XPDNet for MRI Reconstruction: an application to the 2020 fastMRI 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.
PDF AbstractCode
Datasets
fastMRI
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| MRI Reconstruction | fastMRI Brain 4x | XPDNet | SSIM | 0.9581 | # 2 | |
| PSNR | 41.3 | # 1 | ||||
| MRI Reconstruction | fastMRI Brain 8x | XPDNet | SSIM | 0.9408 | # 2 | |
| PSNR | 38.1 | # 1 | ||||
| MRI Reconstruction | fastMRI Knee 4x | XPDNet | SSIM | 0.9287 | # 2 | |
| PSNR | 40.2 | # 1 | ||||
| MRI Reconstruction | fastMRI Knee 8x | XPDNet | SSIM | 0.8893 | # 4 | |
| PSNR | 37.2 | # 2 |
Methods
No methods listed for this paper. Add
relevant methods here
