MR Elastography (MRE)

Join the Competition Contribute to Benchmark

Standard reconstruction benchmark — forward model perfectly known, no calibration needed. Score = 0.5 × clip((PSNR−15)/30, 0, 1) + 0.5 × SSIM

#	Method	Score	PSNR (dB)	SSIM	Source
🥇	SwinMR++ SwinMR++ Huang et al., IEEE TMI 2025 — 5 improvements: multi-scale axial attention (cross-scale long-range modeling), INR coordinate-query head (high-acceleration k-space interpolation), k-space DC per unrolled module, joint LPIPS+SSIM+k-space consistency loss, dynamic conv-Transformer branch weighting 43.8 dB SSIM 0.983 Checkpoint unavailable	0.971	43.8	0.983	✓ Certified	Huang et al., IEEE TMI 2025 — 5 improvements: multi-scale axial attention (cross-scale long-range modeling), INR coordinate-query head (high-acceleration k-space interpolation), k-space DC per unrolled module, joint LPIPS+SSIM+k-space consistency loss, dynamic conv-Transformer branch weighting
🥈	HUMUS-Net++ HUMUS-Net++ Fabian et al., dHUMUS-Net 2023 — 5 improvements: k-space DC per unrolled module, dynamic optimal-scale prediction (dHUMUS-Net), INR coordinate head (continuous representation), LPIPS+SSIM perceptual-structural loss, lightweight axial attention Transformer 43.1 dB SSIM 0.979 Checkpoint unavailable	0.958	43.1	0.979	✓ Certified	Fabian et al., dHUMUS-Net 2023 — 5 improvements: k-space DC per unrolled module, dynamic optimal-scale prediction (dHUMUS-Net), INR coordinate head (continuous representation), LPIPS+SSIM perceptual-structural loss, lightweight axial attention Transformer
🥉	MR-IPT MR-IPT Sci. Reports 2025 42.48 dB SSIM 0.983 Checkpoint unavailable	0.950	42.48	0.983	✓ Certified	Sci. Reports 2025
4	HybridCascade++ HybridCascade++ HybridCascade++ MICCAI 2021 + IEEE TMI 2025 — 5 improvements: multi-stage cascade DC (coarse-to-fine 4-stage unrolling), SIREN INR warm-start (continuous prior initialization), SSIM structural anchor (perceptual consistency in late DC stages), DRUNet final polish (blind denoising post-DC), freq-blend LF/HF fusion (SIREN low-freq + structured high-freq recombination) 42.5 dB SSIM 0.981 Checkpoint unavailable	0.949	42.5	0.981	✓ Certified	HybridCascade++ MICCAI 2021 + IEEE TMI 2025 — 5 improvements: multi-stage cascade DC (coarse-to-fine 4-stage unrolling), SIREN INR warm-start (continuous prior initialization), SSIM structural anchor (perceptual consistency in late DC stages), DRUNet final polish (blind denoising post-DC), freq-blend LF/HF fusion (SIREN low-freq + structured high-freq recombination)
5	MoDL-Net++ MoDL-Net++ MoDL-Net++ IEEE TMI 2025 — 5 improvements: multi-scale pyramid fusion (coarse-to-fine representation), RDN/Swin deep prior (rich feature hierarchy), differentiable DC layers (physics-informed unrolling), joint LPIPS+SSIM+L1 loss (perceptual+structural+fidelity), two-stage training (pre-train then fine-tune with DC) 41.8 dB SSIM 0.978 Checkpoint unavailable	0.936	41.8	0.978	✓ Certified	MoDL-Net++ IEEE TMI 2025 — 5 improvements: multi-scale pyramid fusion (coarse-to-fine representation), RDN/Swin deep prior (rich feature hierarchy), differentiable DC layers (physics-informed unrolling), joint LPIPS+SSIM+L1 loss (perceptual+structural+fidelity), two-stage training (pre-train then fine-tune with DC)
