¶
Leaderboard - Second round¶
Based on the median rank profile for SSIM scores, the top five submissions from each task were assessed by a panel of radiographers and radiologists. The median rank profile of these observer quality scores (QS) determines the final ranking (QS-rank) for each task. The definition of the quality scores can be found under Evaluation.
Test Results - Task 1:¶
The columns SSIM and QS show average values across all test subjects. Files containing individual SSIM and QS values for all teams are available under: Metric_Values.zip.
Test Results - Task 2:¶
Files containing individual SSIM and QS values for all teams are available under: Metric_Values.zip.
Participating Teams:¶
| Team Name | Participants | Description | Details |
| MBI | Kamlesh Pawar, Gary F. Egan, Zhaolin
Chen |
Variational network for simultaneous motion correction and accelerated imaging | fastMRI brain dataset used for pre-training |
| MLI_lab | Mohammad Zalbagi Darestani, Tobit
Klug, Reinhard Heckel |
End-to-end variational network augmented with motion simulation | AXT1 volumes of the fastMRI dataset used for pre-training |
| SubtleMedical | Kevin Blansit, Zhehao Hu, Zechen Zhou, Keshav Datta, Ben Duffy | Deep convolutional neural network (DCNN), combined SSIM and L1 loss | non-public data (T1/T2/FLAIR) used for training |
| Uniandes | María Escobar, Cristhian Forigua, Pablo Arbeláez | SwinIR Transformer + Robust Adversarial Training with PGD with Charbonnier loss | fastMRI dataset used for training |
| UVABME | Quan Dou, Xue Feng, Craig Meyer |
U-Net, combined SSIM and L1 loss |
fastMRI dataset used for training |