Skip to main navigation Skip to search Skip to main content

Multi-modal diffeomorphic demons registration based on mutual information

  • Ying Li*
  • , Yonggang Shi
  • , Fa Jie
  • , Zhiwen Liu
  • , Yong Yuan
  • *Corresponding author for this work
  • Beijing Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Diffeomorphic demons algorithm is an efficient and robust method in nonrigid image registration. It uses mean squared error as the similarity measure and set the gradient and gray level difference as the interior and exterior force respectively to make the points move. However it cannot deal with multiple modality images. In this paper, mutual information is used as the similarity measure instead of mean squared error and the gradient of mutual information respect to parameters is set as the force to make the points move. Then the diffeomorphic demons algorithm is extended to match multi-modal images. The experiment with magnetic resonance T1 image and magnetic resonance T2 image shows that this method is effective and performs better and more quickly compared with B-spline free-form deformation method.

Original languageEnglish
Title of host publicationProceedings - 2011 4th International Conference on Biomedical Engineering and Informatics, BMEI 2011
PublisherIEEE Computer Society
Pages800-804
Number of pages5
ISBN (Print)9781424493524
DOIs
Publication statusPublished - 2011
Externally publishedYes
Event4th International Conference on Biomedical Engineering and Informatics, BMEI 2011 - Shanghai, China
Duration: 15 Oct 201117 Oct 2011

Publication series

NameProceedings - 2011 4th International Conference on Biomedical Engineering and Informatics, BMEI 2011
Volume2

Conference

Conference4th International Conference on Biomedical Engineering and Informatics, BMEI 2011
Country/TerritoryChina
CityShanghai
Period15/10/1117/10/11

Keywords

  • demons
  • diffeomorphic
  • multi-modality
  • mutual information
  • nonrigid registration

Fingerprint

Dive into the research topics of 'Multi-modal diffeomorphic demons registration based on mutual information'. Together they form a unique fingerprint.

Cite this