Self-supervised motion-corrected image reconstruction network for 4D magnetic resonance imaging of the body trunk

Thomas Kustner*, Jiazhen Pan, Christopher Gilliam, Haikun Qi, Gastao Cruz, Kerstin Hammernik, Thierry Blu, Daniel Rueckert, René Botnar, Claudia Prieto, Sergios Gatidis

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

401 Downloads (Pure)

Abstract

Respiratory motion can cause artifacts in magnetic resonance imaging of the body trunk if patients cannot hold their breath or triggered acquisitions are not practical. Retrospective correction strategies usually cope with motion by fast imaging sequences under free-movement conditions followed by motion binning based on motion traces. These acquisitions yield sub-Nyquist sampled and motion-resolved k-space data. Motion states are linked to each other by non-rigid deformation fields. Usually, motion registration is formulated in image space which can however be impaired by aliasing artifacts or by estimation from low-resolution images. Subsequently, any motion-corrected reconstruction can be biased by errors in the deformation fields. In this work, we propose a deep-learning based motion-corrected 4D (3D spatial + time) image reconstruction which combines a non-rigid registration network and a 4D reconstruction network. Non-rigid motion is estimated in k-space and incorporated into the reconstruction network. The proposed method is evaluated on in-vivo 4D motion-resolved magnetic resonance images of patients with suspected liver or lung metastases and healthy subjects. The proposed approach provides 4D motion-corrected images and deformation fields. It enables a ∼ 14× accelerated acquisition with a 25- fold faster reconstruction than comparable approaches under consistent preservation of image quality for changing patients and motion patterns.

Original languageEnglish
Article numbere12
Number of pages27
JournalAPSIPA Transactions on Signal and Information Processing
Volume11
Issue number1
DOIs
Publication statusPublished - 9 May 2022

Bibliographical note

Funding Information:
This work was funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany’s Excellence Strategy EXC 2180 – Project number 390900677 and EXC-Number 2064/1 – Project number 390727645. The work was supported by EPSRC grants EP/P032311/1, EP/P007619/1, and EP/P001009/1.

Publisher Copyright:
© 2022 T. Küstner et al.

Keywords

  • Deep learning reconstruction
  • Image registration
  • Magnetic Resonance Imaging
  • Motion-compensated image reconstruction

ASJC Scopus subject areas

  • Signal Processing
  • Information Systems

Fingerprint

Dive into the research topics of 'Self-supervised motion-corrected image reconstruction network for 4D magnetic resonance imaging of the body trunk'. Together they form a unique fingerprint.

Cite this