Hidden

Endoscopy — 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
fiber_coupling -3.5 – 11.5 %
core_spacing -0.35 – 1.15 μm
bending_loss -0.21 – 0.69 dB

Hidden Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 SwinEndo + gradient 0.739 30.27 0.921 0.84 ✓ Certified Li et al., IEEE TMI 2023
2 TransEndo + gradient 0.727 29.29 0.905 0.86 ✓ Certified Wang et al., Med. Image Anal. 2022
3 PhysEndo + gradient 0.726 29.32 0.906 0.85 ✓ Certified Chen et al., Med. Image Anal. 2024
4 DiffEndo + gradient 0.681 26.69 0.85 0.87 ✓ Certified Gao et al., MICCAI 2024
5 BM3D-Endo + gradient 0.611 24.25 0.777 0.79 ✓ Certified Dabov et al., IEEE TIP 2007
6 DnCNN-Endo + gradient 0.608 24.17 0.775 0.78 ✓ Certified Zhang et al., IEEE TIP 2017
7 EndoSLAM-Net + gradient 0.586 23.15 0.737 0.8 ✓ Certified Ozyoruk et al., Med. Image Anal. 2021
8 CLAHE-Endo + gradient 0.566 22.35 0.705 0.8 ✓ Certified Zuiderveld, Graphics Gems IV 1994
9 Histogram-Eq + gradient 0.523 20.96 0.644 0.78 ✓ Certified Gonzalez & Woods, Digital Image Processing 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 Endoscopy