Hidden
X-ray Angiography — 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 |
|---|---|---|
| contrast_timing | -0.35 – 1.15 | s |
| motion | -1.4 – 4.6 | mm |
| scatter | -0.035 – 0.115 |
Hidden Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | TV-CS + gradient | 0.678 | 26.94 | 0.857 | 0.83 | ✓ Certified | Rudin et al., Physica D 60:259, 1992; Sidky et al., PMB 2008 |
| 2 | AngioFormer + gradient | 0.677 | 27.62 | 0.873 | 0.76 | ✓ Certified | Geometry-aware transformer for few-view 3DRA, 2024 |
| 3 | NeRF-Angio + gradient | 0.665 | 26.4 | 0.843 | 0.82 | ✓ Certified | Wang et al., IEEE Trans. Med. Imaging 43:1401, 2024 |
| 4 | PnP-ADMM + gradient | 0.639 | 24.85 | 0.797 | 0.86 | ✓ Certified | Venkatakrishnan et al., IEEE GlobalSIP 2013 |
| 5 | Learned Primal-Dual + gradient | 0.621 | 24.65 | 0.791 | 0.79 | ✓ Certified | Adler & Oktem, IEEE TMI 37:1322, 2018 |
| 6 | DiffusionAngio + gradient | 0.603 | 23.98 | 0.768 | 0.78 | ✓ Certified | Shen et al., Med. Image Anal. 94:103102, 2024 |
| 7 | VesselNet + gradient | 0.594 | 23.62 | 0.755 | 0.78 | ✓ Certified | Zhang et al., Radiology AI 6:e230298, 2024 |
| 8 | FBPConvNet + gradient | 0.577 | 22.95 | 0.729 | 0.78 | ✓ Certified | Jin et al., IEEE TIP 26:4509, 2017 |
| 9 | FDK + gradient | 0.565 | 22.11 | 0.695 | 0.83 | ✓ Certified | Feldkamp et al., JOSA A 1(6):612, 1984 |
Dataset
Scenes: 3
Scoring Formula
0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)
PSNR: 40%
SSIM: 40%
Consistency: 20%