PT  - JOURNAL ARTICLE
AU  - K. Sommer
AU  - A. Saalbach
AU  - T. Brosch
AU  - C. Hall
AU  - N.M. Cross
AU  - J.B. Andre
TI  - Correction of Motion Artifacts Using a Multiscale Fully Convolutional Neural Network
AID  - 10.3174/ajnr.A6436
DP  - 2020 Mar 01
TA  - American Journal of Neuroradiology
PG  - 416--423
VI  - 41
IP  - 3
4099  - http://www.ajnr.org/content/41/3/416.short
4100  - http://www.ajnr.org/content/41/3/416.full
SO  - Am. J. Neuroradiol.2020 Mar 01; 41
AB  - 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.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.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 (P < .03).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.FCNfully convolutional neural networkMSEmean squared errorSSIMstructural similarity index