6	U-Net++ U-Net++ Chen & Boning, IEEE TMI 2024 — 5 improvements: Residual U-Net blocks (dense skip connections), data consistency layers (physics-informed k-space projection), plug-and-play prior (learned denoiser as proximal operator), joint SSIM+MSE+DC loss, multi-scale feature aggregation 41.5 dB SSIM 0.978 Checkpoint unavailable	0.931	41.5	0.978	✓ Certified	Chen & Boning, IEEE TMI 2024 — 5 improvements: Residual U-Net blocks (dense skip connections), data consistency layers (physics-informed k-space projection), plug-and-play prior (learned denoiser as proximal operator), joint SSIM+MSE+DC loss, multi-scale feature aggregation
7	MRI-FM MRI-FM Wang et al., Nature MI 2026 42.1 dB SSIM 0.948 Checkpoint unavailable	0.926	42.1	0.948	✓ Certified	Wang et al., Nature MI 2026
8	ReconFormer++ ReconFormer++ Pan et al., IEEE TMI 2025 41.5 dB SSIM 0.969 Checkpoint unavailable	0.926	41.5	0.969	✓ Certified	Pan et al., IEEE TMI 2025
9	PromptMR-SFM PromptMR-SFM PWM 2026 41.3 dB SSIM 0.971 Checkpoint unavailable	0.924	41.3	0.971	✓ Certified	PWM 2026
10	PnP-DnCNN-Pro PnP-DnCNN-Pro PnP-DnCNN-Pro IEEE TMI 2025 (DOI:10.1109/TMI.2025.3441240) — 5 improvements: multi-scale DnCNN denoiser (SwinIR-style hierarchical feature extraction), adaptive mu/sigma schedule (dynamic regularization per PnP iteration), SIREN INR coordinate output head (continuous representation for high-acceleration interpolation), joint LPIPS+SSIM denoiser training (perceptual+structural loss), dynamic PnP regularization scheduling (learnable lambda per iteration) 41.0 dB SSIM 0.968 Try in SpecLab →	0.917	41.0	0.968	✓ Certified	PnP-DnCNN-Pro IEEE TMI 2025 (DOI:10.1109/TMI.2025.3441240) — 5 improvements: multi-scale DnCNN denoiser (SwinIR-style hierarchical feature extraction), adaptive mu/sigma schedule (dynamic regularization per PnP iteration), SIREN INR coordinate output head (continuous representation for high-acceleration interpolation), joint LPIPS+SSIM denoiser training (perceptual+structural loss), dynamic PnP regularization scheduling (learnable lambda per iteration)
11	MMR-Mamba MMR-Mamba Zhao et al., Med. Image Anal. 2025 40.98 dB SSIM 0.969 Checkpoint unavailable	0.917	40.98	0.969	✓ Certified	Zhao et al., Med. Image Anal. 2025
12	BrainID-MRI BrainID-MRI Liu et al., CVPR 2025 41.0 dB SSIM 0.942 Checkpoint unavailable	0.904	41.0	0.942	✓ Certified	Liu et al., CVPR 2025
13	MRDynamo MRDynamo Chen et al., NeurIPS 2024 40.5 dB SSIM 0.938 Checkpoint unavailable	0.894	40.5	0.938	✓ Certified	Chen et al., NeurIPS 2024
14	MRI-DiffusionNet MRI-DiffusionNet Song et al., ICCV 2024 40.1 dB SSIM 0.932 Checkpoint unavailable	0.884	40.1	0.932	✓ Certified	Song et al., ICCV 2024
15	PromptMR PromptMR Bai et al., ECCV 2024 39.7 dB SSIM 0.926 Checkpoint unavailable	0.875	39.7	0.926	✓ Certified	Bai et al., ECCV 2024
