MRI Reconstruction
147 papers with code • 6 benchmarks • 3 datasets
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.
Benchmarks
These leaderboards are used to track progress in MRI Reconstruction
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find MRI Reconstruction models and implementations
fastMRI
IXI
SKM-TEA
Most implemented papers
Regularization-Agnostic Compressed Sensing MRI Reconstruction with Hypernetworks
alanqrwang/RegAgnosticCSMRI
•
•
In this paper, we explore a novel strategy of using a hypernetwork to generate the parameters of a separate reconstruction network as a function of the regularization weight(s), resulting in a regularization-agnostic reconstruction model.
Is good old GRAPPA dead?
We perform a qualitative analysis of performance of XPDNet, a state-of-the-art deep learning approach for MRI reconstruction, compared to GRAPPA, a classical approach.
Data augmentation for deep learning based accelerated MRI reconstruction with limited data
Deep neural networks have emerged as very successful tools for image restoration and reconstruction tasks.
Subtle Data Crimes: Naively training machine learning algorithms could lead to overly-optimistic results
mikgroup/subtle_data_crimes
•
•
We demonstrate this phenomenon for inverse problem solvers and show how their biased performance stems from hidden data preprocessing pipelines.
Swin Transformer for Fast MRI
ayanglab/swinmr
•
•
The IM and OM were 2D convolutional layers and the FEM was composed of a cascaded of residual Swin transformer blocks (RSTBs) and 2D convolutional layers.
HUMUS-Net: Hybrid unrolled multi-scale network architecture for accelerated MRI reconstruction
These models split input images into non-overlapping patches, embed the patches into lower-dimensional tokens and utilize a self-attention mechanism that does not suffer from the aforementioned weaknesses of convolutional architectures.
A Neural-Network-Based Convex Regularizer for Inverse Problems
axgoujon/convex_ridge_regularizers
•
•
The emergence of deep-learning-based methods to solve image-reconstruction problems has enabled a significant increase in reconstruction quality.
SMUG: Towards robust MRI reconstruction by smoothed unrolling
lgm70/smug
•
•
To address this problem, we propose a novel image reconstruction framework, termed SMOOTHED UNROLLING (SMUG), which advances a deep unrolling-based MRI reconstruction model using a randomized smoothing (RS)-based robust learning operation.
MRI Recovery with Self-Calibrated Denoisers without Fully-Sampled Data
sizhuoliu/reside
•
•
However, unlike traditional PnP approaches that utilize generic denoisers or train application-specific denoisers using high-quality images or image patches, ReSiDe directly trains the denoiser on the image or images that are being reconstructed from the undersampled data.
Generative AI for Medical Imaging: extending the MONAI Framework
project-monai/generativemodels
•
•
We have implemented these models in a generalisable fashion, illustrating that their results can be extended to 2D or 3D scenarios, including medical images with different modalities (like CT, MRI, and X-Ray data) and from different anatomical areas.
