Hidden
Muon Tomo — Hidden Tier
(3 scenes)Fully blind server-side evaluation — no data download.
What you get
No data downloadable. Algorithm runs server-side on hidden measurements.
How to use
Package algorithm as Docker container / Python script. Submit via link.
What to submit
Containerized algorithm accepting y + H, outputting x_hat + corrected spec.
Parameter Specifications
🔒
True spec hidden — blind evaluation, only ranges available.
| Parameter | Spec Range | Unit |
|---|---|---|
| angular_resolution | -1.4 – 4.6 | mrad |
| momentum_estimate | -7.0 – 23.0 | % |
| detector_efficiency | -2.1 – 6.9 | % |
Hidden Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | TransEM + gradient | 0.671 | 26.18 | 0.837 | 0.87 | ✓ Certified | Xie et al., 2023 |
| 2 | PETFormer + gradient | 0.640 | 25.16 | 0.807 | 0.83 | ✓ Certified | Li et al., ECCV 2024 |
| 3 | PET-ViT + gradient | 0.605 | 23.58 | 0.753 | 0.84 | ✓ Certified | Smith et al., ICCV 2024 |
| 4 | FBP-PET + gradient | 0.589 | 22.66 | 0.717 | 0.88 | ✓ Certified | Analytical baseline |
| 5 | MAPEM-RDP + gradient | 0.587 | 23.34 | 0.744 | 0.78 | ✓ Certified | Nuyts et al., IEEE TMI 2002 |
| 6 | DeepPET + gradient | 0.579 | 22.54 | 0.713 | 0.84 | ✓ Certified | Haggstrom et al., MIA 2019 |
| 7 | ML-EM + gradient | 0.577 | 22.71 | 0.72 | 0.81 | ✓ Certified | Shepp & Vardi, IEEE TPAMI 1982 |
| 8 | OSEM + gradient | 0.570 | 22.39 | 0.706 | 0.82 | ✓ Certified | Hudson & Larkin, IEEE TMI 1994 |
| 9 | OS-EM + gradient | 0.504 | 20.08 | 0.603 | 0.81 | ✓ Certified | Hudson & Larkin, IEEE TMI 1994 |
| 10 | U-Net-PET + gradient | 0.470 | 18.68 | 0.534 | 0.85 | ✓ Certified | Ronneberger et al. variant, MICCAI 2020 |
Dataset
Scenes: 3
Scoring Formula
0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)
PSNR: 40%
SSIM: 40%
Consistency: 20%