Self-Supervised Motion-Corrected Image Reconstruction Network for 4D Magnetic Resonance Imaging of the Body Trunk
Journal
APSIPA Transactions on Signal and Information Processing
Journal Volume
11
Journal Issue
1
Date Issued
2022-02-21
Author(s)
Kustner, Thomas
Pan, Jiazhen
Gilliam, Christopher
Qi, Haikun
Cruz, Gastao
Hammernik, Kerstin
Rueckert, Daniel
Botnar, René
Prieto, Claudia
Gatidis, Sergios
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.
Subjects
Deep learning reconstruction | Image registration | Magnetic Resonance Imaging | Motion-compensated image reconstruction
SDGs
Type
journal article