16	E2E-VarNet E2E-VarNet Sriram et al., MICCAI 2020 39.4 dB SSIM 0.924 Checkpoint unavailable	0.869	39.4	0.924	✓ Certified	Sriram et al., MICCAI 2020
17	ReconFormer ReconFormer Guo et al., IEEE TMI 2024 39.0 dB SSIM 0.922 Checkpoint unavailable	0.861	39.0	0.922	✓ Certified	Guo et al., IEEE TMI 2024
18	HUMUS-Net HUMUS-Net Fabian et al., NeurIPS 2022 38.9 dB SSIM 0.923 Checkpoint unavailable	0.860	38.9	0.923	✓ Certified	Fabian et al., NeurIPS 2022
19	SwinMR SwinMR Huang et al., MICCAI 2022 38.5 dB SSIM 0.921 Checkpoint unavailable	0.852	38.5	0.921	✓ Certified	Huang et al., MICCAI 2022
20	HybridCascade HybridCascade Fastmri, arXiv 2020 37.8 dB SSIM 0.917 Checkpoint unavailable	0.839	37.8	0.917	✓ Certified	Fastmri, arXiv 2020
21	MoDL MoDL Aggarwal et al., IEEE TMI 2019 36.5 dB SSIM 0.912 Checkpoint unavailable	0.814	36.5	0.912	✓ Certified	Aggarwal et al., IEEE TMI 2019
22	U-Net U-Net Zbontar et al., arXiv 2018 35.9 dB SSIM 0.904 Checkpoint unavailable	0.800	35.9	0.904	✓ Certified	Zbontar et al., arXiv 2018
23	DCCNN DCCNN Schlemper et al., IEEE TMI 2018 35.5 dB SSIM 0.908 Checkpoint unavailable	0.796	35.5	0.908	✓ Certified	Schlemper et al., IEEE TMI 2018
24	Deep-ADMM-Net Deep-ADMM-Net Yang et al., NeurIPS 2016 35.3 dB SSIM 0.907 Checkpoint unavailable	0.792	35.3	0.907	✓ Certified	Yang et al., NeurIPS 2016
25	PnP-DnCNN PnP-DnCNN Ahmad et al., IEEE TCI 2019 (DOI:10.1109/TCI.2019.2944521) 35.0 dB SSIM 0.905 Try in SpecLab →	0.786	35.0	0.905	✓ Certified	Ahmad et al., IEEE TCI 2019 (DOI:10.1109/TCI.2019.2944521)
26	ALOHA ALOHA Jin et al., IEEE TMI 2016 34.5 dB SSIM 0.900 Try in SpecLab →	0.775	34.5	0.900	✓ Certified	Jin et al., IEEE TMI 2016
27	BM3D-MRI BM3D-MRI Eksioglu, Comput. Math. Meth. Med. 2016 34.2 dB SSIM 0.897 Try in SpecLab →	0.769	34.2	0.897	✓ Certified	Eksioglu, Comput. Math. Meth. Med. 2016
28	LORAKS LORAKS Haldar, IEEE TMI 2014 33.8 dB SSIM 0.893 Try in SpecLab →	0.760	33.8	0.893	✓ Certified	Haldar, IEEE TMI 2014
29	ESPIRiT ESPIRiT Uecker et al., MRM 2014 33.4 dB SSIM 0.890 Try in SpecLab →	0.752	33.4	0.890	✓ Certified	Uecker et al., MRM 2014
30	k-t SPARSE-SENSE k-t SPARSE-SENSE Lustig et al., MRM 2006 32.5 dB SSIM 0.875 Try in SpecLab →	0.729	32.5	0.875	✓ Certified	Lustig et al., MRM 2006
31	L1-Wavelet L1-Wavelet Lustig et al., MRM 2007 32.1 dB SSIM 0.870 Try in SpecLab →	0.720	32.1	0.870	✓ Certified	Lustig et al., MRM 2007
32	Score-MRI Score-MRI Chung & Ye, Med. Image Anal. 2022 31.4 dB SSIM 0.890 Checkpoint unavailable	0.718	31.4	0.890	✓ Certified	Chung & Ye, Med. Image Anal. 2022
33	GRAPPA GRAPPA Griswold et al., MRM 2002 31.2 dB SSIM 0.860 Try in SpecLab →	0.700	31.2	0.860	✓ Certified	Griswold et al., MRM 2002
34	SENSE SENSE Pruessmann et al., MRM 1999 29.5 dB SSIM 0.830 Try in SpecLab →	0.657	29.5	0.830	✓ Certified	Pruessmann et al., MRM 1999
35	Zero-Filled IFFT Zero-Filled IFFT Pruessmann et al., MRM 1999 26.0 dB SSIM 0.620 Try in SpecLab →	0.493	26.0	0.620	✓ Certified	Pruessmann et al., MRM 1999

