Public

PET/CT — Public Tier

(3 scenes)

Full-access development tier with all data visible.

What you get

Measurements (y), ideal forward operator (H), spec ranges, ground truth (x_true), and true mismatch spec.

How to use

Load HDF5 → compare reconstruction vs x_true → check consistency → iterate.

What to submit

Reconstructed signals (x_hat) and corrected spec as HDF5.

Parameter Specifications

✓

True spec visible — use these exact values for Scenario III oracle reconstruction.

Parameter Spec Range True Value Unit
ct_registration_shift -4.0 – 8.0 2.0 pixels
hu_to_mu_scale -10.0 – 20.0 5.0 %
scatter_fraction -0.15 – 0.3 0.075

InverseNet Baseline Scores

Method: CPU_baseline — Mismatch parameter: nominal

Scenario I (Ideal)

7.72 dB

SSIM 0.3738

Scenario II (Mismatch)

7.66 dB

SSIM 0.2292

Scenario III (Oracle)

16.33 dB

SSIM 0.4587

Per-scene breakdown (4 scenes)
Scene PSNR I SSIM I PSNR II SSIM II PSNR III SSIM III
scene_00 7.57 0.3615 7.52 0.2249 16.28 0.4660
scene_01 7.70 0.3833 7.81 0.2328 16.28 0.4522
scene_02 7.97 0.3846 7.55 0.2285 16.43 0.4500
scene_03 7.63 0.3655 7.75 0.2308 16.33 0.4667

Public Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 DiffusionCT + gradient 0.863 38.14 0.983 0.94 ✓ Certified Kazemi et al., ECCV 2024
2 CTFormer + gradient 0.859 38.02 0.982 0.93 ✓ Certified Li et al., ICCV 2024
3 DOLCE + gradient 0.847 37.14 0.979 0.92 ✓ Certified Liu et al., ICCV 2023
4 Score-CT + gradient 0.846 38.08 0.982 0.86 ✓ Certified Song et al., NeurIPS 2024
5 CT-ViT + gradient 0.838 37.21 0.979 0.87 ✓ Certified Guo et al., NeurIPS 2024
6 DuDoTrans + gradient 0.818 35.4 0.97 0.88 ✓ Certified Wang et al., MLMIR 2022
7 Learned Primal-Dual + gradient 0.804 34.43 0.964 0.87 ✓ Certified Adler & Oktem, IEEE TMI 2018
8 FBPConvNet + gradient 0.797 34.03 0.961 0.86 ✓ Certified Jin et al., IEEE TIP 2017
9 RED-CNN + gradient 0.786 32.2 0.945 0.93 ✓ Certified Chen et al., IEEE TMI 2017
10 PnP-ADMM + gradient 0.776 31.63 0.939 0.92 ✓ Certified Venkatakrishnan et al., IEEE GlobalSIP 2013
11 PnP-DnCNN + gradient 0.763 31.61 0.938 0.86 ✓ Certified Zhang et al., IEEE TIP 2017
12 TV-ADMM + gradient 0.708 27.97 0.88 0.88 ✓ Certified Sidky et al., Phys. Med. Biol. 2008
13 FBP + gradient 0.644 24.72 0.793 0.9 ✓ Certified Kak & Slaney, IEEE Press 1988

Visible Data Fields

y H_ideal spec_ranges x_true true_spec

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 PET/CT