Dev

MR Elastography (MRE) — 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
shear_wave_frequency_error -2.4 – 3.6 -
wave_attenuation_model -0.15 – 0.15 -
motion_encoding_gradient_error -1.2 – 1.8 -
boundary_reflection -4.8 – 7.2 amplitude

Dev Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 SwinMR++ + gradient 0.855 38.56 0.984 0.88 ✓ 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
2 ReconFormer++ + gradient 0.842 38.24 0.983 0.83 ✓ Certified Pan et al., IEEE TMI 2025
3 PnP-DnCNN-Pro + gradient 0.827 37.5 0.98 0.8 ✓ 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
4 HUMUS-Net++ + gradient 0.821 35.46 0.97 0.89 ✓ Certified Fabian et al., dHUMUS-Net 2023 — k-space DC per module + dynamic multi-scale weighting + INR head + perceptual-structural loss + axial attention
5 HUMUS-Net + gradient 0.800 34.74 0.966 0.83 ✓ Certified Fabian et al., NeurIPS 2022
6 HybridCascade++ + gradient 0.797 35.13 0.969 0.79 ✓ 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
7 PromptMR-SFM + gradient 0.795 33.62 0.958 0.88 ✓ Certified PWM 2026
8 MRDynamo + gradient 0.791 32.98 0.952 0.9 ✓ Certified Chen et al., NeurIPS 2024
9 PromptMR + gradient 0.785 32.87 0.951 0.88 ✓ Certified Bai et al., ECCV 2024
10 MRI-FM + gradient 0.783 32.81 0.951 0.87 ✓ Certified Wang et al., Nature MI 2026
11 MR-IPT + gradient 0.781 33.45 0.956 0.82 ✓ Certified Sci. Reports 2025
12 MoDL-Net++ + gradient 0.779 32.99 0.952 0.84 ✓ 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
13 MRI-DiffusionNet + gradient 0.772 33.06 0.953 0.8 ✓ Certified Song et al., ICCV 2024
14 U-Net++ + gradient 0.769 31.55 0.938 0.89 ✓ 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
15 BrainID-MRI + gradient 0.768 32.48 0.948 0.82 ✓ Certified Liu et al., CVPR 2025
16 SwinMR + gradient 0.767 32.28 0.946 0.83 ✓ Certified Huang et al., MICCAI 2022
17 ReconFormer + gradient 0.766 31.63 0.939 0.87 ✓ Certified Guo et al., IEEE TMI 2024
18 PnP-DnCNN + gradient 0.757 31.29 0.935 0.85 ✓ Certified Ahmad et al., IEEE TCI 2019 (DOI:10.1109/TCI.2019.2944521)
19 MMR-Mamba + gradient 0.751 30.52 0.924 0.88 ✓ Certified Zhao et al., Med. Image Anal. 2025
20 BM3D-MRI + gradient 0.740 30.18 0.92 0.85 ✓ Certified Eksioglu, Comput. Math. Meth. Med. 2016
21 E2E-VarNet + gradient 0.722 29.83 0.914 0.79 ✓ Certified Sriram et al., MICCAI 2020
22 HybridCascade + gradient 0.695 27.08 0.86 0.9 ✓ Certified Fastmri, arXiv 2020
23 DCCNN + gradient 0.694 28.22 0.885 0.79 ✓ Certified Schlemper et al., IEEE TMI 2018
24 SENSE + gradient 0.693 26.99 0.858 0.9 ✓ Certified Pruessmann et al., MRM 1999
25 GRAPPA + gradient 0.683 26.81 0.853 0.87 ✓ Certified Griswold et al., MRM 2002
26 LORAKS + gradient 0.680 27.04 0.859 0.83 ✓ Certified Haldar, IEEE TMI 2014
27 k-t SPARSE-SENSE + gradient 0.680 26.82 0.854 0.85 ✓ Certified Lustig et al., MRM 2006
28 U-Net + gradient 0.659 26.19 0.837 0.81 ✓ Certified Zbontar et al., arXiv 2018
29 MoDL + gradient 0.658 26.26 0.839 0.8 ✓ Certified Aggarwal et al., IEEE TMI 2019
30 Deep-ADMM-Net + gradient 0.655 25.47 0.817 0.87 ✓ Certified Yang et al., NeurIPS 2016
31 ALOHA + gradient 0.645 25.38 0.814 0.83 ✓ Certified Jin et al., IEEE TMI 2016
32 L1-Wavelet + gradient 0.642 25.31 0.812 0.82 ✓ Certified Lustig et al., MRM 2007
33 Score-MRI + gradient 0.623 24.06 0.771 0.87 ✓ Certified Chung & Ye, Med. Image Anal. 2022
34 ESPIRiT + gradient 0.604 23.64 0.755 0.83 ✓ Certified Uecker et al., MRM 2014
35 Zero-Filled IFFT + gradient 0.559 21.44 0.666 0.89 ✓ Certified Pruessmann et al., MRM 1999

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 MR Elastography (MRE)