Skip to main content
. Author manuscript; available in PMC: 2021 Mar 1.
Published in final edited form as: IEEE Trans Med Imaging. 2020 Mar 5;39(9):2881–2892. doi: 10.1109/TMI.2020.2972547

Fig. 1.

Fig. 1

Motion artefact augmentation framework: The artefact-free input volume is resampled according to a randomly sampled movement model, defined by a sequence of ‘demeaned’ 3D affine transforms. Their 3D Fourier transforms are combined to form a composite k-space, which is transformed back to the image domain producing the final artefact volume.