Hidden

CEST MRI — 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
b0_inhomogeneity -7.0 – 23.0 Hz
b1_inhomogeneity -2.8 – 9.2 -
saturation_power_error -1.4 – 4.6 -
mt_contamination -4.2 – 13.8 -

Hidden Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 PromptCEST + gradient 0.713 28.35 0.888 0.87 ✓ Certified Liu et al., MRM 2024
2 CESTFormer + gradient 0.702 27.86 0.878 0.86 ✓ Certified Wu et al., IEEE TMI 2023
3 PINN-CEST + gradient 0.700 27.64 0.873 0.87 ✓ Certified Cohen et al., MRM 2022
4 DiffusionCEST + gradient 0.683 27.72 0.875 0.78 ✓ Certified Chen et al., NeurIPS 2024
5 WASSR + gradient 0.657 26.12 0.835 0.81 ✓ Certified Kim et al., MRM 2009
6 Lorentzian-Fit + gradient 0.627 24.75 0.794 0.81 ✓ Certified Zaiss & Bachert, NMR Biomed. 2013
7 U-Net-CEST + gradient 0.620 24.54 0.787 0.8 ✓ Certified Zhao et al., MRM 2021
8 MTR-asym + gradient 0.543 21.04 0.647 0.87 ✓ Certified Zhou et al., Nat. Med. 2003
9 DnCNN-CEST + gradient 0.497 19.77 0.588 0.82 ✓ Certified Zhang et al., IEEE TIP 2017 (CEST adapted)

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 CEST MRI