Public

MR Elastography (MRE) — Public Tier

(3 scenes)

Full-access development tier with all data visible.

What you get

Measurements (y), ideal forward operator (H), spec ranges, ground truth (x_true), and true mismatch spec.

How to use

Load HDF5 → compare reconstruction vs x_true → check consistency → iterate.

What to submit

Reconstructed signals (x_hat) and corrected spec as HDF5.

Parameter Specifications

✓

True spec visible — use these exact values for Scenario III oracle reconstruction.

Parameter Spec Range True Value Unit
shear_wave_frequency_error -2.0 – 4.0 1.0 -
wave_attenuation_model -0.15 – 0.15 0.0 -
motion_encoding_gradient_error -1.0 – 2.0 0.5 -
boundary_reflection -4.0 – 8.0 2.0 amplitude

InverseNet Baseline Scores

Method: CPU_baseline — Mismatch parameter: nominal

Scenario I (Ideal)

17.61 dB

SSIM 0.3262

Scenario II (Mismatch)

13.39 dB

SSIM 0.0553

Scenario III (Oracle)

16.66 dB

SSIM 0.1359

Per-scene breakdown (4 scenes)
Scene PSNR I SSIM I PSNR II SSIM II PSNR III SSIM III
scene_00 16.58 0.3251 12.85 0.0515 16.16 0.1317
scene_01 18.88 0.3252 14.12 0.0562 17.37 0.1299
scene_02 18.30 0.3298 13.74 0.0603 16.95 0.1425
scene_03 16.68 0.3248 12.85 0.0534 16.15 0.1394

Public Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 SwinMR++ + gradient 0.888 41.76 0.991 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
2 PromptMR-SFM + gradient 0.881 39.81 0.987 0.94 ✓ Certified PWM 2026
3 HUMUS-Net++ + gradient 0.880 40.27 0.989 0.91 ✓ Certified Fabian et al., dHUMUS-Net 2023 — k-space DC per module + dynamic multi-scale weighting + INR head + perceptual-structural loss + axial attention
4 MMR-Mamba + gradient 0.877 39.79 0.987 0.92 ✓ Certified Zhao et al., Med. Image Anal. 2025
5 HybridCascade++ + gradient 0.874 40.42 0.989 0.87 ✓ 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
6 MR-IPT + gradient 0.874 40.09 0.988 0.89 ✓ Certified Sci. Reports 2025
7 MRI-FM + gradient 0.870 39.33 0.986 0.91 ✓ Certified Wang et al., Nature MI 2026
8 MRI-DiffusionNet + gradient 0.868 39.01 0.985 0.92 ✓ Certified Song et al., ICCV 2024
9 MoDL-Net++ + gradient 0.864 38.84 0.985 0.91 ✓ 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
10 ReconFormer++ + gradient 0.863 39.3 0.986 0.88 ✓ Certified Pan et al., IEEE TMI 2025
11 U-Net++ + gradient 0.863 38.5 0.984 0.92 ✓ 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
12 E2E-VarNet + gradient 0.860 37.73 0.981 0.95 ✓ Certified Sriram et al., MICCAI 2020
13 PnP-DnCNN-Pro + gradient 0.857 38.37 0.983 0.9 ✓ 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
14 BrainID-MRI + gradient 0.857 38.94 0.985 0.87 ✓ Certified Liu et al., CVPR 2025
15 MRDynamo + gradient 0.852 37.95 0.982 0.9 ✓ Certified Chen et al., NeurIPS 2024
16 SwinMR + gradient 0.850 37.26 0.979 0.93 ✓ Certified Huang et al., MICCAI 2022
17 PromptMR + gradient 0.842 36.9 0.978 0.91 ✓ Certified Bai et al., ECCV 2024
18 ReconFormer + gradient 0.835 36.62 0.976 0.89 ✓ Certified Guo et al., IEEE TMI 2024
19 HUMUS-Net + gradient 0.834 36.9 0.978 0.87 ✓ Certified Fabian et al., NeurIPS 2022
20 HybridCascade + gradient 0.821 35.79 0.972 0.87 ✓ Certified Fastmri, arXiv 2020
21 DCCNN + gradient 0.812 34.15 0.962 0.93 ✓ Certified Schlemper et al., IEEE TMI 2018
22 Deep-ADMM-Net + gradient 0.810 34.15 0.962 0.92 ✓ Certified Yang et al., NeurIPS 2016
23 MoDL + gradient 0.804 34.12 0.962 0.89 ✓ Certified Aggarwal et al., IEEE TMI 2019
24 U-Net + gradient 0.792 32.95 0.952 0.91 ✓ Certified Zbontar et al., arXiv 2018
25 LORAKS + gradient 0.788 32.05 0.943 0.95 ✓ Certified Haldar, IEEE TMI 2014
26 PnP-DnCNN + gradient 0.782 32.34 0.946 0.9 ✓ Certified Ahmad et al., IEEE TCI 2019 (DOI:10.1109/TCI.2019.2944521)
27 ALOHA + gradient 0.778 32.36 0.946 0.88 ✓ Certified Jin et al., IEEE TMI 2016
28 BM3D-MRI + gradient 0.775 32.3 0.946 0.87 ✓ Certified Eksioglu, Comput. Math. Meth. Med. 2016
29 ESPIRiT + gradient 0.760 30.84 0.929 0.9 ✓ Certified Uecker et al., MRM 2014
30 k-t SPARSE-SENSE + gradient 0.746 30.1 0.918 0.89 ✓ Certified Lustig et al., MRM 2006
31 L1-Wavelet + gradient 0.734 29.12 0.902 0.91 ✓ Certified Lustig et al., MRM 2007
32 Score-MRI + gradient 0.733 29.51 0.909 0.87 ✓ Certified Chung & Ye, Med. Image Anal. 2022
33 GRAPPA + gradient 0.728 29.36 0.907 0.86 ✓ Certified Griswold et al., MRM 2002
34 SENSE + gradient 0.723 28.37 0.888 0.92 ✓ Certified Pruessmann et al., MRM 1999
35 Zero-Filled IFFT + gradient 0.614 23.45 0.748 0.9 ✓ Certified Pruessmann et al., MRM 1999

Visible Data Fields

y H_ideal spec_ranges x_true true_spec

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)