Dataset: PWM Benchmark (35 algorithms)

Blind Reconstruction Challenge — forward model has unknown mismatch, must calibrate from data. Score = 0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖)

#	Method	Overall Score	Public PSNR / SSIM	Dev PSNR / SSIM	Hidden PSNR / SSIM	Trust	Source
🥇	SwinMR++ + gradient SwinMR++ + gradient 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 Score 0.858 Correct & Reconstruct →	0.858	0.888 41.76 dB / 0.991	0.855 38.56 dB / 0.984	0.832 37.75 dB / 0.981	✓ 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
🥈	ReconFormer++ + gradient ReconFormer++ + gradient Pan et al., IEEE TMI 2025 Score 0.836 Correct & Reconstruct →	0.836	0.863 39.3 dB / 0.986	0.842 38.24 dB / 0.983	0.803 36.01 dB / 0.973	✓ Certified	Pan et al., IEEE TMI 2025
🥉	PnP-DnCNN-Pro + gradient PnP-DnCNN-Pro + gradient 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 Score 0.835 Correct & Reconstruct →	0.835	0.857 38.37 dB / 0.983	0.827 37.5 dB / 0.980	0.820 35.88 dB / 0.973	✓ 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 HUMUS-Net++ + gradient Fabian et al., dHUMUS-Net 2023 — k-space DC per module + dynamic multi-scale weighting + INR head + perceptual-structural loss + axial attention Score 0.821 Correct & Reconstruct →	0.821	0.880 40.27 dB / 0.989	0.821 35.46 dB / 0.970	0.762 31.5 dB / 0.937	✓ Certified	Fabian et al., dHUMUS-Net 2023 — k-space DC per module + dynamic multi-scale weighting + INR head + perceptual-structural loss + axial attention
5	HybridCascade++ + gradient HybridCascade++ + gradient HybridCascade++ MICCAI 2021 + IEEE TMI 2025 — multi-scale cascade DC + SIREN INR warm-start + SSIM structural anchor + DRUNet polish + freq-blend LF/HF fusion Score 0.819 Correct & Reconstruct →	0.819	0.874 40.42 dB / 0.989	0.797 35.13 dB / 0.969	0.787 34.19 dB / 0.962	✓ 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	PromptMR-SFM + gradient PromptMR-SFM + gradient PWM 2026 Score 0.815 Correct & Reconstruct →	0.815	0.881 39.81 dB / 0.987	0.795 33.62 dB / 0.958	0.768 31.94 dB / 0.942	✓ Certified	PWM 2026
7	MR-IPT + gradient MR-IPT + gradient Sci. Reports 2025 Score 0.803 Correct & Reconstruct →	0.803	0.874 40.09 dB / 0.988	0.781 33.45 dB / 0.956	0.754 31.64 dB / 0.939	✓ Certified	Sci. Reports 2025
8	MRI-FM + gradient MRI-FM + gradient Wang et al., Nature MI 2026 Score 0.802 Correct & Reconstruct →	0.802	0.870 39.33 dB / 0.986	0.783 32.81 dB / 0.951	0.752 31.75 dB / 0.940	✓ Certified	Wang et al., Nature MI 2026
9	PromptMR + gradient PromptMR + gradient Bai et al., ECCV 2024 Score 0.798 Correct & Reconstruct →	0.798	0.842 36.9 dB / 0.978	0.785 32.87 dB / 0.951	0.768 32.75 dB / 0.950	✓ Certified	Bai et al., ECCV 2024
10	HUMUS-Net + gradient HUMUS-Net + gradient Fabian et al., NeurIPS 2022 Score 0.795 Correct & Reconstruct →	0.795	0.834 36.9 dB / 0.978	0.800 34.74 dB / 0.966	0.752 31.91 dB / 0.942	✓ Certified	Fabian et al., NeurIPS 2022
11	MRI-DiffusionNet + gradient MRI-DiffusionNet + gradient Song et al., ICCV 2024 Score 0.795 Correct & Reconstruct →	0.795	0.868 39.01 dB / 0.985	0.772 33.06 dB / 0.953	0.744 31.11 dB / 0.932	✓ Certified	Song et al., ICCV 2024
12	MRDynamo + gradient MRDynamo + gradient Chen et al., NeurIPS 2024 Score 0.795 Correct & Reconstruct →	0.795	0.852 37.95 dB / 0.982	0.791 32.98 dB / 0.952	0.743 31.41 dB / 0.936	✓ Certified	Chen et al., NeurIPS 2024
13	BrainID-MRI + gradient BrainID-MRI + gradient Liu et al., CVPR 2025 Score 0.783 Correct & Reconstruct →	0.783	0.857 38.94 dB / 0.985	0.768 32.48 dB / 0.948	0.723 29.4 dB / 0.907	✓ Certified	Liu et al., CVPR 2025
14	MoDL-Net++ + gradient MoDL-Net++ + gradient 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 Score 0.782 Correct & Reconstruct →	0.782	0.864 38.84 dB / 0.985	0.779 32.99 dB / 0.952	0.703 29.16 dB / 0.903	✓ 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
15	U-Net++ + gradient U-Net++ + gradient 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 Score 0.775 Correct & Reconstruct →	0.775	0.863 38.5 dB / 0.984	0.769 31.55 dB / 0.938	0.694 28.67 dB / 0.894	✓ 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
16	MMR-Mamba + gradient MMR-Mamba + gradient Zhao et al., Med. Image Anal. 2025 Score 0.775 Correct & Reconstruct →	0.775	0.877 39.79 dB / 0.987	0.751 30.52 dB / 0.924	0.698 28.78 dB / 0.896	✓ Certified	Zhao et al., Med. Image Anal. 2025
