Dev
Digital Breast Tomosynthesis (DBT) — 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 |
|---|---|---|
| angular_range_error | -0.48 – 0.72 | degtotal |
| detector_motion_blur | -0.12 – 0.18 | px |
| scatter_fraction | 0.228 – 0.408 | - |
Dev Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | PhysDBT + gradient | 0.744 | 30.11 | 0.918 | 0.88 | ✓ Certified | Nett et al., IEEE TMI 2024 |
| 2 | SwinDBT + gradient | 0.730 | 30.48 | 0.924 | 0.78 | ✓ Certified | Li et al., Med. Phys. 2023 |
| 3 | DiffusionDBT + gradient | 0.723 | 28.74 | 0.895 | 0.89 | ✓ Certified | Gao et al., MICCAI 2024 |
| 4 | TransDBT + gradient | 0.712 | 28.39 | 0.889 | 0.86 | ✓ Certified | Wang et al., MICCAI 2022 |
| 5 | DuDoRNet-DBT + gradient | 0.649 | 25.55 | 0.819 | 0.83 | ✓ Certified | Zhou et al., CVPR 2020 |
| 6 | SART-DBT + gradient | 0.602 | 23.15 | 0.737 | 0.88 | ✓ Certified | Andersen & Kak, Ultrason. Imaging 1984 |
| 7 | DnCNN-DBT + gradient | 0.600 | 23.23 | 0.74 | 0.86 | ✓ Certified | Chen et al., IEEE TMI 2018 |
| 8 | FBP-DBT + gradient | 0.514 | 20.57 | 0.626 | 0.79 | ✓ Certified | Sechopoulos, Med. Phys. 2013 |
| 9 | TV-DBT + gradient | 0.410 | 16.39 | 0.42 | 0.89 | ✓ Certified | Sidky et al., Med. Phys. 2014 |
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%