Sparse MRI: The application of compressed sensing for rapid MR imaging

By Michael Lustig, David L. Donoho, John M. Pauly. 2007

7,475 citations recorded by the source corpus.

Subfields: Atomic and Molecular Physics, and Optics, Computational Mechanics, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

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

In Atomic and Molecular Physics, and Optics

In Computational Mechanics

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

An overview of deep learning in medical imaging focusing on MRI (2018, background): “MRF is closely related to the idea of compressed sensing [151] in MRI [152] in that MRF undersamples data in k-space producing aliasing artifacts in the reconstructed images that can be suppressed by compressed 27”
KIKI‐net: cross‐domain convolutional neural networks for reconstructing undersampled magnetic resonance images (2018, methodology): “(4) where bx is the estimation of the true image, x; and Hx is the hypothesis function to estimate bx with the input of xu and the unknown parameters hx.”
Compressive sensing of the Tohoku‐Oki Mw 9.0 earthquake: Frequency‐dependent rupture modes (2011, methodology): “0 earthquake in Japan from teleseismic P waves recorded by an array of stations in the United States.”
Scan-specific Robust Artificial-neural-networks for k-space Interpolation (RAKI) Reconstruction: Database-free Deep Learning for Fast Imaging (2018, methodology): “9,10 Although such undersampled acquisitions can be reconstructed using the linear conjugate gradient SENSE 8 or SPIRiT method, they are more traditionally processed with nonlinear iterative algorithms that enforce some regularization based on the compressibility of images in a transform domain.”
Image-Adaptive GAN based Reconstruction (2019, neutral): “This acquisition model is also more common in practice, e.g. in sparse MRI (Lustig, Donoho, and Pauly 2007).”
Learning a Variational Network for Reconstruction of Accelerated MRI Data (2017, background): “In MRI, we usually achieve incoherence by random (16) or non-Cartesian sampling trajectories (19).”
CNN-Based Projected Gradient Descent for Consistent CT Image Reconstruction (2017, background): “, total variation (TV) or the 1-norm of the wavelet coefficients of the image [1], [4]–[7]) or learned through a dictionary [8]–[10].”
Snapshot Compressive Imaging: Theory, Algorithms, and Applications (2021, background): “In contrast with global transformations, both SCI and sparse MRI incorporate compact forward model support to improve conditioning and a physics-based sampling structure.”
Robust Compressed Sensing MRI with Deep Generative Priors (2021, methodology): “Using compressed sensing for multi-coil MRI reconstruction has led to a rich body of work in the past two decades [58, 20, 83, 71].”
fastMRI: An Open Dataset and Benchmarks for Accelerated MRI (2018, background): “The introduction of compressed sensing (CS) in 2006 [2, 23] promised another breakthrough in the reduction of MR scan time.”
A Novel Strategy for Radar Imaging Based on Compressive Sensing (2008, neutral): “imaging [6], biosensing [7], geophysical data acquisition [8],”
From Denoising to Compressed Sensing (2014, background): “The matrix can take on a variety of physical interpretations: In a compressively sampled MRI, might be sampled rows of an n × n Fourier matrix [1], [2].”
Magnetic resonance image reconstruction from undersampled measurements using a patch-based nonlocal operator (2014, methodology): “…on the sampling scheme (Lustig et al., 2007), and e 2 CM is the noise vector, a typical CS-MRI reconstruction attempts to solve the following problem (Lustig et al., 2007): x̂ ¼ arg min x kWT xk1 þ k 2 ky FUxk22 ; ð2Þ where WT is a sparsifying transform of x, the k k1 stands for the ‘1 norm,…”
Deep Generative Adversarial Networks for Compressed Sensing Automates MRI (2017, background): “To render it well-posed, the conventional compressed-sensing (CS) incorporates the prior image information by means of sparsity regularization in a proper transform domain such as Wavelet (WV), or, Total Variation (TV); see e.g., [22].”
MODEL-BASED IMAGE RECONSTRUCTION FOR MRI (2010, background): “The moniker of compressed sensing or compressive sampling has become widespread for such techniques, and recently entire sessions at MR conferences are devoted to this topic [77] [12].”