K Sommer1, A Saalbach2, T Brosch2, C Hall3, N M Cross4, J B Andre4. 1. From Philips Research, (K.S., A.S., T.B.) Hamburg, Germany karsten.sommer@philips.com. 2. From Philips Research, (K.S., A.S., T.B.) Hamburg, Germany. 3. Radiology Solutions (C.H.), Philips, Seattle, Washington. 4. Department of Radiology (N.M.C., J.B.A.), University of Washington, Seattle, Washington.
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. 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.
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.
Authors: Peter Kochunov; Jack L Lancaster; David C Glahn; David Purdy; Angela R Laird; Feng Gao; Peter Fox Journal: Hum Brain Mapp Date: 2006-12 Impact factor: 5.038
Authors: M V McConnell; V C Khasgiwala; B J Savord; M H Chen; M L Chuang; R R Edelman; W J Manning Journal: Magn Reson Med Date: 1997-01 Impact factor: 4.668
Authors: Theodore D Satterthwaite; Daniel H Wolf; James Loughead; Kosha Ruparel; Mark A Elliott; Hakon Hakonarson; Ruben C Gur; Raquel E Gur Journal: Neuroimage Date: 2012-01-02 Impact factor: 6.556
Authors: Sahil S Nalawade; Fang F Yu; Chandan Ganesh Bangalore Yogananda; Gowtham K Murugesan; Bhavya R Shah; Marco C Pinho; Benjamin C Wagner; Yin Xi; Bruce Mickey; Toral R Patel; Baowei Fei; Ananth J Madhuranthakam; Joseph A Maldjian Journal: J Med Imaging (Bellingham) Date: 2022-01-27
Authors: Anouk S Verschuur; Vivian Boswinkel; Chantal M W Tax; Jochen A C van Osch; Ingrid M Nijholt; Cornelis H Slump; Linda S de Vries; Gerda van Wezel-Meijler; Alexander Leemans; Martijn F Boomsma Journal: J Neuroimaging Date: 2022-03-07 Impact factor: 2.324