Data Consistent Deep Rigid MRI Motion CorrectionDownload PDF

Published: 04 Apr 2023, Last Modified: 14 Apr 2024MIDL 2023 OralReaders: Everyone
Keywords: Motion Correction, MRI, Deep Learning, Hypernetworks, Data Consistency
Abstract: Motion artifacts are a pervasive problem in MRI, leading to misdiagnosis or mischaracterization in population-level imaging studies. Current retrospective rigid intra-slice motion correction techniques jointly optimize estimates of the image and the motion parameters. In this paper, we use a deep network to reduce the joint image-motion parameter search to a search over rigid motion parameters alone. Our network produces a reconstruction as a function of two inputs: corrupted k-space data and motion parameters. We train the network using simulated, motion-corrupted k-space data generated from known motion parameters. At test-time, we estimate unknown motion parameters by minimizing a data consistency loss between the motion parameters, the network-based image reconstruction given those parameters, and the acquired measurements. Intra-slice motion correction experiments on simulated and realistic 2D fast spin echo brain MRI achieve high reconstruction fidelity while retaining the benefits of explicit data consistency-based optimization.
TL;DR: Explicitly enforcing data consistency in deep learning-based rigid motion correction yields high fidelity reconstructions and rapid optimization of motion parameters.
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](
4 Replies