Left-invariant metrics for diffeomorphic image registration with spatially-varying regularisation

Schmah, Tanya; Risser, Laurent; Vialard, François-Xavier

Schmah, Tanya; Risser, Laurent; Vialard, François-Xavier (2013), Left-invariant metrics for diffeomorphic image registration with spatially-varying regularisation, in Kensaku Mori, Ichiro Sakuma, Yoshinobu Sato, Christian Barillot, Nassir Navab, Medical Image Computing and Computer-Assisted Intervention – MICCAI 2013 16th International Conference, Nagoya, Japan, September 22-26, 2013, Proceedings, Part I, Springer : Berlin Heidelberg, p. 203-210. 10.1007/978-3-642-40811-3_26

Type

Communication / Conférence

Date

2013

Conference country

JAPAN

Book title

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2013 16th International Conference, Nagoya, Japan, September 22-26, 2013, Proceedings, Part I; MICCAI 2013

Book author

Kensaku Mori, Ichiro Sakuma, Yoshinobu Sato, Christian Barillot, Nassir Navab

Publisher

Springer

Published in

Berlin Heidelberg

ISBN

978-3-642-40810-6

Pages

203-210

Abstract (EN)

We present a new framework for diffeomorphic image registration which supports natural interpretations of spatially-varying metrics. This framework is based on left-invariant diffeomorphic metrics (LIDM) and is closely related to the now standard large deformation diffeomorphic metric mapping (LDDMM). We discuss the relationship between LIDM and LDDMM and introduce a computationally convenient class of spatially-varying metrics appropriate for both frameworks. Finally, we demonstrate the effectiveness of our method on a 2D toy example and on the 40 3D brain images of the LPBA40 dataset.

Subjects / Keywords

Imaging / Radiology; Health Informatics; Artificial Intelligence (incl. Robotics); Image Processing and Computer Vision; Pattern Recognition; Computer Graphics