Hidden

Correlative Light-Electron Microscopy (CLEM) — 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
registration_error_(lm_to_em) -70.0 – 230.0 nm
sample_deformation_(fixation) -0.7 – 2.3 shrinkage
fluorescence_preservation 67.8 – 109.8 -

Hidden Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 SwinCLEM + gradient 0.726 28.98 0.9 0.88 ✓ Certified Huang et al., IEEE TMI 2023
2 DiffusionCLEM + gradient 0.715 28.59 0.893 0.86 ✓ Certified Chen et al., Nat. Methods 2024
3 TransMorph + gradient 0.667 26.18 0.837 0.85 ✓ Certified Chen et al., Med. Image Anal. 2022
4 CLEM-Net + gradient 0.666 26.74 0.852 0.79 ✓ Certified Spiers et al., Nat. Methods 2021
5 VoxelMorph + gradient 0.615 24.07 0.771 0.83 ✓ Certified Balakrishnan et al., IEEE TPAMI 2019
6 PINN-CLEM + gradient 0.568 22.14 0.696 0.84 ✓ Certified Löffler et al., Nat. Methods 2023
7 Landmark-Reg + gradient 0.560 22.6 0.715 0.74 ✓ Certified Arganda-Carreras et al., Bioinformatics 2006
8 CNN-Reg + gradient 0.509 19.99 0.598 0.85 ✓ Certified de Vos et al., NeuroImage 2019
9 Cross-Correlation + gradient 0.441 18.43 0.521 0.74 ✓ Certified Thévenaz et al., IEEE TIP 1998

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 Correlative Light-Electron Microscopy (CLEM)