best features for deformable registration of MR brains
Abstract
This paper presents a learning method to select best geometric features for deformable brain registration. Best geometric features are selected for each brain location, and used to reduce the ambiguity in image matching during the deformable registration. Best geometric features are obtained by solving an energy minimization problem that requires the features of corresponding points in the training samples to be similar, and the features of a point to be different from those of nearby points. By incorporating those learned best features into the framework of HAMMER registration algorithm, we achieved about 10% improvement of accuracy in estimating the simulated deformation fields, compared to that obtained by HAMMER. Also, on real MR brain images, we found visible improvement of registration in cortical regions.
Similar articles
-
[Non-linear registration of MR brain images integrated with machine learning].Zhongguo Yi Liao Qi Xie Za Zhi. 2006 Jul;30(4):268-70. Zhongguo Yi Liao Qi Xie Za Zhi. 2006. PMID: 17039935 Chinese.
-
Learning-based deformable registration of MR brain images.IEEE Trans Med Imaging. 2006 Sep;25(9):1145-57. doi: 10.1109/tmi.2006.879320. IEEE Trans Med Imaging. 2006. PMID: 16967800
-
Learning best features and deformation statistics for hierarchical registration of MR brain images.Inf Process Med Imaging. 2007;20:160-71. doi: 10.1007/978-3-540-73273-0_14. Inf Process Med Imaging. 2007. PMID: 17633697
-
Mono- and multimodal registration of optical breast images.J Biomed Opt. 2012 Aug;17(8):080901-1. doi: 10.1117/1.JBO.17.8.080901. J Biomed Opt. 2012. PMID: 23224161 Review.
-
Machine learning and radiology.Med Image Anal. 2012 Jul;16(5):933-51. doi: 10.1016/j.media.2012.02.005. Epub 2012 Feb 23. Med Image Anal. 2012. PMID: 22465077 Free PMC article. Review.
Cited by
-
Region-adaptive Deformable Registration of CT/MRI Pelvic Images via Learning-based Image Synthesis.IEEE Trans Image Process. 2018 Mar 30:10.1109/TIP.2018.2820424. doi: 10.1109/TIP.2018.2820424. Online ahead of print. IEEE Trans Image Process. 2018. PMID: 29994091 Free PMC article.
Publication types
MeSH terms
LinkOut - more resources
Medical