A multi-scale kernel bundle for LDDMM: towards sparse deformation description across space and scales

TY - GEN

T1 - A multi-scale kernel bundle for LDDMM

T2 - 22nd International Conference on Information Processing in Medical Imaging

AU - Sommer, Stefan Horst

AU - Nielsen, Mads

AU - Lauze, Francois Bernard

AU - Pennec, Xavier

N1 - Conference code: 22

PY - 2011

Y1 - 2011

N2 - The Large Deformation Diffeomorphic Metric Mapping framework constitutes a widely used and mathematically well-founded setup for registration in medical imaging. At its heart lies the notion of the regularization kernel, and the choice of kernel greatly affects the results of registrations. This paper presents an extension of the LDDMM framework allowing multiple kernels at multiple scales to be incorporated in each registration while preserving many of the mathematical properties of standard LDDMM. On a dataset of landmarks from lung CT images, we show by example the influence of the kernel size in standard LDDMM, and we demonstrate how our framework, LDDKBM, automatically incorporates the advantages of each scale to reach the same accuracy as the standard method optimally tuned with respect to scale. The framework, which is not limited to landmark data, thus removes the need for classical scale selection. Moreover, by decoupling the momentum across scales, it promises to provide better interpolation properties, to allow sparse descriptions of the total deformation, to remove the trade-off between match quality and regularity, and to allow for momentum based statistics using scale information.

AB - The Large Deformation Diffeomorphic Metric Mapping framework constitutes a widely used and mathematically well-founded setup for registration in medical imaging. At its heart lies the notion of the regularization kernel, and the choice of kernel greatly affects the results of registrations. This paper presents an extension of the LDDMM framework allowing multiple kernels at multiple scales to be incorporated in each registration while preserving many of the mathematical properties of standard LDDMM. On a dataset of landmarks from lung CT images, we show by example the influence of the kernel size in standard LDDMM, and we demonstrate how our framework, LDDKBM, automatically incorporates the advantages of each scale to reach the same accuracy as the standard method optimally tuned with respect to scale. The framework, which is not limited to landmark data, thus removes the need for classical scale selection. Moreover, by decoupling the momentum across scales, it promises to provide better interpolation properties, to allow sparse descriptions of the total deformation, to remove the trade-off between match quality and regularity, and to allow for momentum based statistics using scale information.

U2 - 10.1007/978-3-642-22092-0_51

DO - 10.1007/978-3-642-22092-0_51

M3 - Article in proceedings

SN - 978-3-642-22091-3

T3 - Lecture notes in computer science

SP - 624

EP - 635

BT - Information Processing in Medical Imaging

A2 - Székely, Gábor

A2 - Hahn, Horst K.

PB - Springer

Y2 - 3 July 2011 through 8 July 2011

ER -