Paper ID: 2312.13220

SISMIK for brain MRI: Deep-learning-based motion estimation and model-based motion correction in k-space

Oscar Dabrowski (1 and 2), Jean-Luc Falcone (1), Antoine Klauser (2 and 3), Julien Songeon (2 and 3), Michel Kocher (4), Bastien Chopard (1), François Lazeyras (2 and 3), Sébastien Courvoisier (2 and 3) ((1) Computer Science Department, Faculty of Science, University of Geneva, Switzerland, (2) Department of Radiology and Medical Informatics, Faculty of Medicine, University of Geneva, Switzerland, (3) CIBM Center for Biomedical Imaging, MRI HUG-UNIGE, Geneva, Switzerland, (4) EPFL Biomedical Imaging Group (BIG), Lausanne, Switzerland)

MRI, a widespread non-invasive medical imaging modality, is highly sensitive to patient motion. Despite many attempts over the years, motion correction remains a difficult problem and there is no general method applicable to all situations. We propose a retrospective method for motion estimation and correction to tackle the problem of in-plane rigid-body motion, apt for classical 2D Spin-Echo scans of the brain, which are regularly used in clinical practice. Due to the sequential acquisition of k-space, motion artifacts are well localized. The method leverages the power of deep neural networks to estimate motion parameters in k-space and uses a model-based approach to restore degraded images to avoid ''hallucinations''. Notable advantages are its ability to estimate motion occurring in high spatial frequencies without the need of a motion-free reference. The proposed method operates on the whole k-space dynamic range and is moderately affected by the lower SNR of higher harmonics. As a proof of concept, we provide models trained using supervised learning on 600k motion simulations based on motion-free scans of 43 different subjects. Generalization performance was tested with simulations as well as in-vivo. Qualitative and quantitative evaluations are presented for motion parameter estimations and image reconstruction. Experimental results show that our approach is able to obtain good generalization performance on simulated data and in-vivo acquisitions. We provide a Python implementation at this https URL

Submitted: Dec 20, 2023