XPDNet for MRI Reconstruction: an application to the 2020 fastMRI challenge
arXiv:2010.07290v229 citations
Originality Synthesis-oriented
AI Analysis
This work addresses faster and more accurate MRI reconstruction for medical imaging, but it appears incremental as it builds on existing practices from MRI and computer vision.
The authors tackled MRI reconstruction from under-sampled multi-coil data by developing the XPDNet, which achieved state-of-the-art results, ranking second in the fastMRI 2020 challenge.
We present a new neural network, the XPDNet, for MRI reconstruction from periodically under-sampled multi-coil data. We inform the design of this network by taking best practices from MRI reconstruction and computer vision. We show that this network can achieve state-of-the-art reconstruction results, as shown by its ranking of second in the fastMRI 2020 challenge.