Sliding at First-Order: Higher-Order Momentum Distributions for Discontinuous Image Registration

Research output: Contribution to journal › Journal article › Research › peer-review

Standard

Sliding at First-Order: Higher-Order Momentum Distributions for Discontinuous Image Registration. / Bao, Lili; Lu, Jiahao; Ying, Shihui; Sommer, Stefan.

In: SIAM Journal on Imaging Sciences, Vol. 17, No. 2, 2024, p. 861-887.

Research output: Contribution to journal › Journal article › Research › peer-review

Harvard

Bao, L, Lu, J, Ying, S & Sommer, S 2024, 'Sliding at First-Order: Higher-Order Momentum Distributions for Discontinuous Image Registration', SIAM Journal on Imaging Sciences, vol. 17, no. 2, pp. 861-887. https://doi.org/10.1137/23M1558665

APA

Bao, L., Lu, J., Ying, S., & Sommer, S. (2024). Sliding at First-Order: Higher-Order Momentum Distributions for Discontinuous Image Registration. SIAM Journal on Imaging Sciences, 17(2), 861-887. https://doi.org/10.1137/23M1558665

Vancouver

Bao L, Lu J, Ying S, Sommer S. Sliding at First-Order: Higher-Order Momentum Distributions for Discontinuous Image Registration. SIAM Journal on Imaging Sciences. 2024;17(2):861-887. https://doi.org/10.1137/23M1558665

Author

Bao, Lili ; Lu, Jiahao ; Ying, Shihui ; Sommer, Stefan. / Sliding at First-Order: Higher-Order Momentum Distributions for Discontinuous Image Registration. In: SIAM Journal on Imaging Sciences. 2024 ; Vol. 17, No. 2. pp. 861-887.

Bibtex

@article{3136326aaa4741aeadf197f159b1b024,
title = "Sliding at First-Order: Higher-Order Momentum Distributions for Discontinuous Image Registration",
abstract = "In this paper, we propose a new approach to deformable image registration that captures sliding motions. The large deformation diffeomorphic metric mapping (LDDMM) registration method faces challenges in representing sliding motion since it per construction generates smooth warps. To address this issue, we extend LDDMM by incorporating both zeroth- and first-order momenta with a nondifferentiable kernel. This allows us to represent both discontinuous deformation at switching boundaries and diffeomorphic deformation in homogeneous regions. We provide a mathematical analysis of the proposed deformation model from the viewpoint of discontinuous systems. To evaluate our approach, we conduct experiments on both artificial images and the publicly available DIR-Lab 4DCT dataset. Results show the effectiveness of our approach in capturing plausible sliding motion.",
author = "Lili Bao and Jiahao Lu and Shihui Ying and Stefan Sommer",
year = "2024",
doi = "10.1137/23M1558665",
language = "English",
volume = "17",
pages = "861--887",
journal = "SIAM Journal on Imaging Sciences",
issn = "1936-4954",
publisher = "Society for Industrial and Applied Mathematics",
number = "2",

}

RIS

TY - JOUR

T1 - Sliding at First-Order: Higher-Order Momentum Distributions for Discontinuous Image Registration

AU - Bao, Lili

AU - Lu, Jiahao

AU - Ying, Shihui

AU - Sommer, Stefan

PY - 2024

Y1 - 2024

N2 - In this paper, we propose a new approach to deformable image registration that captures sliding motions. The large deformation diffeomorphic metric mapping (LDDMM) registration method faces challenges in representing sliding motion since it per construction generates smooth warps. To address this issue, we extend LDDMM by incorporating both zeroth- and first-order momenta with a nondifferentiable kernel. This allows us to represent both discontinuous deformation at switching boundaries and diffeomorphic deformation in homogeneous regions. We provide a mathematical analysis of the proposed deformation model from the viewpoint of discontinuous systems. To evaluate our approach, we conduct experiments on both artificial images and the publicly available DIR-Lab 4DCT dataset. Results show the effectiveness of our approach in capturing plausible sliding motion.

AB - In this paper, we propose a new approach to deformable image registration that captures sliding motions. The large deformation diffeomorphic metric mapping (LDDMM) registration method faces challenges in representing sliding motion since it per construction generates smooth warps. To address this issue, we extend LDDMM by incorporating both zeroth- and first-order momenta with a nondifferentiable kernel. This allows us to represent both discontinuous deformation at switching boundaries and diffeomorphic deformation in homogeneous regions. We provide a mathematical analysis of the proposed deformation model from the viewpoint of discontinuous systems. To evaluate our approach, we conduct experiments on both artificial images and the publicly available DIR-Lab 4DCT dataset. Results show the effectiveness of our approach in capturing plausible sliding motion.

U2 - 10.1137/23M1558665

DO - 10.1137/23M1558665

M3 - Journal article

VL - 17

SP - 861

EP - 887

JO - SIAM Journal on Imaging Sciences

JF - SIAM Journal on Imaging Sciences

SN - 1936-4954

IS - 2

ER -

ID: 387837499