[en] Abstract. Transitive consistency of pairwise transformations is a desir- able property of groupwise image registration procedures. The transfor- mation synchronisation method [4] is able to retrieve transitively con- sistent pairwise transformations from pairwise transformations that are initially not transitively consistent. In the present paper, we present a numerically stable implementation of the transformation synchronisa- tion method for a ne transformations, which can deal with very large translations, such as those occurring in medical images where the coor- dinate origins may be far away from each other. By using this method in conjunction with any pairwise (a ne) image registration algorithm, a transitively consistent and unbiased groupwise image registration can be achieved. Experiments involving the average template generation from 3D brain images demonstrate that the method is more robust with re- spect to outliers and achieves higher registration accuracy compared to reference-based registration.
Disciplines :
Computer science
Author, co-author :
Bernard, Florian ; University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB)
Thunberg, Johan ; University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB)
Salamanca Mino, Luis ; University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB)
Gemmar, Peter; Trier University of Applied Sciences, Trier, GERMANY
Hertel, Frank ; University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB)
Goncalves, Jorge ; University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB)
Husch, Andreas ; University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB)
External co-authors :
yes
Language :
English
Title :
Transitively Consistent and Unbiased Multi-Image Registration Using Numerically Stable Transformation Synchronisation
Publication date :
2015
Event name :
MICCAI15 18th International Conference on Image Computing and Computer Assisted Interventions
Event date :
from 5-9-2015 to 9-9-2015
Journal title :
MIDAS Journal
Peer reviewed :
Peer reviewed
FnR Project :
FNR8864515 - Set Convergence In Nonlinear Multi-agent Systems, 2014 (01/02/2015-31/01/2017) - Johan Thunberg