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

Tanya Schmah; Laurent Risser; François-Xavier Vialard

doi:10.1007/978-3-642-40811-3_26

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

Med Image Comput Comput Assist Interv. 2013;16(Pt 1):203-10. doi: 10.1007/978-3-642-40811-3_26.

Authors

Tanya Schmah¹, Laurent Risser², François-Xavier Vialard³

Affiliations

¹ Rotman Research Institute, Baycrest, Toronto, Canada.
² CNRS, Institut de Mathématiques de Toulouse (UMR 5219), France.
³ CEREMADE (UMR 7534), Université Paris Dauphine, France.

PMID: 24505667
DOI: 10.1007/978-3-642-40811-3_26

Abstract

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.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Algorithms*
Brain / anatomy & histology*
Humans
Image Enhancement / methods
Image Interpretation, Computer-Assisted / methods*
Imaging, Three-Dimensional / methods*
Magnetic Resonance Imaging / methods*
Pattern Recognition, Automated / methods*
Reproducibility of Results
Sensitivity and Specificity
Subtraction Technique*