Dev
X-ray Angiography — 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 |
|---|---|---|
| contrast_timing | -0.6 – 0.9 | s |
| motion | -2.4 – 3.6 | mm |
| scatter | -0.06 – 0.09 |
Dev Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | AngioFormer + gradient | 0.746 | 30.2 | 0.92 | 0.88 | ✓ Certified | Geometry-aware transformer for few-view 3DRA, 2024 |
| 2 | NeRF-Angio + gradient | 0.704 | 28.4 | 0.889 | 0.82 | ✓ Certified | Wang et al., IEEE Trans. Med. Imaging 43:1401, 2024 |
| 3 | TV-CS + gradient | 0.698 | 27.99 | 0.881 | 0.83 | ✓ Certified | Rudin et al., Physica D 60:259, 1992; Sidky et al., PMB 2008 |
| 4 | VesselNet + gradient | 0.669 | 26.61 | 0.848 | 0.82 | ✓ Certified | Zhang et al., Radiology AI 6:e230298, 2024 |
| 5 | DiffusionAngio + gradient | 0.667 | 25.83 | 0.827 | 0.89 | ✓ Certified | Shen et al., Med. Image Anal. 94:103102, 2024 |
| 6 | PnP-ADMM + gradient | 0.666 | 26.04 | 0.833 | 0.86 | ✓ Certified | Venkatakrishnan et al., IEEE GlobalSIP 2013 |
| 7 | Learned Primal-Dual + gradient | 0.660 | 25.6 | 0.821 | 0.88 | ✓ Certified | Adler & Oktem, IEEE TMI 37:1322, 2018 |
| 8 | FBPConvNet + gradient | 0.653 | 25.56 | 0.819 | 0.85 | ✓ Certified | Jin et al., IEEE TIP 26:4509, 2017 |
| 9 | FDK + gradient | 0.604 | 24.0 | 0.769 | 0.78 | ✓ Certified | Feldkamp et al., JOSA A 1(6):612, 1984 |
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%