Hidden
SPECT/CT — 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 |
|---|---|---|
| ct_registration_shift | -3.5 – 11.5 | pixels |
| hu_to_mu_scale | -8.4 – 27.6 | % |
| scatter_fraction | -0.245 – 0.805 | |
| collimator_blur | 0.05 – 10.55 | pixels |
Hidden Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | AC-OSEM + gradient | 0.686 | 27.46 | 0.869 | 0.82 | ✓ Certified | CT-based attenuation correction |
| 2 | MAP-OSEM + gradient | 0.667 | 27.19 | 0.863 | 0.75 | ✓ Certified | Nuyts et al., 2002 |
| 3 | DL-SPECT + gradient | 0.660 | 26.74 | 0.852 | 0.76 | ✓ Certified | Ramon et al., IEEE TMI 2020 |
| 4 | OSEM + gradient | 0.508 | 20.3 | 0.613 | 0.8 | ✓ Certified | Hudson & Larkin, IEEE TMI 1994 |
Dataset
Scenes: 3
Scoring Formula
0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)
PSNR: 40%
SSIM: 40%
Consistency: 20%