Fig. 1
From: Improving MR image quality with a multi-task model, using convolutional losses
Artefact augmentations and their corrections by the MT+\(\mathcal {L}_C\) model for an example image (seen in the top row). The second row shows the artefacted images, while the fourth row shows their correction by the trained model. The figure shows examples for all artefact types from left to right: bias, k-space subsampling, motion, and noise. For each artefact type, the images and their difference to the original clean image are shown in the third and fifth row, respectively