SOTAVerified

MRI Reconstruction

In its most basic form, MRI reconstruction consists in retrieving a complex-valued image from its under-sampled Fourier coefficients. Besides, it can be addressed as a encoder-decoder task, in which the normative model in the latent space will only capture the relevant information without noise or corruptions. Then, we decode the latent space in order to have a reconstructed MRI.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 26–50 of 441 papers

TitleStatusHype
SMRD: SURE-based Robust MRI Reconstruction with Diffusion ModelsCode1
Fill the K-Space and Refine the Image: Prompting for Dynamic and Multi-Contrast MRI ReconstructionCode1
InverseSR: 3D Brain MRI Super-Resolution Using a Latent Diffusion ModelCode1
Learning Weakly Convex Regularizers for Convergent Image-Reconstruction AlgorithmsCode1
Generative Priors for MRI Reconstruction Trained from Magnitude-Only Images Using Phase AugmentationCode1
Learning Fourier-Constrained Diffusion Bridges for MRI ReconstructionCode1
Global k-Space Interpolation for Dynamic MRI Reconstruction using Masked Image ModelingCode1
Self-Supervised MRI Reconstruction with Unrolled Diffusion ModelsCode1
CDiffMR: Can We Replace the Gaussian Noise with K-Space Undersampling for Fast MRI?Code1
Optimizing Sampling Patterns for Compressed Sensing MRI with Diffusion Generative ModelsCode1
Implicit Neural Networks with Fourier-Feature Inputs for Free-breathing Cardiac MRI ReconstructionCode1
M4Raw: A multi-contrast, multi-repetition, multi-channel MRI k-space dataset for low-field MRI researchCode1
Fast MRI Reconstruction via Edge AttentionCode1
Learning Federated Visual Prompt in Null Space for MRI ReconstructionCode1
Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse ProblemsCode1
Decomposition-Based Variational Network for Multi-Contrast MRI Super-Resolution and ReconstructionCode1
A Neural-Network-Based Convex Regularizer for Inverse ProblemsCode1
T2LR-Net: An unrolling network learning transformed tensor low-rank prior for dynamic MR image reconstructionCode1
High-Frequency Space Diffusion Models for Accelerated MRICode1
Adaptive Diffusion Priors for Accelerated MRI ReconstructionCode1
K-Space Transformer for Undersampled MRI ReconstructionCode1
Dynamic Cardiac MRI Reconstruction Using Combined Tensor Nuclear Norm and Casorati Matrix Nuclear Norm RegularizationsCode1
A theoretical framework for self-supervised MR image reconstruction using sub-sampling via variable density Noisier2NoiseCode1
Scale-Equivariant Unrolled Neural Networks for Data-Efficient Accelerated MRI ReconstructionCode1
Monarch: Expressive Structured Matrices for Efficient and Accurate TrainingCode1
Show:102550
← PrevPage 2 of 18Next →
All datasetsfastMRI Knee 8xfastMRI Knee Val 8xfastMRI Brain 4xfastMRI Brain 8xfastMRI Knee 4xIXI

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1HUMUS-Net (train+val data)SSIM0.89—Unverified
2HUMUS-Net (train only)SSIM0.89—Unverified
3End-to-end variational networkSSIM0.89—Unverified
4XPDNetSSIM0.89—Unverified
#ModelMetricClaimedVerifiedStatus
1PromptMRSSIM0.9—Unverified
2HUMUS-Net-LSSIM0.9—Unverified
3HUMUS-NetSSIM0.89—Unverified
4E2E-VarNet (train+val)SSIM0.89—Unverified
#ModelMetricClaimedVerifiedStatus
1End-to-end variational networkSSIM0.96—Unverified
2XPDNetSSIM0.96—Unverified
#ModelMetricClaimedVerifiedStatus
1End-to-end variational networkSSIM0.94—Unverified
2XPDNetSSIM0.94—Unverified
#ModelMetricClaimedVerifiedStatus
1End-to-end variational networkSSIM0.93—Unverified
2XPDNetSSIM0.93—Unverified
#ModelMetricClaimedVerifiedStatus
1Residual U-NETDSSIM0—Unverified