Hidden

MALDI Mass Spectrometry Imaging — Hidden Tier

(5 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
laser_fluence_drift 0.972 – 1.092 -
mass_accuracy -0.7 – 2.3 ppm
extraction_delay 97.2 – 109.2 ns
matrix_crystallization 0.958 – 1.138 -

Hidden Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 CalibFormer + gradient 0.672 26.51 0.846 0.84 ✓ Certified Transformer calibration, 2024
2 Peak Fitting + gradient 0.553 21.73 0.678 0.82 ✓ Certified Gaussian peak fitting
3 Deconv + gradient 0.531 21.01 0.646 0.81 ✓ Certified Analytical baseline
4 Calibration-Lookup + gradient 0.510 20.7 0.632 0.75 ✓ Certified Look-up table calibration
5 PnP-BM3D + gradient 0.492 19.75 0.587 0.8 ✓ Certified Danielyan et al., 2012
6 ResNet-Calib + gradient 0.485 19.16 0.558 0.85 ✓ Certified ResNet for calibration, 2022
7 MassSpecFormer + gradient 0.461 18.45 0.522 0.84 ✓ Certified Mass spectrometry transformer, 2024
8 PnP-NLM + gradient 0.438 17.6 0.48 0.85 ✓ Certified Non-local means filter
9 DiffusionInstrumentation + gradient 0.429 17.17 0.459 0.87 ✓ Certified Zhang et al., 2024
10 Instrument-CNN + gradient 0.392 16.05 0.404 0.85 ✓ Certified Instrument-specific CNN
11 ScoreInstrumentation + gradient 0.391 16.55 0.428 0.77 ✓ Certified Wei et al., 2025

Dataset

Scenes: 5

Scoring Formula

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

PSNR: 40% SSIM: 40% Consistency: 20%
Back to MALDI Mass Spectrometry Imaging