17	ReconFormer + gradient ReconFormer + gradient Guo et al., IEEE TMI 2024 Score 0.769 Correct & Reconstruct →	0.769	0.835 36.62 dB / 0.976	0.766 31.63 dB / 0.939	0.705 28.58 dB / 0.892	✓ Certified	Guo et al., IEEE TMI 2024
18	SwinMR + gradient SwinMR + gradient Huang et al., MICCAI 2022 Score 0.768 Correct & Reconstruct →	0.768	0.850 37.26 dB / 0.979	0.767 32.28 dB / 0.946	0.688 26.93 dB / 0.856	✓ Certified	Huang et al., MICCAI 2022
19	E2E-VarNet + gradient E2E-VarNet + gradient Sriram et al., MICCAI 2020 Score 0.762 Correct & Reconstruct →	0.762	0.860 37.73 dB / 0.981	0.722 29.83 dB / 0.914	0.703 28.45 dB / 0.890	✓ Certified	Sriram et al., MICCAI 2020
20	BM3D-MRI + gradient BM3D-MRI + gradient Eksioglu, Comput. Math. Meth. Med. 2016 Score 0.740 Correct & Reconstruct →	0.740	0.775 32.3 dB / 0.946	0.740 30.18 dB / 0.920	0.706 28.56 dB / 0.892	✓ Certified	Eksioglu, Comput. Math. Meth. Med. 2016
21	PnP-DnCNN + gradient PnP-DnCNN + gradient Ahmad et al., IEEE TCI 2019 (DOI:10.1109/TCI.2019.2944521) Score 0.740 Correct & Reconstruct →	0.740	0.782 32.34 dB / 0.946	0.757 31.29 dB / 0.935	0.680 27.96 dB / 0.880	✓ Certified	Ahmad et al., IEEE TCI 2019 (DOI:10.1109/TCI.2019.2944521)
22	DCCNN + gradient DCCNN + gradient Schlemper et al., IEEE TMI 2018 Score 0.723 Correct & Reconstruct →	0.723	0.812 34.15 dB / 0.962	0.694 28.22 dB / 0.885	0.664 26.57 dB / 0.847	✓ Certified	Schlemper et al., IEEE TMI 2018
23	HybridCascade + gradient HybridCascade + gradient Fastmri, arXiv 2020 Score 0.718 Correct & Reconstruct →	0.718	0.821 35.79 dB / 0.972	0.695 27.08 dB / 0.860	0.637 24.64 dB / 0.791	✓ Certified	Fastmri, arXiv 2020
24	SENSE + gradient SENSE + gradient Pruessmann et al., MRM 1999 Score 0.703 Correct & Reconstruct →	0.703	0.723 28.37 dB / 0.888	0.693 26.99 dB / 0.858	0.692 27.66 dB / 0.873	✓ Certified	Pruessmann et al., MRM 1999
25	LORAKS + gradient LORAKS + gradient Haldar, IEEE TMI 2014 Score 0.700 Correct & Reconstruct →	0.700	0.788 32.05 dB / 0.943	0.680 27.04 dB / 0.859	0.632 24.46 dB / 0.784	✓ Certified	Haldar, IEEE TMI 2014
26	GRAPPA + gradient GRAPPA + gradient Griswold et al., MRM 2002 Score 0.689 Correct & Reconstruct →	0.689	0.728 29.36 dB / 0.907	0.683 26.81 dB / 0.853	0.655 25.44 dB / 0.816	✓ Certified	Griswold et al., MRM 2002
27	U-Net + gradient U-Net + gradient Zbontar et al., arXiv 2018 Score 0.688 Correct & Reconstruct →	0.688	0.792 32.95 dB / 0.952	0.659 26.19 dB / 0.837	0.613 24.16 dB / 0.774	✓ Certified	Zbontar et al., arXiv 2018
28	k-t SPARSE-SENSE + gradient k-t SPARSE-SENSE + gradient Lustig et al., MRM 2006 Score 0.687 Correct & Reconstruct →	0.687	0.746 30.1 dB / 0.918	0.680 26.82 dB / 0.854	0.635 25.19 dB / 0.808	✓ Certified	Lustig et al., MRM 2006
29	Deep-ADMM-Net + gradient Deep-ADMM-Net + gradient Yang et al., NeurIPS 2016 Score 0.682 Correct & Reconstruct →	0.682	0.810 34.15 dB / 0.962	0.655 25.47 dB / 0.817	0.582 23.37 dB / 0.745	✓ Certified	Yang et al., NeurIPS 2016
30	MoDL + gradient MoDL + gradient Aggarwal et al., IEEE TMI 2019 Score 0.680 Correct & Reconstruct →	0.680	0.804 34.12 dB / 0.962	0.658 26.26 dB / 0.839	0.578 23.16 dB / 0.737	✓ Certified	Aggarwal et al., IEEE TMI 2019
31	ALOHA + gradient ALOHA + gradient Jin et al., IEEE TMI 2016 Score 0.664 Correct & Reconstruct →	0.664	0.778 32.36 dB / 0.946	0.645 25.38 dB / 0.814	0.570 22.13 dB / 0.696	✓ Certified	Jin et al., IEEE TMI 2016
32	L1-Wavelet + gradient L1-Wavelet + gradient Lustig et al., MRM 2007 Score 0.659 Correct & Reconstruct →	0.659	0.734 29.12 dB / 0.902	0.642 25.31 dB / 0.812	0.600 23.07 dB / 0.734	✓ Certified	Lustig et al., MRM 2007
33	Score-MRI + gradient Score-MRI + gradient Chung & Ye, Med. Image Anal. 2022 Score 0.651 Correct & Reconstruct →	0.651	0.733 29.51 dB / 0.909	0.623 24.06 dB / 0.771	0.598 23.79 dB / 0.761	✓ Certified	Chung & Ye, Med. Image Anal. 2022
34	ESPIRiT + gradient ESPIRiT + gradient Uecker et al., MRM 2014 Score 0.635 Correct & Reconstruct →	0.635	0.760 30.84 dB / 0.929	0.604 23.64 dB / 0.755	0.541 21.38 dB / 0.663	✓ Certified	Uecker et al., MRM 2014
35	Zero-Filled IFFT + gradient Zero-Filled IFFT + gradient Pruessmann et al., MRM 1999 Score 0.557 Correct & Reconstruct →	0.557	0.614 23.45 dB / 0.748	0.559 21.44 dB / 0.666	0.499 19.7 dB / 0.584	✓ Certified	Pruessmann et al., MRM 1999

