Dev

SPECT — 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
center_offset -1.8 – 2.7 pixels
collimator_septal -0.024 – 0.036
attenuation -6.0 – 9.0 %
scatter 0.14 – 0.29

Dev Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 PET-ViT + gradient 0.781 33.6 0.958 0.81 ✓ Certified Smith et al., ICCV 2024
2 PETFormer + gradient 0.764 31.25 0.934 0.89 ✓ Certified Li et al., ECCV 2024
3 FBP-PET + gradient 0.693 27.21 0.863 0.88 ✓ Certified Analytical baseline
4 TransEM + gradient 0.691 27.83 0.877 0.81 ✓ Certified Xie et al., 2023
5 ML-EM + gradient 0.683 27.06 0.86 0.84 ✓ Certified Shepp & Vardi, IEEE TPAMI 1982
6 DeepPET + gradient 0.653 25.36 0.813 0.87 ✓ Certified Haggstrom et al., MIA 2019
7 MAPEM-RDP + gradient 0.643 25.08 0.805 0.85 ✓ Certified Nuyts et al., IEEE TMI 2002
8 U-Net-PET + gradient 0.630 25.11 0.806 0.78 ✓ Certified Ronneberger et al. variant, MICCAI 2020
9 OS-EM + gradient 0.621 23.91 0.765 0.88 ✓ Certified Hudson & Larkin, IEEE TMI 1994
10 OSEM + gradient 0.553 21.81 0.682 0.81 ✓ Certified Hudson & Larkin, IEEE TMI 1994

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%
Back to SPECT