MoCo_cGAN: A conditional generative adverserial network designed to predict motion free MR images from motion-corrupted data. This model is based off of work done by Patricia Johnson (https://github.com/pjohnson519/MoCo_cGAN):
PM Johnson, M Drangova. Conditional generative adversarial network for three-dimensional rigid-body motion correction in MRI, Magn Reson Med, 2019.
This version includes options to perform motion correction using complex, multichannel data prior to coil combination, as described in the following publication:
M Hewlett et al. Deep-learning-based motion correction using multichannel MRI data: a study using simulated artifacts in the fastMRI dataset, NMR Biomed, 2024.