Hidden

Confocal Laser Endomicroscopy (CLE) — Hidden Tier

(3 scenes)

Fully blind server-side evaluation — no data download.

No data downloadable. Algorithm runs server-side on hidden measurements.

Package algorithm as Docker container / Python script. Submit via link.

Containerized algorithm accepting y + H, outputting x_hat + corrected spec.

🔒

True spec hidden — blind evaluation, only ranges available.

Parameter	Spec Range	Unit
fiber_bundle_honeycomb_pattern	-0.15 – 0.15	-
motion_artifact	-1.4 – 4.6	px/frame
fluorescein_concentration_variation	0.72 – 1.92	relative

#	Method	Score	PSNR	SSIM	Consistency	Trust	Source
1	DiffusionEndo + gradient	0.746	31.65	0.939	0.77	✓ Certified	Li et al., Med. Image Anal. 2024
2	Restormer-CLE + gradient	0.734	31.22	0.934	0.74	✓ Certified	Zamir et al., CVPR 2022 (CLE)
3	CARE-CLE + gradient	0.648	25.23	0.809	0.86	✓ Certified	Weigert et al., Nat. Methods 2018 (CLE)
4	SwinIR-CLE + gradient	0.642	25.85	0.828	0.76	✓ Certified	Liang et al., ICCV 2021 (CLE)
5	BM3D-CLE + gradient	0.617	24.85	0.797	0.75	✓ Certified	Dabov et al., IEEE TIP 2007
6	PINN-CLE + gradient	0.585	22.73	0.72	0.85	✓ Certified	Kang et al., Med. Phys. 2022
7	DnCNN-CLE + gradient	0.581	22.73	0.72	0.83	✓ Certified	Zhang et al., IEEE TIP 2017
8	NLM-Speckle + gradient	0.573	22.62	0.716	0.8	✓ Certified	Buades et al., CVPR 2005
9	U-Net-CLE + gradient	0.553	22.2	0.698	0.76	✓ Certified	Andre et al., Med. Image Anal. 2011 (updated DL)

Scenes: 3

0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)

PSNR: 40% SSIM: 40% Consistency: 20%