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

Showing 7180 of 441 papers

TitleStatusHype
Is good old GRAPPA dead?Code1
Unsupervised MRI Reconstruction via Zero-Shot Learned Adversarial TransformersCode1
Deep J-Sense: Accelerated MRI Reconstruction via Unrolled Alternating OptimizationCode1
Zero-Shot Self-Supervised Learning for MRI ReconstructionCode1
Deep Convolutional Autoencoders for reconstructing magnetic resonance images of the healthy brainCode1
Regularization-Agnostic Compressed Sensing MRI Reconstruction with HypernetworksCode1
Density Compensated Unrolled Networks for Non-Cartesian MRI ReconstructionCode1
Results of the 2020 fastMRI Challenge for Machine Learning MR Image ReconstructionCode1
Learning Multiscale Convolutional Dictionaries for Image ReconstructionCode1
Adversarial Robust Training of Deep Learning MRI Reconstruction ModelsCode1
Show:102550
← PrevPage 8 of 45Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1HUMUS-Net (train+val data)SSIM0.89Unverified
2HUMUS-Net (train only)SSIM0.89Unverified
3End-to-end variational networkSSIM0.89Unverified
4XPDNetSSIM0.89Unverified
#ModelMetricClaimedVerifiedStatus
1PromptMRSSIM0.9Unverified
2HUMUS-Net-LSSIM0.9Unverified
3HUMUS-NetSSIM0.89Unverified
4E2E-VarNet (train+val)SSIM0.89Unverified
#ModelMetricClaimedVerifiedStatus
1End-to-end variational networkSSIM0.96Unverified
2XPDNetSSIM0.96Unverified
#ModelMetricClaimedVerifiedStatus
1End-to-end variational networkSSIM0.94Unverified
2XPDNetSSIM0.94Unverified
#ModelMetricClaimedVerifiedStatus
1End-to-end variational networkSSIM0.93Unverified
2XPDNetSSIM0.93Unverified
#ModelMetricClaimedVerifiedStatus
1Residual U-NETDSSIM0Unverified