Back to Search
Start Over
Correction of Motion Artifacts Using a Multiscale Fully Convolutional Neural Network.
- Source :
-
AJNR. American journal of neuroradiology [AJNR Am J Neuroradiol] 2020 Mar; Vol. 41 (3), pp. 416-423. Date of Electronic Publication: 2020 Feb 13. - Publication Year :
- 2020
-
Abstract
- Background and Purpose: Motion artifacts are a frequent source of image degradation in the clinical application of MR imaging (MRI). Here we implement and validate an MRI motion-artifact correction method using a multiscale fully convolutional neural network.<br />Materials and Methods: The network was trained to identify motion artifacts in axial T2-weighted spin-echo images of the brain. Using an extensive data augmentation scheme and a motion artifact simulation pipeline, we created a synthetic training dataset of 93,600 images based on only 16 artifact-free clinical MRI cases. A blinded reader study using a unique test dataset of 28 additional clinical MRI cases with real patient motion was conducted to evaluate the performance of the network.<br />Results: Application of the network resulted in notably improved image quality without the loss of morphologic information. For synthetic test data, the average reduction in mean squared error was 41.84%. The blinded reader study on the real-world test data resulted in significant reduction in mean artifact scores across all cases ( Pā <ā.03).<br />Conclusions: Retrospective correction of motion artifacts using a multiscale fully convolutional network is promising and may mitigate the substantial motion-related problems in the clinical MRI workflow.<br /> (© 2020 by American Journal of Neuroradiology.)
Details
- Language :
- English
- ISSN :
- 1936-959X
- Volume :
- 41
- Issue :
- 3
- Database :
- MEDLINE
- Journal :
- AJNR. American journal of neuroradiology
- Publication Type :
- Academic Journal
- Accession number :
- 32054615
- Full Text :
- https://doi.org/10.3174/ajnr.A6436