Choreography Controlled (ChoCo) brain MRI artifact generation for labeled motion-corrupted datasets. (October 2022)

• Record Type: Journal Article
• Authors: Dabrowski, Oscar; Courvoisier, Sébastien; Falcone, Jean-Luc; Klauser, Antoine; Songeon, Julien; Kocher, Michel; Chopard, Bastien; Lazeyras, François
• Is Part Of: Physica medica. Volume 102(2022)
• Page Start: 79
• Page End: 87
• Publication Date: 2022-10
• Subjects: MRI -- Motion-tracking -- Motion calibration -- Motion artifact -- Motion estimation -- In-vivo -- EPI -- Spin-Echo; Medical physics -- Periodicals; Biophysics -- Periodicals; Biophysics -- Periodicals; Imagerie médicale -- Périodiques; Radiothérapie -- Périodiques; Rayons X -- Sécurité -- Mesures -- Périodiques; Physique -- Périodiques; Médecine -- Périodiques; 610.153
• DOI: 10.1016/j.ejmp.2022.09.005
• Languages: English
• ISSNs: 1120-1797

Abstract

Abstract: MRI is a non-invasive medical imaging modality that is sensitive to patient motion, which constitutes a major limitation in most clinical applications. Solutions may arise from the reduction of acquisition times or from motion-correction techniques, either prospective or retrospective. Benchmarking the latter methods requires labeled motion-corrupted datasets, which are uncommon. Up to our best knowledge, no protocol for generating labeled datasets of MRI images corrupted by controlled motion has yet been proposed. Hence, we present a methodology allowing the acquisition of reproducible motion-corrupted MRI images as well as validation of the system's performance by motion estimation through rigid-body volume registration of fast 3D echo-planar imaging (EPI) time series. A proof-of-concept is presented, to show how the protocol can be implemented to provide qualitative and quantitative results. An MRI-compatible video system displays a moving target that volunteers equipped with customized plastic glasses must follow to perform predefined head choreographies. Motion estimation using rigid-body EPI time series registration demonstrated that head position can be accurately determined (with an average standard deviation of about 0.39 degrees). A spatio-temporal upsampling and interpolation method to cope with fast motion is also proposed in order to improve motion estimation. The proposed protocol is versatile and straightforward. It is compatible with all MRI systems and may provide insights on the origins of specific motion artifacts. The MRI and artificial intelligence research communities could benefit from this work to build in-vivo labeled datasets of motion-corrupted MRI images suitable for training/testing any retrospective motion correction or machine learning algorithm. Highlights: Choreography-controlled head motion protocol for MRI. Labeled motion-corrupted MRI dataset generation for Machine Learning. Improved volume to volume registration by temporal upsampling.