Low-rank and Sparse Matrix Decomposition for Accelerated Dynamic MRI with Separation of Background and Dynamic Components

By Ricardo Otazo, E.J. Candes, Daniel K. Sodickson. Magnetic Resonance in Medicine, 2014

735 citations recorded by the source corpus.

To apply the low‐rank plus sparse (L+S) matrix decomposition model to reconstruct undersampled dynamic MRI as a superposition of background and dynamic components in various problems of clinical interest.

Subfields: Computational Mechanics, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/b5211bec45d0f23487795ee0c1a3d87a526de40b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstruction (2017, methodology): “Sparse Matrix Decomposition (L+S) [21], which are the stateof-the-art compressed sensing and low-rank approaches.”
Modern regularization methods for inverse problems (2018, background): “[303]), which is again based on a decomposition”
Robust Subspace Learning: Robust PCA, Robust Subspace Tracking, and Robust Subspace Recovery (2017, methodology): “(b ) Low-rank and sparse matrix decomposition for accelerated dynamic MRI [22].”
Model-Based Deep Learning (2020, methodology): “The domain knowledge that S is sparse and that L is low rank implies that their recovery can be obtained by solving the following relaxed optimization problem [53]:”
Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstruction (2017, neutral): “An alternative popular approach is to exploit temporal redundancy to unravel from the aliasing by using CS approaches [1], [6] or CS combined with low-rank approaches [2], [7].”
Adaptive Spatiotemporal SVD Clutter Filtering for Ultrafast Doppler Imaging Using Similarity of Spatial Singular Vectors (2018, positive): “[18] also introduced a soft-thresholding strategies for MRI clutter filtering by weighting each singular values.”
KIKI‐net: cross‐domain convolutional neural networks for reconstructing undersampled magnetic resonance images (2018, methodology): “As more advanced algorithms, CS algorithms have been combined with parallel imaging(9-11) and low-rank constraint terms.(12,13) More recently, image-adaptive algorithms that enforce sparsity on image patches, such as dictionary-learning algorithms,(14-18) have appeared.”