Dev

DESI Mass Spectrometry Imaging — Dev Tier

(5 scenes)

Blind evaluation tier — no ground truth available.

Measurements (y), ideal forward operator (H), and spec ranges only.

Apply your pipeline from the Public tier. Use consistency as self-check.

Reconstructed signals and corrected spec. Scored server-side.

🔒

True spec hidden — estimate parameters from spec ranges below.

Parameter	Spec Range	Unit
spray_angle_error	-1.2 – 1.8	deg
solvent_flow_variation	-3.6 – 5.4	-
ion_suppression_(matrix_effect)	-12.0 – 18.0	-
spatial_resolution_degradation	-12.0 – 18.0	-

#	Method	Score	PSNR	SSIM	Consistency	Trust	Source
1	MSIFormer + gradient	0.775	32.55	0.948	0.85	✓ Certified	Kalinichenko et al., Nat. Methods 2023
2	DiffusionMSI + gradient	0.756	31.11	0.932	0.86	✓ Certified	Palmer et al., Nat. Methods 2024
3	MSI-GAN + gradient	0.677	26.42	0.843	0.88	✓ Certified	Yang et al., Anal. Chem. 2021
4	DeepMSI + gradient	0.630	24.87	0.798	0.81	✓ Certified	Gruber et al., Anal. Chem. 2021
5	SpaMSI-Net + gradient	0.628	24.59	0.789	0.83	✓ Certified	Rappez et al., Nat. Methods 2021
6	MSI-NMF + gradient	0.607	23.58	0.753	0.85	✓ Certified	Blanco et al., Anal. Chem. 2013
7	MSI-TV + gradient	0.600	23.37	0.745	0.84	✓ Certified	Fonville et al., Bioinformatics 2012
8	MSI-PCA + gradient	0.585	22.93	0.728	0.82	✓ Certified	Alexandrov et al., J. Bioinform. Comput. Biol. 2010
9	MSI-Hotelling + gradient	0.516	20.22	0.609	0.85	✓ Certified	Deininger et al., Proteomics 2011

y H_ideal spec_ranges

Format: HDF5

Scenes: 5

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

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