Dev
PET/CT — 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 |
|---|---|---|
| ct_registration_shift | -4.8 – 7.2 | pixels |
| hu_to_mu_scale | -12.0 – 18.0 | % |
| scatter_fraction | -0.18 – 0.27 |
Dev Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | CTFormer + gradient | 0.801 | 35.3 | 0.97 | 0.8 | ✓ Certified | Li et al., ICCV 2024 |
| 2 | CT-ViT + gradient | 0.800 | 34.44 | 0.964 | 0.85 | ✓ Certified | Guo et al., NeurIPS 2024 |
| 3 | DiffusionCT + gradient | 0.753 | 30.78 | 0.928 | 0.87 | ✓ Certified | Kazemi et al., ECCV 2024 |
| 4 | Score-CT + gradient | 0.739 | 29.54 | 0.91 | 0.9 | ✓ Certified | Song et al., NeurIPS 2024 |
| 5 | DuDoTrans + gradient | 0.720 | 28.88 | 0.898 | 0.86 | ✓ Certified | Wang et al., MLMIR 2022 |
| 6 | Learned Primal-Dual + gradient | 0.698 | 27.79 | 0.876 | 0.85 | ✓ Certified | Adler & Oktem, IEEE TMI 2018 |
| 7 | DOLCE + gradient | 0.692 | 27.32 | 0.866 | 0.86 | ✓ Certified | Liu et al., ICCV 2023 |
| 8 | PnP-DnCNN + gradient | 0.692 | 27.98 | 0.88 | 0.8 | ✓ Certified | Zhang et al., IEEE TIP 2017 |
| 9 | PnP-ADMM + gradient | 0.672 | 25.96 | 0.831 | 0.9 | ✓ Certified | Venkatakrishnan et al., IEEE GlobalSIP 2013 |
| 10 | FBPConvNet + gradient | 0.670 | 26.55 | 0.847 | 0.83 | ✓ Certified | Jin et al., IEEE TIP 2017 |
| 11 | FBP + gradient | 0.668 | 26.25 | 0.839 | 0.85 | ✓ Certified | Kak & Slaney, IEEE Press 1988 |
| 12 | TV-ADMM + gradient | 0.662 | 25.75 | 0.825 | 0.87 | ✓ Certified | Sidky et al., Phys. Med. Biol. 2008 |
| 13 | RED-CNN + gradient | 0.602 | 23.24 | 0.74 | 0.87 | ✓ Certified | Chen et al., IEEE TMI 2017 |
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%