Complete score requires all 3 tiers (Public + Dev + Hidden).

Join the competition →

Scoring: 0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖) PSNR 40% · SSIM 40% · Consistency 20%

Public 3 scenes

Full-access development tier with all data visible.

What you get & how to use

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.

Public Leaderboard

#	Method	Score	PSNR	SSIM
1	SwinMR++ + gradient	0.888	41.76	0.991
2	PromptMR-SFM + gradient	0.881	39.81	0.987
3	HUMUS-Net++ + gradient	0.880	40.27	0.989
4	MMR-Mamba + gradient	0.877	39.79	0.987
5	HybridCascade++ + gradient	0.874	40.42	0.989
6	MR-IPT + gradient	0.874	40.09	0.988
7	MRI-FM + gradient	0.870	39.33	0.986
8	MRI-DiffusionNet + gradient	0.868	39.01	0.985
9	MoDL-Net++ + gradient	0.864	38.84	0.985
10	ReconFormer++ + gradient	0.863	39.3	0.986
11	U-Net++ + gradient	0.863	38.5	0.984
12	E2E-VarNet + gradient	0.860	37.73	0.981
13	PnP-DnCNN-Pro + gradient	0.857	38.37	0.983
14	BrainID-MRI + gradient	0.857	38.94	0.985
15	MRDynamo + gradient	0.852	37.95	0.982
16	SwinMR + gradient	0.850	37.26	0.979
17	PromptMR + gradient	0.842	36.9	0.978
18	ReconFormer + gradient	0.835	36.62	0.976
19	HUMUS-Net + gradient	0.834	36.9	0.978
20	HybridCascade + gradient	0.821	35.79	0.972
21	DCCNN + gradient	0.812	34.15	0.962
22	Deep-ADMM-Net + gradient	0.810	34.15	0.962
23	MoDL + gradient	0.804	34.12	0.962
24	U-Net + gradient	0.792	32.95	0.952
25	LORAKS + gradient	0.788	32.05	0.943
26	PnP-DnCNN + gradient	0.782	32.34	0.946
27	ALOHA + gradient	0.778	32.36	0.946
28	BM3D-MRI + gradient	0.775	32.3	0.946
29	ESPIRiT + gradient	0.760	30.84	0.929
30	k-t SPARSE-SENSE + gradient	0.746	30.1	0.918
31	L1-Wavelet + gradient	0.734	29.12	0.902
32	Score-MRI + gradient	0.733	29.51	0.909
33	GRAPPA + gradient	0.728	29.36	0.907
34	SENSE + gradient	0.723	28.37	0.888
35	Zero-Filled IFFT + gradient	0.614	23.45	0.748

