Hidden

Neutron Tomo — 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
beam_spectrum -2.1 – 6.9 %
scatter_correction -3.5 – 11.5 %
rotation_offset -0.7 – 2.3 pixels

Hidden Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 PETFormer + gradient 0.666 26.06 0.834 0.86 ✓ Certified Li et al., ECCV 2024
2 FBP-PET + gradient 0.596 23.92 0.766 0.75 ✓ Certified Analytical baseline
3 TransEM + gradient 0.560 22.45 0.709 0.76 ✓ Certified Xie et al., 2023
4 U-Net-PET + gradient 0.526 21.08 0.649 0.78 ✓ Certified Ronneberger et al. variant, MICCAI 2020
5 DeepPET + gradient 0.520 21.07 0.649 0.75 ✓ Certified Haggstrom et al., MIA 2019
6 ML-EM + gradient 0.519 20.4 0.618 0.84 ✓ Certified Shepp & Vardi, IEEE TPAMI 1982
7 PET-ViT + gradient 0.491 19.24 0.562 0.87 ✓ Certified Smith et al., ICCV 2024
8 OS-EM + gradient 0.472 19.15 0.557 0.79 ✓ Certified Hudson & Larkin, IEEE TMI 1994
9 OSEM + gradient 0.471 18.7 0.535 0.85 ✓ Certified Hudson & Larkin, IEEE TMI 1994
10 MAPEM-RDP + gradient 0.465 18.45 0.522 0.86 ✓ Certified Nuyts et al., IEEE TMI 2002

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 Neutron Tomo