Public

Proton Therapy Imaging — 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
range_uncertainty -0.6 – 1.2 0.3 mm
scattering_power_error 0.99 – 1.02 1.005 -
detector_efficiency_drift 0.84 – 0.87 0.855 -
setup_error -0.4 – 0.8 0.2 mm

InverseNet Baseline Scores

Method: CPU_baseline — Mismatch parameter: nominal

Scenario I (Ideal)

17.61 dB

SSIM 0.3262

Scenario II (Mismatch)

13.04 dB

SSIM 0.0468

Scenario III (Oracle)

16.34 dB

SSIM 0.1224

Per-scene breakdown (4 scenes)
Scene PSNR I SSIM I PSNR II SSIM II PSNR III SSIM III
scene_00 16.58 0.3251 12.51 0.0447 15.93 0.1214
scene_01 18.88 0.3252 13.74 0.0480 17.02 0.1162
scene_02 18.30 0.3298 13.37 0.0496 16.55 0.1259
scene_03 16.68 0.3248 12.53 0.0450 15.85 0.1262

Public Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 DiffusionCT + gradient 0.863 38.36 0.983 0.93 ✓ Certified Kazemi et al., ECCV 2024
2 Score-CT + gradient 0.845 37.5 0.98 0.89 ✓ Certified Song et al., NeurIPS 2024
3 CTFormer + gradient 0.839 36.8 0.977 0.9 ✓ Certified Li et al., ICCV 2024
4 DuDoTrans + gradient 0.839 36.25 0.975 0.93 ✓ Certified Wang et al., MLMIR 2022
5 CT-ViT + gradient 0.835 36.5 0.976 0.9 ✓ Certified Guo et al., NeurIPS 2024
6 DOLCE + gradient 0.826 35.87 0.973 0.89 ✓ Certified Liu et al., ICCV 2023
7 FBPConvNet + gradient 0.815 34.05 0.961 0.95 ✓ Certified Jin et al., IEEE TIP 2017
8 Learned Primal-Dual + gradient 0.805 34.54 0.965 0.87 ✓ Certified Adler & Oktem, IEEE TMI 2018
9 PnP-DnCNN + gradient 0.760 30.96 0.93 0.89 ✓ Certified Zhang et al., IEEE TIP 2017
10 RED-CNN + gradient 0.758 30.6 0.926 0.91 ✓ Certified Chen et al., IEEE TMI 2017
11 PnP-ADMM + gradient 0.751 30.67 0.926 0.87 ✓ Certified Venkatakrishnan et al., IEEE GlobalSIP 2013
12 TV-ADMM + gradient 0.707 27.83 0.877 0.89 ✓ Certified Sidky et al., Phys. Med. Biol. 2008
13 FBP + gradient 0.676 25.79 0.826 0.94 ✓ 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 Proton Therapy Imaging