XPDNet for MRI Reconstruction: an application to the 2020 fastMRI challenge
About
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.
Zaccharie Ramzi, Philippe Ciuciu, Jean-Luc Starck• 2020
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| MRI Reconstruction | fastMRI 4X acceleration (test) | -- | 32 | |
| MRI Reconstruction | fastMRI 8X acceleration (test) | SSIM0.942 | 11 | |
| Accelerated MRI reconstruction | fastMRI knee multi-coil x8 (test) | SSIM88.93 | 10 |
Showing 3 of 3 rows