i-RIM applied to the fastMRI challenge
About
We, team AImsterdam, summarize our submission to the fastMRI challenge (Zbontar et al., 2018). Our approach builds on recent advances in invertible learning to infer models as presented in Putzky and Welling (2019). Both, our single-coil and our multi-coil model share the same basic architecture.
Patrick Putzky, Dimitrios Karkalousos, Jonas Teuwen, Nikita Miriakov, Bart Bakker, Matthan Caan, Max Welling• 2019
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| MRI Reconstruction | fastMRI Knee (test) | SSIM92.8 | 26 | |
| Accelerated MRI reconstruction | fastMRI knee multi-coil x8 (test) | SSIM88.75 | 10 |
Showing 2 of 2 rows