Thumbnail - Request a copy

Spatially-Varying Metric Learning for Diffeomorphic Image Registration: A Variational Framework

Vialard, François-Xavier; Risser, Laurent (2014), Spatially-Varying Metric Learning for Diffeomorphic Image Registration: A Variational Framework, International Conference on Medical Image Computing and Computer-Assisted Intervention: MICCAI 2014, Springer : Berlin Heidelberg, p. 227-234. 10.1007/978-3-319-10404-1_29

Type
Communication / Conférence
Date
2014
Conference title
Medical Image Computing and Computer-Assisted Intervention – MICCAI 2014 17th International Conference
Conference date
2014-09
Conference city
Boston
Conference country
United States
Book title
International Conference on Medical Image Computing and Computer-Assisted Intervention: MICCAI 2014
Publisher
Springer
Published in
Berlin Heidelberg
ISBN
978-3-319-10403-4
Number of pages
826
Pages
227-234
Publication identifier
Metadata
Show full item record
Author(s)
Vialard, François-Xavier
CEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
Risser, Laurent
Institut de Mathématiques de Toulouse UMR5219 [IMT]
Abstract (EN)
This paper introduces a variational strategy to learn spatially-varying metrics on large groups of images, in the Large Deformation Diffeomorphic Metric Mapping (LDDMM) framework. Spatially-varying metrics we learn not only favor local deformations but also correlated deformations in different image regions and in different directions. In addition, metric parameters can be efficiently estimated using a gradient descent method. We first describe the general strategy and then show how to use it on 3D medical images with reasonable computational ressources. Our method is assessed on the 3D brain images of the LPBA40 dataset. Results are compared with ANTS-SyN and LDDMM with spatially-homogeneous metrics.
Subjects / Keywords
Image Registration; Dimensionality Reduction Method; Grid Step Size; Simple Gradient Descent; Target Overlap