Density Compensated Unrolled Networks For Non-Cartesian MRI Reconstruction

@article{Ramzi2021DensityCU,
  title={Density Compensated Unrolled Networks For Non-Cartesian MRI Reconstruction},
  author={Zaccharie Ramzi and Philippe Ciuciu and Jean-Luc Starck},
  journal={2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)},
  year={2021},
  pages={1443-1447}
}
Deep neural networks have recently been thoroughly investigated as a powerful tool for MRI reconstruction. There is a lack of research, however, regarding their use for a specific setting of MRI, namely non-Cartesian acquisitions. In this work, we introduce a novel kind of deep neural networks to tackle this problem, namely density compensated unrolled neural networks, which rely on Density Compensation to correct the uneven weighting of the k-space. We assess their efficiency on the publicly… Expand

Figures and Tables from this paper

Learning the sampling density in 2D SPARKLING MRI acquisition for optimized image reconstruction
The SPARKLING algorithm was originally developed for accelerated 2D magnetic resonance imaging (MRI) in the compressed sensing (CS) context. It yields non-Cartesian sampling trajectories that jointlyExpand

References

SHOWING 1-10 OF 27 REFERENCES
A Deep Cascade of Convolutional Neural Networks for MR Image Reconstruction
TLDR
This work proposes a framework for reconstructing MR images from undersampled data using a deep cascade of convolutional neural networks to accelerate the data acquisition process and shows that for Cartesian undersampling of 2D cardiac MR images, the proposed method outperforms the state-of-the-art compressed sensing approaches. Expand
Nonuniform Variational Network: Deep Learning for Accelerated Nonuniform MR Image Reconstruction
TLDR
This work presents a novel approach for reconstructing from nonuniform undersampled MR data, which is a convolutional neural network architecture based on the unrolling of a traditional iterative nonlinear reconstruction, where the knowledge of the non uniform forward and adjoint sampling operators are efficiently incorporated. Expand
fastMRI: An Open Dataset and Benchmarks for Accelerated MRI
TLDR
The fastMRI dataset is introduced, a large-scale collection of both raw MR measurements and clinical MR images that can be used for training and evaluation of machine-learning approaches to MR image reconstruction. Expand
Learned Primal-Dual Reconstruction
  • J. Adler, O. Öktem
  • Computer Science, Medicine
  • IEEE Transactions on Medical Imaging
  • 2018
We propose the Learned Primal-Dual algorithm for tomographic reconstruction. The algorithm accounts for a (possibly non-linear) forward operator in a deep neural network by unrolling a proximalExpand
An Adaptive Intelligence Algorithm for Undersampled Knee MRI Reconstruction
TLDR
A novel deep neural network is developed to refine and correct prior reconstruction assumptions given the training data to accelerate MR acquisition and demonstrates the superior performance and wide applicability of the method. Expand
U-Net: Convolutional Networks for Biomedical Image Segmentation
TLDR
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Expand
Dictionary Learning and Time Sparsity for Dynamic MR Data Reconstruction
TLDR
An iterative algorithm is presented that enables the application of DL for the reconstruction of cardiac cine data with Cartesian undersampling and is compared to and shown to systematically outperform k- t FOCUSS, a successful CS method that uses a fixed basis transform. Expand
Learning a variational network for reconstruction of accelerated MRI data
To allow fast and high‐quality reconstruction of clinical accelerated multi‐coil MR data by learning a variational network that combines the mathematical structure of variational models with deepExpand
KIKI‐net: cross‐domain convolutional neural networks for reconstructing undersampled magnetic resonance images
TLDR
To demonstrate accurate MR image reconstruction from undersampled k‐space data using cross‐domain convolutional neural networks (CNNs) using cross-domain Convolutional Neural Networks, a parallel version of TSP, is presented. Expand
Sampling density compensation in MRI: Rationale and an iterative numerical solution
TLDR
This method uses only the coordinates of the sampled data; unlike previous methods, it does not require knowledge of the trajectories and can easily handle trajectories that “cross” in k‐space. Expand
...
1
2
3
...