Zaccharie Ramzi1,2,3, Philippe Ciuciu1,2, Jean-Luc Starck3, and Alexandre Vignaud1
1Neurospin, Gif-Sur-Yvette, France, 2Parietal team, Inria Saclay, Gif-Sur-Yvette, France, 3Cosmostat team, CEA, Gif-Sur-Yvette, France
1Neurospin, Gif-Sur-Yvette, France, 2Parietal team, Inria Saclay, Gif-Sur-Yvette, France, 3Cosmostat team, CEA, Gif-Sur-Yvette, France
XPDNet, a state-of-the-art deep learning approach for MRI reconstruction, can generalize well when compared to GRAPPA on unseen settings.
Magnitude reconstruction results for a brain acquired at acceleration factor 2, contrast T2, and field strength of 7T. The top row represents the reconstruction using the different methods, while the bottom one represents a zoom in the cerebellum region, an anatomical feature that was not present in the XPDNet training set.
Magnitude reconstruction results for a specific fastMRI slice with T2 contrast, at acceleration factor 8. The top row represents the reconstruction using the different methods, while the bottom row represents the error when compared to the reference.
