Dev

MR Angiography (MRA) — 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
contrast_timing_error -0.72 – 1.08 s
background_suppression -4.8 – 7.2 -
velocity_encoding_error -3.6 – 5.4 -

Dev Tier Leaderboard

# Method Score PSNR SSIM Consistency Trust Source
1 HUMUS-Net++ + gradient 0.853 38.51 0.984 0.87 ✓ Certified Fabian et al., dHUMUS-Net 2023 — k-space DC per module + dynamic multi-scale weighting + INR head + perceptual-structural loss + axial attention
2 ReconFormer++ + gradient 0.839 37.63 0.981 0.85 ✓ Certified Pan et al., IEEE TMI 2025
3 SwinMR++ + gradient 0.826 37.22 0.979 0.81 ✓ 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
4 ReconFormer + gradient 0.818 35.89 0.973 0.85 ✓ Certified Guo et al., IEEE TMI 2024
5 MRI-FM + gradient 0.814 35.1 0.968 0.88 ✓ Certified Wang et al., Nature MI 2026
6 HUMUS-Net + gradient 0.810 34.71 0.966 0.88 ✓ Certified Fabian et al., NeurIPS 2022
7 PnP-DnCNN-Pro + gradient 0.796 34.91 0.967 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
8 MR-IPT + gradient 0.795 34.51 0.964 0.82 ✓ Certified Sci. Reports 2025
9 MoDL-Net++ + gradient 0.788 34.4 0.964 0.79 ✓ 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 SwinMR + gradient 0.779 32.88 0.951 0.85 ✓ Certified Huang et al., MICCAI 2022
11 MMR-Mamba + gradient 0.777 33.12 0.954 0.82 ✓ Certified Zhao et al., Med. Image Anal. 2025
12 HybridCascade++ + gradient 0.772 32.6 0.949 0.83 ✓ 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
13 BrainID-MRI + gradient 0.772 32.94 0.952 0.81 ✓ Certified Liu et al., CVPR 2025
14 U-Net++ + gradient 0.769 33.03 0.953 0.79 ✓ 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 MRI-DiffusionNet + gradient 0.769 32.37 0.947 0.83 ✓ Certified Song et al., ICCV 2024
16 PromptMR + gradient 0.767 31.56 0.938 0.88 ✓ Certified Bai et al., ECCV 2024
17 E2E-VarNet + gradient 0.765 32.25 0.945 0.82 ✓ Certified Sriram et al., MICCAI 2020
18 PromptMR-SFM + gradient 0.759 30.93 0.93 0.89 ✓ Certified PWM 2026
19 MRDynamo + gradient 0.754 30.71 0.927 0.88 ✓ Certified Chen et al., NeurIPS 2024
20 U-Net + gradient 0.750 30.87 0.929 0.85 ✓ Certified Zbontar et al., arXiv 2018
21 PnP-DnCNN + gradient 0.742 30.99 0.931 0.8 ✓ Certified Ahmad et al., IEEE TCI 2019 (DOI:10.1109/TCI.2019.2944521)
22 HybridCascade + gradient 0.728 28.97 0.9 0.89 ✓ Certified Fastmri, arXiv 2020
23 MoDL + gradient 0.724 29.1 0.902 0.86 ✓ Certified Aggarwal et al., IEEE TMI 2019
24 BM3D-MRI + gradient 0.708 28.64 0.894 0.82 ✓ Certified Eksioglu, Comput. Math. Meth. Med. 2016
25 GRAPPA + gradient 0.691 27.07 0.86 0.88 ✓ Certified Griswold et al., MRM 2002
26 DCCNN + gradient 0.690 26.82 0.854 0.9 ✓ Certified Schlemper et al., IEEE TMI 2018
27 SENSE + gradient 0.685 27.19 0.863 0.84 ✓ Certified Pruessmann et al., MRM 1999
28 Deep-ADMM-Net + gradient 0.678 27.02 0.859 0.82 ✓ Certified Yang et al., NeurIPS 2016
29 k-t SPARSE-SENSE + gradient 0.647 25.1 0.805 0.87 ✓ Certified Lustig et al., MRM 2006
30 LORAKS + gradient 0.639 24.56 0.788 0.89 ✓ Certified Haldar, IEEE TMI 2014
31 ALOHA + gradient 0.637 25.01 0.803 0.83 ✓ Certified Jin et al., IEEE TMI 2016
32 L1-Wavelet + gradient 0.622 24.67 0.792 0.79 ✓ Certified Lustig et al., MRM 2007
33 ESPIRiT + gradient 0.617 24.4 0.782 0.8 ✓ Certified Uecker et al., MRM 2014
34 Zero-Filled IFFT + gradient 0.589 23.1 0.735 0.82 ✓ Certified Pruessmann et al., MRM 1999
35 Score-MRI + gradient 0.580 23.06 0.733 0.78 ✓ Certified Chung & Ye, Med. Image Anal. 2022

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 Angiography (MRA)