Hidden
Ultrasound — 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 |
|---|---|---|
| sos | 1526.0 – 1586.0 | m/s |
| attenuation | 0.43 – 0.73 | dB/cm/MHz |
| element_sensitivity | -3.5 – 11.5 | % |
| phase_aberration | -0.21 – 0.69 | rad |
Hidden Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | UltrasoundFormer + gradient | 0.688 | 27.54 | 0.871 | 0.82 | ✓ Certified | Park et al., CVPR 2024 |
| 2 | BeamDATA + gradient | 0.675 | 27.42 | 0.868 | 0.77 | ✓ Certified | Smith et al., ICCV 2024 |
| 3 | AttentionBeam + gradient | 0.664 | 26.57 | 0.847 | 0.8 | ✓ Certified | Xu et al., ECCV 2024 |
| 4 | Phase-ADMM-Net + gradient | 0.637 | 25.08 | 0.805 | 0.82 | ✓ Certified | Hou et al., IEEE TMI 2022 |
| 5 | BeamFormer + gradient | 0.633 | 25.53 | 0.818 | 0.75 | ✓ Certified | Li et al., ICCV 2024 |
| 6 | ScoreUS + gradient | 0.609 | 24.31 | 0.779 | 0.77 | ✓ Certified | Johnson et al., ECCV 2025 |
| 7 | PW-DAS + gradient | 0.592 | 23.22 | 0.74 | 0.82 | ✓ Certified | Plane wave synthesis baseline |
| 8 | DiffUS + gradient | 0.557 | 21.81 | 0.682 | 0.83 | ✓ Certified | Chen et al., NeurIPS 2024 |
| 9 | PnP-ADMM + gradient | 0.534 | 21.33 | 0.661 | 0.78 | ✓ Certified | Goudarzi et al., 2020 |
| 10 | MU-Net + gradient | 0.522 | 20.83 | 0.638 | 0.79 | ✓ Certified | Hyun et al., IEEE TUFFC 2022 |
| 11 | DAS-CF + gradient | 0.515 | 20.88 | 0.64 | 0.75 | ✓ Certified | Capon filter, IEEE 1969 |
| 12 | ABLE + gradient | 0.511 | 19.84 | 0.591 | 0.88 | ✓ Certified | Luijten et al., IEEE TMI 2020 |
| 13 | DAS + gradient | 0.490 | 19.68 | 0.583 | 0.8 | ✓ Certified | Analytical baseline |
| 14 | PnP-TV + gradient | 0.438 | 17.52 | 0.476 | 0.86 | ✓ Certified | TV regularization for ultrasound |
Dataset
Scenes: 3
Scoring Formula
0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)
PSNR: 40%
SSIM: 40%
Consistency: 20%