Public
Brachytherapy Imaging — Public Tier
(3 scenes)Full-access development tier with all data visible.
What you get
Measurements (y), ideal forward operator (H), spec ranges, ground truth (x_true), and true mismatch spec.
How to use
Load HDF5 → compare reconstruction vs x_true → check consistency → iterate.
What to submit
Reconstructed signals (x_hat) and corrected spec as HDF5.
Parameter Specifications
✓
True spec visible — use these exact values for Scenario III oracle reconstruction.
| Parameter | Spec Range | True Value | Unit |
|---|---|---|---|
| source_position_error | -0.4 – 0.8 | 0.2 | mm |
| attenuation_coefficient | 0.19 – 0.22 | 0.205 | 1/cm |
| detector_gain_drift | 0.99 – 1.02 | 1.005 | - |
| scatter_fraction | 0.13 – 0.19 | 0.16 | - |
InverseNet Baseline Scores
Method: CPU_baseline — Mismatch parameter: nominal
Scenario I (Ideal)
17.61 dB
SSIM 0.3262
Scenario II (Mismatch)
13.04 dB
SSIM 0.0468
Scenario III (Oracle)
16.34 dB
SSIM 0.1224
Per-scene breakdown (4 scenes)
| Scene | PSNR I | SSIM I | PSNR II | SSIM II | PSNR III | SSIM III |
|---|---|---|---|---|---|---|
| scene_00 | 16.58 | 0.3251 | 12.51 | 0.0447 | 15.93 | 0.1214 |
| scene_01 | 18.88 | 0.3252 | 13.74 | 0.0480 | 17.02 | 0.1162 |
| scene_02 | 18.30 | 0.3298 | 13.37 | 0.0496 | 16.55 | 0.1259 |
| scene_03 | 16.68 | 0.3248 | 12.53 | 0.0450 | 15.85 | 0.1262 |
Public Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | DiffusionSeed + gradient | 0.849 | 38.22 | 0.983 | 0.87 | ✓ Certified | Gao et al., Med. Phys. 2024 |
| 2 | CTFormer + gradient | 0.837 | 36.99 | 0.978 | 0.88 | ✓ Certified | Wang et al., MICCAI 2023 |
| 3 | Learned Primal-Dual + gradient | 0.830 | 35.38 | 0.97 | 0.94 | ✓ Certified | Adler & Oktem, IEEE TMI 2018 |
| 4 | DuDoTrans + gradient | 0.825 | 35.97 | 0.973 | 0.88 | ✓ Certified | Wang et al., IEEE TMI 2022 |
| 5 | RED-CNN + gradient | 0.809 | 34.05 | 0.961 | 0.92 | ✓ Certified | Chen et al., IEEE TMI 2017 |
| 6 | Metal-AR-Net + gradient | 0.802 | 33.99 | 0.961 | 0.89 | ✓ Certified | Zhang & Yu, IEEE TMI 2018 |
| 7 | FBPConvNet + gradient | 0.771 | 31.89 | 0.941 | 0.88 | ✓ Certified | Jin et al., IEEE TIP 2017 |
| 8 | TV-ADMM + gradient | 0.733 | 29.3 | 0.906 | 0.89 | ✓ Certified | Boyd et al., Found. Trends Mach. Learn. 2011 |
| 9 | FDK + gradient | 0.672 | 26.03 | 0.833 | 0.89 | ✓ Certified | Feldkamp et al., J. Opt. Soc. Am. A 1984 |
Visible Data Fields
y
H_ideal
spec_ranges
x_true
true_spec
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%