A Fast Diffeomorphic Image Registration Algorithm
Speaker: John Ashburner , University College London/The Wellcome Trust Centre for Neuroimaging
Date: May 29 2008
Time: 11:00AM to 12:00PM
Location: 32-D507
Host: Polina Golland, CSAIL
Contact: Polina Golland, x38005, polina@csail.mit.edu
Relevant URL: This talk describes DARTEL, which is an algorithm for diffeomorphic image
registration. Nonlinear registration is considered as a local optimisation
problem, which is solved using a Levenberg-Marquardt strategy.
The necessary matrix solutions are obtained in reasonable time using a
multi-grid method. A constant Eulerian velocity framework is used, which
allows a rapid scaling and squaring method to be used in the computations.
The original framework has been extended for generating tissue probability
maps that represent the average shape of a number of subjects' brain images.
The procedure is formulated as finding maximum a posteriori estimates within a
probabilistic generative model. Estimating the parameters involves
alternating between estimating the deformations that match tissue class
images of individual subjects to template, and updating the template
according to the latest estimates of the deformations. A multinomial matching
criterion is used, such that multiple tissue class images (e.g. grey and
white matter) are registered simultaneously with the current template
estimate. In order to generalise the resulting template to a broader range of
subjects, a smoothness prior is included within the model.
See other events that are part of Biomedical Imaging and Analysis 2007/2008
See other events happening in May 2008
