LAPNet: non-rigid registration derived in k-space for magnetic resonance imaging

Thomas Kustner*, Jiazhen Pan, Haikun Qi, Gastao Cruz, Christopher Gilliam, Thierry Blu, Bin Yang, Sergios Gatidis, Rene Botnar, Claudia Prieto

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)
33 Downloads (Pure)


Physiological motion, such as cardiac and respiratory motion, during Magnetic Resonance (MR) image acquisition can cause image artifacts. Motion correction techniques have been proposed to compensate for these types of motion during thoracic scans, relying on accurate motion estimation from undersampled motion-resolved reconstruction. A particular interest and challenge lie in the derivation of reliable non-rigid motion fields from the undersampled motion-resolved data. Motion estimation is usually formulated in image space via diffusion, parametric-spline, or optical flow methods. However, image-based registration can be impaired by remaining aliasing artifacts due to the undersampled motion-resolved reconstruction. In this work, we describe a formalism to perform non-rigid registration directly in the sampled Fourier space, i.e. k-space. We propose a deep-learning based approach to perform fast and accurate non-rigid registration from the undersampled k-space data. The basic working principle originates from the Local All-Pass (LAP) technique, a recently introduced optical flow-based registration. The proposed LAPNet is compared against traditional and deep learning image-based registrations and tested on fully-sampled and highly-accelerated (with two undersampling strategies) 3D respiratory motion-resolved MR images in a cohort of 40 patients with suspected liver or lung metastases and 25 healthy subjects. The proposed LAPNet provided consistent and superior performance to image-based approaches throughout different sampling trajectories and acceleration factors.

Original languageEnglish
Pages (from-to)3686-3697
Number of pages12
JournalIEEE Transactions on Medical Imaging
Issue number12
Early online date9 Jul 2021
Publication statusPublished - Dec 2021

Bibliographical note

Funding Information:
Manuscript received May 31, 2021; accepted July 7, 2021. Date of publication July 9, 2021; date of current version November 30, 2021. This work was supported in part by the Deutsche Forschungsgemeinschaft (DFG) through the Germany’s Excellence Strategy by EXC 2180 under Grant 390900677 and EXC 2064/1 under Grant 390727645; in part by EPSRC under Grant EP/P032311/1, Grant EP/P001009/1, and Grant EP/P007619/1; and in part by the Wellcome EPSRC Centre for Medical Engineering under Grant NS/A000049/1. (Corresponding author: Thomas Küstner.) This work involved human subjects. Approval of all ethical and experimental procedures and protocols was granted by the Local Ethics Committee under Application No. 721/2012BO1, and performed in line with the Helsinki Declaration of 1964 and its later amendments, and the EU Good Clinical Practice Directive 2005/28/EC, the EU Clinical Trial Regulation No. 536/2014, and the EU Regulation No. 746/2017 on medical devices.

Publisher Copyright:
© 1982-2012 IEEE.


  • deep learning registration
  • Magnetic resonance imaging
  • motion correction
  • non-rigid registration

ASJC Scopus subject areas

  • Software
  • Radiological and Ultrasound Technology
  • Computer Science Applications
  • Electrical and Electronic Engineering


Dive into the research topics of 'LAPNet: non-rigid registration derived in k-space for magnetic resonance imaging'. Together they form a unique fingerprint.

Cite this