Dev

Susceptibility-Weighted Imaging (SWI) — Dev Tier

(3 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
phase_unwrapping_error -1.2 – 1.8 -
background_field_removal_error -2.4 – 3.6 -
dipole_inversion_regularization -0.15 – 0.15 -

Dev Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 HUMUS-Net++ + gradient 0.844 37.95 0.982 0.86 ✓ Certified Fabian et al., dHUMUS-Net 2023 — k-space DC per module + dynamic multi-scale weighting + INR head + perceptual-structural loss + axial attention
2 SwinMR++ + gradient 0.842 37.55 0.98 0.87 ✓ Certified Huang et al., IEEE TMI 2025 — multi-scale axial attention + INR head + k-space DC per module + LPIPS+SSIM+k-space joint loss + dynamic feature fusion
3 ReconFormer++ + gradient 0.840 37.39 0.98 0.87 ✓ Certified Pan et al., IEEE TMI 2025
4 PnP-DnCNN-Pro + gradient 0.815 36.13 0.974 0.82 ✓ Certified PnP-DnCNN-Pro IEEE TMI 2025 (DOI:10.1109/TMI.2025.3441240) — multi-scale DnCNN denoiser + adaptive mu/sigma schedule + SIREN INR output head + joint LPIPS+SSIM denoiser training + dynamic PnP regularization scheduling
5 PromptMR-SFM + gradient 0.812 35.53 0.971 0.84 ✓ Certified PWM 2026
6 SwinMR + gradient 0.805 35.35 0.97 0.82 ✓ Certified Huang et al., MICCAI 2022
7 ReconFormer + gradient 0.799 35.01 0.968 0.81 ✓ Certified Guo et al., IEEE TMI 2024
8 MRI-FM + gradient 0.797 34.36 0.963 0.84 ✓ Certified Wang et al., Nature MI 2026
9 MRI-DiffusionNet + gradient 0.797 34.52 0.965 0.83 ✓ Certified Song et al., ICCV 2024
10 HUMUS-Net + gradient 0.797 33.71 0.959 0.88 ✓ Certified Fabian et al., NeurIPS 2022
11 MoDL-Net++ + gradient 0.794 34.25 0.963 0.83 ✓ Certified MoDL-Net++ IEEE TMI 2025 — multi-scale pyramid fusion + RDN/Swin deep prior + differentiable DC layers + LPIPS+SSIM+L1 joint loss + two-stage training strategy
12 MRDynamo + gradient 0.789 33.6 0.958 0.85 ✓ Certified Chen et al., NeurIPS 2024
13 U-Net++ + gradient 0.788 34.27 0.963 0.8 ✓ Certified Chen & Boning, IEEE TMI 2024 (DOI: 10.1109/TMI.2024.3367890) — Residual U-Net + data consistency layers + plug-and-play prior + residual connections + dense skip paths
14 HybridCascade++ + gradient 0.783 33.91 0.96 0.8 ✓ Certified HybridCascade++ MICCAI 2021 + IEEE TMI 2025 — multi-scale cascade DC + SIREN INR warm-start + SSIM structural anchor + DRUNet polish + freq-blend LF/HF fusion
15 BrainID-MRI + gradient 0.782 33.05 0.953 0.85 ✓ Certified Liu et al., CVPR 2025
16 MR-IPT + gradient 0.777 33.6 0.958 0.79 ✓ Certified Sci. Reports 2025
17 E2E-VarNet + gradient 0.768 32.61 0.949 0.81 ✓ Certified Sriram et al., MICCAI 2020
18 PnP-DnCNN + gradient 0.754 31.38 0.936 0.83 ✓ Certified Ahmad et al., IEEE TCI 2019 (DOI:10.1109/TCI.2019.2944521)
19 MMR-Mamba + gradient 0.749 31.29 0.935 0.81 ✓ Certified Zhao et al., Med. Image Anal. 2025
20 BM3D-MRI + gradient 0.740 30.32 0.922 0.84 ✓ Certified Eksioglu, Comput. Math. Meth. Med. 2016
21 PromptMR + gradient 0.728 30.07 0.918 0.8 ✓ Certified Bai et al., ECCV 2024
22 MoDL + gradient 0.723 29.06 0.901 0.86 ✓ Certified Aggarwal et al., IEEE TMI 2019
23 DCCNN + gradient 0.716 28.55 0.892 0.87 ✓ Certified Schlemper et al., IEEE TMI 2018
24 HybridCascade + gradient 0.708 28.63 0.893 0.82 ✓ Certified Fastmri, arXiv 2020
25 GRAPPA + gradient 0.704 28.56 0.892 0.81 ✓ Certified Griswold et al., MRM 2002
26 ALOHA + gradient 0.700 27.85 0.878 0.85 ✓ Certified Jin et al., IEEE TMI 2016
27 Deep-ADMM-Net + gradient 0.697 27.7 0.874 0.85 ✓ Certified Yang et al., NeurIPS 2016
28 U-Net + gradient 0.677 26.69 0.85 0.85 ✓ Certified Zbontar et al., arXiv 2018
29 SENSE + gradient 0.668 26.45 0.844 0.83 ✓ Certified Pruessmann et al., MRM 1999
30 L1-Wavelet + gradient 0.659 25.83 0.827 0.85 ✓ Certified Lustig et al., MRM 2007
31 LORAKS + gradient 0.658 26.36 0.842 0.79 ✓ Certified Haldar, IEEE TMI 2014
32 k-t SPARSE-SENSE + gradient 0.654 25.39 0.814 0.87 ✓ Certified Lustig et al., MRM 2006
33 Score-MRI + gradient 0.615 24.14 0.773 0.82 ✓ Certified Chung & Ye, Med. Image Anal. 2022
34 Zero-Filled IFFT + gradient 0.608 23.63 0.755 0.85 ✓ Certified Pruessmann et al., MRM 1999
35 ESPIRiT + gradient 0.604 24.0 0.769 0.78 ✓ Certified Uecker et al., MRM 2014

Visible Data Fields

y H_ideal spec_ranges

Dataset

Format: HDF5
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 Susceptibility-Weighted Imaging (SWI)