Meeting Banner
Abstract #4098

Motion correction in MRI using deep learning

Patricia M Johnson1,2 and Maria Drangova1,2

1Robarts Research Institute, London, ON, Canada, 2Medical Biophysics, Western University, London, ON, Canada

Subject motion in brain MRI remains an unsolved problem. We propose a machine learning approach for motion correction of brain images. Our initial objective is to train a neural network to perform a motion corrected image reconstruction on image data with simulated motion artefacts. Training pairs were generated using an open source MRI data set; a unique motion profile was applied to each 2D image. A deep neural network was developed and trained with over 3000 image pairs. The images predicted by the network, from motion-corrupted k-space, have improved image quality compared to the motion corrupted images.

This abstract and the presentation materials are available to members only; a login is required.

Join Here