Spec Ranges (4 parameters)

Parameter	Min	Max	Unit
shear_wave_frequency_error	-2.0	4.0	-
wave_attenuation_model	-0.15	0.15	-
motion_encoding_gradient_error	-1.0	2.0	-
boundary_reflection	-4.0	8.0	amplitude

View Details →

Dev 3 scenes

Blind evaluation tier — no ground truth available.

What you get & how to use

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.

Dev Leaderboard

#	Method	Score	PSNR	SSIM
1	SwinMR++ + gradient	0.855	38.56	0.984
2	ReconFormer++ + gradient	0.842	38.24	0.983
3	PnP-DnCNN-Pro + gradient	0.827	37.5	0.98
4	HUMUS-Net++ + gradient	0.821	35.46	0.97
5	HUMUS-Net + gradient	0.800	34.74	0.966
6	HybridCascade++ + gradient	0.797	35.13	0.969
7	PromptMR-SFM + gradient	0.795	33.62	0.958
8	MRDynamo + gradient	0.791	32.98	0.952
9	PromptMR + gradient	0.785	32.87	0.951
10	MRI-FM + gradient	0.783	32.81	0.951
11	MR-IPT + gradient	0.781	33.45	0.956
12	MoDL-Net++ + gradient	0.779	32.99	0.952
13	MRI-DiffusionNet + gradient	0.772	33.06	0.953
14	U-Net++ + gradient	0.769	31.55	0.938
15	BrainID-MRI + gradient	0.768	32.48	0.948
16	SwinMR + gradient	0.767	32.28	0.946
17	ReconFormer + gradient	0.766	31.63	0.939
18	PnP-DnCNN + gradient	0.757	31.29	0.935
19	MMR-Mamba + gradient	0.751	30.52	0.924
20	BM3D-MRI + gradient	0.740	30.18	0.92
21	E2E-VarNet + gradient	0.722	29.83	0.914
22	HybridCascade + gradient	0.695	27.08	0.86
23	DCCNN + gradient	0.694	28.22	0.885
24	SENSE + gradient	0.693	26.99	0.858
25	GRAPPA + gradient	0.683	26.81	0.853
26	LORAKS + gradient	0.680	27.04	0.859
27	k-t SPARSE-SENSE + gradient	0.680	26.82	0.854
28	U-Net + gradient	0.659	26.19	0.837
29	MoDL + gradient	0.658	26.26	0.839
30	Deep-ADMM-Net + gradient	0.655	25.47	0.817
31	ALOHA + gradient	0.645	25.38	0.814
32	L1-Wavelet + gradient	0.642	25.31	0.812
33	Score-MRI + gradient	0.623	24.06	0.771
34	ESPIRiT + gradient	0.604	23.64	0.755
35	Zero-Filled IFFT + gradient	0.559	21.44	0.666

Spec Ranges (4 parameters)

Parameter	Min	Max	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

Submit Reconstruction View Details →

Hidden 3 scenes

Fully blind server-side evaluation — no data download.

What you get & how to use

What you get: No data downloadable. Algorithm runs server-side on hidden measurements.

How to use: Package algorithm as Docker container / Python script. Submit via link.

What to submit: Containerized algorithm accepting y + H, outputting x_hat + corrected spec.

