Imperial College London
Portrait Picture

ProfessorDeclanO'Regan

Faculty of Medicine, Institute of Clinical Sciences

Professor of Imaging Sciences
 
 
 
//

Contact

 

+44 (0)20 3313 1510declan.oregan

 
 
//

Location

 

Imaging Sciences DepartmentHammersmith HospitalHammersmith Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Thorley:2021:10.1007/978-3-030-87202-1_15,
author = {Thorley, A and Jia, X and Chang, HJ and Liu, B and Bunting, K and Stoll, V and de, Marvao A and O'Regan, DP and Gkoutos, G and Kotecha, D and Duan, J},
doi = {10.1007/978-3-030-87202-1_15},
pages = {150--160},
publisher = {SPRINGER INTERNATIONAL PUBLISHING AG},
title = {Nesterov accelerated ADMM for fast diffeomorphic image registration},
url = {http://dx.doi.org/10.1007/978-3-030-87202-1_15},
year = {2021}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - Deterministic approaches using iterative optimisation have been historically successful in diffeomorphic image registration (DiffIR). Although these approaches are highly accurate, they typically carry a significant computational burden. Recent developments in stochastic approaches based on deep learning have achieved sub-second runtimes for DiffIR with competitive registration accuracy, offering a fast alternative to conventional iterative methods. In this paper, we attempt to reduce this difference in speed whilst retaining the performance advantage of iterative approaches in DiffIR. We first propose a simple iterative scheme that functionally composes intermediate non-stationary velocity fields to handle large deformations in images whilst guaranteeing diffeomorphisms in the resultant deformation. We then propose a convex optimisation model that uses a regularisation term of arbitrary order to impose smoothness on these velocity fields and solve this model with a fast algorithm that combines Nesterov gradient descent and the alternating direction method of multipliers (ADMM). Finally, we leverage the computational power of GPU to implement this accelerated ADMM solver on a 3D cardiac MRI dataset, further reducing runtime to less than 2 s. In addition to producing strictly diffeomorphic deformations, our methods outperform both state-of-the-art deep learning-based and iterative DiffIR approaches in terms of dice and Hausdorff scores, with speed approaching the inference time of deep learning-based methods.
AU  - Thorley,A
AU  - Jia,X
AU  - Chang,HJ
AU  - Liu,B
AU  - Bunting,K
AU  - Stoll,V
AU  - de,Marvao A
AU  - O'Regan,DP
AU  - Gkoutos,G
AU  - Kotecha,D
AU  - Duan,J
DO  - 10.1007/978-3-030-87202-1_15
EP  - 160
PB  - SPRINGER INTERNATIONAL PUBLISHING AG
PY  - 2021///
SN  - 0302-9743
SP  - 150
TI  - Nesterov accelerated ADMM for fast diffeomorphic image registration
UR  - http://dx.doi.org/10.1007/978-3-030-87202-1_15
UR  - http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000712021400015&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=1ba7043ffcc86c417c072aa74d649202
UR  - https://link.springer.com/chapter/10.1007%2F978-3-030-87202-1_15
UR  - http://hdl.handle.net/10044/1/93260
ER  -
Download