Hidden

Fluoroscopy — 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
motion_blur -3.5 – 11.5 ms
lag -2.1 – 6.9 ms
gain_drift -0.35 – 1.15 %

Hidden Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 PhysFluoro + gradient 0.756 30.84 0.929 0.88 ✓ Certified Chen et al., IEEE TMI 2024
2 TransFluoro + gradient 0.755 31.57 0.938 0.82 ✓ Certified Wang et al., IEEE TMI 2022
3 DiffFluoro + gradient 0.714 28.39 0.889 0.87 ✓ Certified Gao et al., MICCAI 2024
4 SwinFluoro + gradient 0.666 25.97 0.831 0.87 ✓ Certified Li et al., Med. Phys. 2023
5 REDCNN-Fluoro + gradient 0.635 25.29 0.811 0.79 ✓ Certified Chen et al., IEEE TMI 2017
6 NLM-Fluoro + gradient 0.616 23.69 0.757 0.88 ✓ Certified Buades et al., CVPR 2005
7 DnCNN-Fluoro + gradient 0.606 24.37 0.781 0.75 ✓ Certified Chen et al., IEEE TMI 2017
8 BM3D-Fluoro + gradient 0.531 21.31 0.66 0.77 ✓ Certified Dabov et al., IEEE TIP 2007
9 TV-Fluoro + gradient 0.399 16.35 0.418 0.84 ✓ Certified Sidky & Pan, Phys. Med. Biol. 2008

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 Fluoroscopy