Model card aligned with the paper

README.md

@@ -5,36 +5,38 @@ tags:
 - mri-reconstruction
 - medical-imaging
 - accelerated-mri
-- looped-transformer
 ---
 
-# LoopMR weights
+# One Block Is Enough: LoopMR for Accelerated MRI Reconstruction
 
-Trained models of LoopMR, a looped (weight-tied) SDUM-Restormer for multicoil MRI reconstruction: one denoiser block applied 12 times
-with E2E-VarNet's k-space state and soft data consistency, PromptMR+'s cascade inputs and sensitivity estimator, 4 carried latent
-images and 5 adjacent slices (CMRxRecon: 5 adjacent time frames). 10.27M parameters. Trained with a fixed depth of 12 loops, gradient
-through all 12, 1 - SSIM on the final output.
+Weights of LoopMR. LoopMR reuses a single Restormer block at every iteration of an unrolled reconstruction. Besides the current
+image estimate, the block receives data-consistency inputs and latent images. It uses 12 iterations, 4 latents and 5 adjacent
+slices, with sensitivity maps from PromptMR+'s sensitivity map estimator (SME), and has 10.27M parameters.
 
-The files are read by the loopmri code (`loopmri.evaluate.load_model`), which downloads them to its `weights/` folder on first use.
+Training and evaluation code: the loopmri repository, which downloads these files to its `weights/` folder on first use.
 
-| file | data | test results (SSIM / PSNR dB) |
-|---|---|---|
-| `cc359_rs5_fd_146k.pt` | CC359 12-channel brain, 2-D Poisson-disc R 5 / 10 | PromptMR+'s 10 test volumes, challenge metric: R 5 0.9528 / 37.45, R 10 0.9377 / 35.12 |
-| `knee5_rs5_fd_100k.pt` | fastMRI knee (159 train volumes of `multicoil_val`), random lines R 4 / 8 | 40 held-out volumes: 0.9326 / 39.35 (R 4 0.9424 / 40.44, R 8 0.9161 / 37.54) |
-| `cmr23_rs5_fd_466k.pt` | CMRxRecon2023 cine / mapping (P001-P100), equispaced R 4 / 8 / 10 | 76 held-out files (P101-P120), challenge ranking protocol: 0.9629 / 38.62 |
-| `knee5_sens_prefit/` | sensitivity estimator pre-fitted to plain calibration maps | the starting point of the knee training run |
+| file | dataset |
+|---|---|
+| `cc359_rs5_fd_146k.pt` | Calgary-Campinas (CC359) brain, ×5 / ×10 |
+| `knee5_rs5_fd_100k.pt` | fastMRI knee, ×4 / ×8 |
+| `cmr23_rs5_fd_466k.pt` | CMRxRecon2023 cine and mapping, ×4 / ×8 / ×10 |
+| `knee5_sens_prefit/` | the SME pre-fit the knee training starts from |
 
-Each `.pt` holds `model` (state dict), `cfg` (the training config) and `step`.
+## Results
 
-## Training
+PSNR (dB) / SSIM on the test sets, each dataset with its official protocol (computed on an H100):
 
-AdamW lr 3e-4 (estimator 1e-4, CMRxRecon 2e-4), weight decay 0.01, 500 warm-up steps, gradient-norm clip 0.01, batch 1, bf16 inside the
-block, single seed. The knee model was trained exactly as the code's `configs/knee5_rs5_fd.yaml`. The CC359 and CMRxRecon models used
-the same model, objective, optimiser and schedule, except that their first 90,000 (CC359) / 350,000 (CMRxRecon) steps used a
-sampled-depth objective (4-32 loops per step, gradient through the last 8, every iterate scored) before fixed-depth training took over
-to the same final step.
+| dataset | R | LoopMR | PromptMR+ |
+|---|---|---|---|
+| CC359 brain | ×5 | 37.45 / 0.9528 | 37.28 / 0.9513 |
+| | ×10 | 35.12 / 0.9377 | 34.83 / 0.9346 |
+| fastMRI knee | ×4 | 40.44 / 0.9424 | 40.34 / 0.9410 |
+| | ×8 | 37.54 / 0.9161 | 37.39 / 0.9138 |
+| CMRxRecon2023 heart | ×4 | 41.33 / 0.9795 | 40.91 / 0.9779 |
+| | ×8 | 37.79 / 0.9632 | 37.41 / 0.9605 |
+| | ×10 | 36.37 / 0.9431 | 36.14 / 0.9391 |
 
-## Licence and data
+## Licence
 
-CC BY-NC 4.0 (non-commercial). The models were trained on Calgary-Campinas (CC359), fastMRI and CMRxRecon2023 data, whose terms of use
-apply, and use PromptMR+'s sensitivity estimator (Rutgers non-commercial research licence). Research use only, not for clinical use.
+CC BY-NC 4.0. The models were trained on CC359, fastMRI and CMRxRecon2023 data, whose terms of use apply, and use PromptMR+'s SME
+(Rutgers non-commercial research licence). Research use only, not for clinical use.