Dev
Doppler Ultrasound — Dev Tier
(3 scenes)Blind evaluation tier — no ground truth available.
What you get
Measurements (y), ideal forward operator (H), and spec ranges only.
How to use
Apply your pipeline from the Public tier. Use consistency as self-check.
What to submit
Reconstructed signals and corrected spec. Scored server-side.
Parameter Specifications
🔒
True spec hidden — estimate parameters from spec ranges below.
| Parameter | Spec Range | Unit |
|---|---|---|
| sos | 1522.0 – 1567.0 | m/s |
| doppler_angle | -6.0 – 9.0 | deg |
| wall_filter | 14.0 – 104.0 | Hz |
| prf | -1.2 – 1.8 | % |
Dev Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | SwinDoppler + gradient | 0.790 | 33.65 | 0.958 | 0.85 | ✓ Certified | Li et al., Ultrasound Med. Biol. 2023 |
| 2 | PhysDoppler + gradient | 0.759 | 31.61 | 0.938 | 0.84 | ✓ Certified | Perdios et al., Sci. Rep. 2024 |
| 3 | TransFlow + gradient | 0.753 | 31.72 | 0.94 | 0.8 | ✓ Certified | Wang et al., IEEE TUFFC 2022 |
| 4 | DiffDoppler + gradient | 0.731 | 30.41 | 0.923 | 0.79 | ✓ Certified | Gao et al., MICCAI 2024 |
| 5 | FlowNet-US + gradient | 0.573 | 22.66 | 0.717 | 0.8 | ✓ Certified | Nair et al., IEEE TMI 2020 |
| 6 | VENC-Flow + gradient | 0.536 | 21.0 | 0.646 | 0.84 | ✓ Certified | Moran, Magn. Reson. Imaging 1982 |
| 7 | DnCNN-Doppler + gradient | 0.503 | 19.78 | 0.588 | 0.85 | ✓ Certified | Perdios et al., IEEE TUFFC 2018 |
| 8 | CF-Doppler + gradient | 0.472 | 19.15 | 0.557 | 0.79 | ✓ Certified | Evans & McDicken, Doppler Ultrasound 2000 |
| 9 | MV-Doppler + gradient | 0.451 | 18.38 | 0.519 | 0.8 | ✓ Certified | Langeland et al., IEEE TUFFC 2003 |
Visible Data Fields
y
H_ideal
spec_ranges
Dataset
Format: HDF5
Scenes: 3
Scoring Formula
0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)
PSNR: 40%
SSIM: 40%
Consistency: 20%