Ensemble registration: Combining groupwise registration and segmentation

Research output: Chapter in Book/Report/Conference proceedingConference contribution

  • Authors:
  • Sri Purwani
  • Carole Twining
  • Timothy Cootes
  • Constantino Carlos Reyes-Aldasoro (Editor)
  • Greg Slabaugh (Editor)


We investigate incorporating structural information from segmentation into agroupwise registration framework. Previous work by Petrovic et al., using MR brainimages, showed that using tissue fractions to help construct an intensity referenceimage gives better results than just using intensity images alone. In their work, aGaussian Mixture Model (GMM) was fitted to the 1D intensity histogram, then usedto construct tissue fraction images for each example. The mean fraction images were then used to create an artificial intensity reference for the registration.By using only the mean, this discarded much of the structural information. Weretain all this information, and augment each intensity image with its set of tissuefraction images (and also intensity gradient images) to form an image ensemble foreach example. We then perform groupwise registration using these ensembles ofimages. This groupwise ensemble registration is applied to the same real-world dataset as used by Petrovic et al. Ground-truth labels enable quantitative evaluation to be performed. It is shown that ensemble registration gives quantitatively better results than the algorithm of Petrovic et al., and that the best results are achieved when more than one of the three types of images (intensity, tissue fraction and gradient) are included as an ensemble.

Bibliographical metadata

Original languageEnglish
Title of host publicationProceedings of the 18th Conference on Medical Image Understanding and Analysis
EditorsConstantino Carlos Reyes-Aldasoro, Greg Slabaugh
PublisherBMVA Press
Number of pages6
ISBN (Print)1-901725-51-0
Publication statusPublished - Jul 2014
EventMedical Image Understanding and Analysis (MIUA) 2014 - City University London
Event duration: 9 Jul 201411 Jul 2014


ConferenceMedical Image Understanding and Analysis (MIUA) 2014
CityCity University London