Compressed sensing in dynamic MRI

By U. Gamper, Peter Boesiger, Sebastian Kozerke. Magnetic Resonance in Medicine, 2008

612 citations recorded by the source corpus.

Subfields: Computational Mechanics, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/dbf685f8afb7e22b0dd5ca3ea69d5b479d04cb30

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

Prior image constrained compressed sensing (PICCS) (2008, positive): “The other sparsifying transforms such as second order difference of the image or the wavelet transform of the image have also been investigated in MRI to reconstruct image from few projections (16-18).”
Golden-Angle Radial Sparse Parallel MRI: Combination of Compressed Sensing, Parallel Imaging, and Golden-Angle Radial Sampling for Fast and Flexible Dynamic Volumetric MRI (2013, methodology): “CS methods exploit spatial and temporal correlations by employing irregular undersampling schemes to create incoherent aliasing artifacts and using a non-linear reconstruction to enforce sparsity in a suitable transform domain (17-24).”
MR Image Reconstruction From Highly Undersampled k-Space Data by Dictionary Learning (2011, methodology): “Compressed Sensing has been applied to a variety of MR modalities such as static MRI [16], [19], [20], dynamic MRI [17],[21],[ 41 ],[42],andperfusionimaginganddiffusiontensor imaging (DTI) [45].”
Performance comparison between total variation (TV)-based compressed sensing and statistical iterative reconstruction algorithms (2009, result): “This result is consistent with the in vivo results of previous studies in both MRI (Block et al 2007, Lustig et al 2007, Gamper et al 2008, Jung et al 2009) and micro-CT (Song et al 2007).”
Compressed sensing reconstruction for magnetic resonance parameter mapping (2010, methodology): “For example, in dynamic imaging, sparsity along the temporal dimension is promoted by subtracting a composite image or applying a Fourier transform in case of periodic motion (10,11).”
RODEO: Robust DE-aliasing autoencOder for real-time medical image reconstruction (2017, positive): “This formulation was proposed by [12, 13].”
Kalman filtered Compressed Sensing (2008, background): “A common example of such a problem is dynamic MRI or CT to image deforming human organs such as the beating heart or to image brain neural activationpatterns (in response to stimuli) using fMRI.”
Sparse Signal Recovery With Temporally Correlated Source Vectors Using Sparse Bayesian Learning (2011, methodology): “This single measurement vector (SMV) model (1) has a wide range of applications, such as electroencephalography (EEG)/magnetoencephalography (MEG) source localization [7], direction-ofarrival (DOA) estimation [8], radar detection [9], and magnetic resonance imaging (MRI) [10].”
Compressive sensing: From theory to applications, a survey (2013, background): “MRI is an active area of research for CS community and in recent past, a number of CS algorithms have been specifically designed for it [64], [65], [66], [54], [67].”
Magnetic resonance image reconstruction from undersampled measurements using a patch-based nonlocal operator (2014, methodology): “For the cardiac imaging, the temporal sparsity is represented with Fourier transform (Gamper et al., 2008; Jung et al., 2009; Otazo et al., 2010) and combined with low-rank strcture (Lingala et al., 2011; Zhao et al., 2012).”
Deep-Learning Methods for Parallel Magnetic Resonance Imaging Reconstruction: A Survey of the Current Approaches, Trends, and Issues (2019, background): “For dynamic acquisitions where periodic motion is encountered, sparsity in the Fourier domain common choice [27].”
Self‐supervised learning of physics‐guided reconstruction neural networks without fully sampled reference data (2019, background): “ften used to improve acquisition resolution. When higher acceleration rates are achievable, these are not solely used for image time reduction, but rather a trade-off is made with improved resolution (12,43,44). However, this newer resolution may necessitate re-training of the DL reconstruction, sin”
Modified-CS: Modifying compressive sensing for problems with partially known support (2009, background): “servation vector is assumed to be incoherent with respect to the sparsity basis of the signal/image [1], [2]. Important applications include realtime (causal and recursive) dynamic MRI reconstruction [3], [4], real-time single-pixel video imaging [5] or real-timetimevarying spatial ﬁeld estimation u”
Methods for Sparse Signal Recovery Using Kalman Filtering With Embedded Pseudo-Measurement Norms and Quasi-Norms (2010, background): “A typical example is the reconstruction of images from under-sampled Fourier data as encountered in radiology, biomedical imaging and astronomy [3], [4].”