Dev
MALDI Mass Spectrometry Imaging — Dev Tier
(5 scenes)Blind evaluation tier — no ground truth available.
What you get
Measurements (y), ideal forward operator (H), and spec ranges only.
How to use
Apply your pipeline from the Public tier. Use consistency as self-check.
What to submit
Reconstructed signals and corrected spec. Scored server-side.
Parameter Specifications
🔒
True spec hidden — estimate parameters from spec ranges below.
| Parameter | Spec Range | Unit |
|---|---|---|
| laser_fluence_drift | 0.952 – 1.072 | - |
| mass_accuracy | -1.2 – 1.8 | ppm |
| extraction_delay | 95.2 – 107.2 | ns |
| matrix_crystallization | 0.928 – 1.108 | - |
Dev Tier Leaderboard
| # | Method | Score | PSNR | SSIM | Consistency | Trust | Source |
|---|---|---|---|---|---|---|---|
| 1 | CalibFormer + gradient | 0.733 | 29.98 | 0.917 | 0.83 | ✓ Certified | Transformer calibration, 2024 |
| 2 | MassSpecFormer + gradient | 0.610 | 24.1 | 0.772 | 0.8 | ✓ Certified | Mass spectrometry transformer, 2024 |
| 3 | Peak Fitting + gradient | 0.570 | 21.85 | 0.684 | 0.89 | ✓ Certified | Gaussian peak fitting |
| 4 | ResNet-Calib + gradient | 0.550 | 21.79 | 0.681 | 0.8 | ✓ Certified | ResNet for calibration, 2022 |
| 5 | PnP-NLM + gradient | 0.539 | 21.32 | 0.66 | 0.81 | ✓ Certified | Non-local means filter |
| 6 | PnP-BM3D + gradient | 0.530 | 20.55 | 0.625 | 0.87 | ✓ Certified | Danielyan et al., 2012 |
| 7 | Calibration-Lookup + gradient | 0.527 | 20.59 | 0.627 | 0.85 | ✓ Certified | Look-up table calibration |
| 8 | Deconv + gradient | 0.525 | 20.97 | 0.644 | 0.79 | ✓ Certified | Analytical baseline |
| 9 | DiffusionInstrumentation + gradient | 0.506 | 20.23 | 0.61 | 0.8 | ✓ Certified | Zhang et al., 2024 |
| 10 | ScoreInstrumentation + gradient | 0.491 | 19.51 | 0.575 | 0.83 | ✓ Certified | Wei et al., 2025 |
| 11 | Instrument-CNN + gradient | 0.489 | 19.52 | 0.575 | 0.82 | ✓ Certified | Instrument-specific CNN |
Visible Data Fields
y
H_ideal
spec_ranges
Dataset
Format: HDF5
Scenes: 5
Scoring Formula
0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)
PSNR: 40%
SSIM: 40%
Consistency: 20%