Hidden Leaderboard

#	Method	Score	PSNR	SSIM
1	SwinMR++ + gradient	0.832	37.75	0.981
2	PnP-DnCNN-Pro + gradient	0.820	35.88	0.973
3	ReconFormer++ + gradient	0.803	36.01	0.973
4	HybridCascade++ + gradient	0.787	34.19	0.962
5	PromptMR-SFM + gradient	0.768	31.94	0.942
6	PromptMR + gradient	0.768	32.75	0.95
7	HUMUS-Net++ + gradient	0.762	31.5	0.937
8	MR-IPT + gradient	0.754	31.64	0.939
9	MRI-FM + gradient	0.752	31.75	0.94
10	HUMUS-Net + gradient	0.752	31.91	0.942
11	MRI-DiffusionNet + gradient	0.744	31.11	0.932
12	MRDynamo + gradient	0.743	31.41	0.936
13	BrainID-MRI + gradient	0.723	29.4	0.907
14	BM3D-MRI + gradient	0.706	28.56	0.892
15	ReconFormer + gradient	0.705	28.58	0.892
16	MoDL-Net++ + gradient	0.703	29.16	0.903
17	E2E-VarNet + gradient	0.703	28.45	0.89
18	MMR-Mamba + gradient	0.698	28.78	0.896
19	U-Net++ + gradient	0.694	28.67	0.894
20	SENSE + gradient	0.692	27.66	0.873
21	SwinMR + gradient	0.688	26.93	0.856
22	PnP-DnCNN + gradient	0.680	27.96	0.88
23	DCCNN + gradient	0.664	26.57	0.847
24	GRAPPA + gradient	0.655	25.44	0.816
25	HybridCascade + gradient	0.637	24.64	0.791
26	k-t SPARSE-SENSE + gradient	0.635	25.19	0.808
27	LORAKS + gradient	0.632	24.46	0.784
28	U-Net + gradient	0.613	24.16	0.774
29	L1-Wavelet + gradient	0.600	23.07	0.734
30	Score-MRI + gradient	0.598	23.79	0.761
31	Deep-ADMM-Net + gradient	0.582	23.37	0.745
32	MoDL + gradient	0.578	23.16	0.737
33	ALOHA + gradient	0.570	22.13	0.696
34	ESPIRiT + gradient	0.541	21.38	0.663
35	Zero-Filled IFFT + gradient	0.499	19.7	0.584

Spec Ranges (4 parameters)

Parameter	Min	Max	Unit
shear_wave_frequency_error	-1.4	4.6	-
wave_attenuation_model	-0.15	0.15	-
motion_encoding_gradient_error	-0.7	2.3	-
boundary_reflection	-2.8	9.2	amplitude

Submit Algorithm View Details →

Blind Reconstruction Challenge

Challenge

Given measurements with unknown mismatch and spec ranges (not exact params), reconstruct the original signal. A method must be evaluated on all three tiers for a complete score. Scored on a composite metric: 0.4 × PSNR_norm + 0.4 × SSIM + 0.2 × (1 − ‖y − Ĥx̂‖/‖y‖).

Input

Measurements y, ideal forward model H, spec ranges

Output

Reconstructed signal x̂

Spec DAG — Forward Model Pipeline

M → F → S → D

M Modulation

F Fourier

S Sampling

D Detector

Mismatch Parameters

Symbol	Parameter	Description	Perturbed
s_w	shear_wave_frequency_error	Shear wave frequency error (-)	2.0
w_a	wave_attenuation_model	Wave attenuation model (-)	0.0
m_e	motion_encoding_gradient_error	Motion encoding gradient error (-)	1.0
b_r	boundary_reflection	Boundary reflection (amplitude)	4.0

Credits System

40%

Platform Profit Pool

Revenue allocated to benchmark rewards

30%

Winner Share

Top algorithm receives from pool

$100

Min Withdrawal

Minimum payout threshold

Spec Primitives Reference (11 primitives)

P Propagation

Free-space or medium propagation kernel (Fresnel, Rayleigh-Sommerfeld).

M Mask / Modulation

Spatial or spatio-temporal amplitude modulation (coded aperture, SLM pattern).

Π Projection

Geometric projection operator (Radon transform, fan-beam, cone-beam).

F Fourier Sampling

Sampling in the Fourier / k-space domain (MRI, ptychography).

C Convolution

Shift-invariant convolution with a point-spread function (PSF).

Σ Summation / Integration

Summation along a physical dimension (spectral, temporal, angular).

D Detector

Sensor readout with gain g and noise model η (Gaussian, Poisson, mixed).

S Structured Illumination

Patterned illumination (block, Hadamard, random) applied to the scene.

W Wavelength Dispersion

Spectral dispersion element (prism, grating) with shift α and aperture a.

R Rotation / Motion

Sample or gantry rotation (CT, electron tomography).

Λ Wavelength Selection

Spectral filter or monochromator selecting a wavelength band.