Hidden

PET/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 -2.8 – 9.2 pixels
hu_to_mu_scale -7.0 – 23.0 %
scatter_fraction -0.105 – 0.345

Hidden Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 CTFormer + gradient 0.779 32.81 0.951 0.85 ✓ Certified Li et al., ICCV 2024
2 CT-ViT + gradient 0.739 30.53 0.925 0.82 ✓ Certified Guo et al., NeurIPS 2024
3 DiffusionCT + gradient 0.727 29.89 0.915 0.81 ✓ Certified Kazemi et al., ECCV 2024
4 DuDoTrans + gradient 0.684 27.98 0.88 0.76 ✓ Certified Wang et al., MLMIR 2022
5 Score-CT + gradient 0.666 26.32 0.841 0.83 ✓ Certified Song et al., NeurIPS 2024
6 DOLCE + gradient 0.647 26.11 0.835 0.76 ✓ Certified Liu et al., ICCV 2023
7 TV-ADMM + gradient 0.638 25.43 0.815 0.79 ✓ Certified Sidky et al., Phys. Med. Biol. 2008
8 PnP-DnCNN + gradient 0.616 24.86 0.798 0.74 ✓ Certified Zhang et al., IEEE TIP 2017
9 FBP + gradient 0.609 24.5 0.786 0.75 ✓ Certified Kak & Slaney, IEEE Press 1988
10 FBPConvNet + gradient 0.599 23.99 0.768 0.76 ✓ Certified Jin et al., IEEE TIP 2017
11 PnP-ADMM + gradient 0.599 24.08 0.771 0.75 ✓ Certified Venkatakrishnan et al., IEEE GlobalSIP 2013
12 Learned Primal-Dual + gradient 0.587 23.65 0.756 0.74 ✓ Certified Adler & Oktem, IEEE TMI 2018
13 RED-CNN + gradient 0.540 21.72 0.678 0.76 ✓ Certified Chen et al., IEEE TMI 2017

Dataset

Scenes: 3

Scoring Formula

0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)

PSNR: 40% SSIM: 40% Consistency: 20%
Back to PET/CT