Asymmetric image-template registration

Mert R. Sabuncu, B. T. Thomas Yeo, Koen Van Leemput, Tom Vercauteren, Polina Golland

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review


A natural requirement in pairwise image registration is that the resulting deformation is independent of the order of the images. This constraint is typically achieved via a symmetric cost function and has been shown to reduce the effects of local optima. Consequently, symmetric registration has been successfully applied to pairwise image registration as well as the spatial alignment of individual images with a template. However, recent work has shown that the relationship between an image and a template is fundamentally asymmetric. In this paper, we develop a method that reconciles the practical advantages of symmetric registration with the asymmetric nature of image-template registration by adding a simple correction factor to the symmetric cost function. We instantiate our model within a log-domain diffeomorphic registration framework. Our experiments show exploiting the asymmetry in image-template registration improves alignment in the image coordinates. © 2009 Springer-Verlag.
Original languageEnglish
Title of host publicationMedical Image Computing and Computer-Assisted Intervention
PublisherSpringer-verlag Berlin
Publication date2009
ISBN (Print)978-3-642-04267-6
Publication statusPublished - 2009
Externally publishedYes
Event12th International Conference on Medical Image Computing and Computer-Assisted Intervention - Imperial College, London, United Kingdom
Duration: 20 Sep 200924 Sep 2009
Conference number: 12


Conference12th International Conference on Medical Image Computing and Computer-Assisted Intervention
LocationImperial College
Country/TerritoryUnited Kingdom
SeriesLecture Notes in Computer Science


  • Alignment
  • Cost functions
  • Cost reduction
  • Image registration
  • Medical computing


Dive into the research topics of 'Asymmetric image-template registration'. Together they form a unique fingerprint.

Cite this