Compressed Sensing MRI

By Michael Lustig, David L. Donoho, Juan M. Santos, John M. Pauly. IEEE Signal Processing Magazine, 2008

2,351 citations recorded by the source corpus.

Subfields: Computational Mechanics, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/506990305a80381fb7195b25a43d5735db48dd8e

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

Microwave Imaging Within the First-Order Born Approximation by Means of the Contrast-Field Bayesian Compressive Sensing (2012, methodology): “Thanks to these features, CS techniques have been already employed for solving electromagnetic inverse problems arising in radar [45], magnetic resonance [46], and terahertz applications [47].”
Intermediate Layer Optimization for Inverse Problems using Deep Generative Models (2021, background): “Such inverse problems naturally appear in many applications including medical imaging, single pixel reconstruction and other domains (Lustig et al., 2007; 2008; Chen et al., 2008; Duarte et al., 2008; Qaisar et al., 2013; Hegde et al., 2009).”
Kronecker Compressive Sensing (2012, methodology): “Kronecker product matrices have been proposed for use as sparsifying bases in CS for certain spatiotemporal signals [9], [11], [17].”
Compressive Sensing via Nonlocal Low-Rank Regularization (2014, background): “…under Grant 61227004 and Grant 61100154, in part by the Program for New Scientific and Technological Star of Shaanxi Province under Grant 2014KJXX-46, in part by the Fundamental Research Funds of the Central Universities of China under Grant BDY081424, and in part by NSF under Award ECCS-0968730.”
Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstruction (2017, neutral): “The class of methods which employ CS to the MRI reconstruction is termed as CS-MRI [8].”
Secure and Robust Machine Learning for Healthcare: A Survey (2020, background): “taken, patients might be asked to hold their breath during short scans [42].”
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 [52], [61]–[64].”
Prior Image-Constrained Reconstruction using Style-Based Generative Models (2021, positive): “Approaches incorporating sparsity-based priors have been successful in obtaining accurate reconstructions from incomplete measurements (Candès & Wakin, 2008; Lustig et al., 2008).”
Noise2Noise: Learning Image Restoration without Clean Data (2018, background): “Modern MRI techniques have long relied on compressed sensing (CS) to cheat the Nyquist-Shannon limit: they undersample k -space, and perform non-linear reconstruction that removes aliasing by exploiting the sparsity of the image in a suitable transform domain (Lustig et al., 2008).”
Probing the Pareto Frontier for Basis Pursuit Solutions (2008, background): “Some important applications include image reconstruction, such as MRI [35] [36] and seismic [30] [31] images, and model selection in regression [25].”
Confidence intervals and hypothesis testing for high-dimensional regression (2013, background): “Examples abound from signal processing (Lustig et al., 2008), to genomics (Peng et al.”
Compressed Sensing (2014, neutral): “Estas abarcan diversas áreas como: imagenoloǵıa medica [49, 45], conversión analógico/digital [68], detección mediante RADAR [4, 42], corrección de errores [18], cámaras digitales [34, 21, 51], Sismoloǵıa [41], Radioastronomı́a [71], comunicación inalámbrica [63, 3, 65] y redes de sensores inalámbri”
Deep Residual Learning for Accelerated MRI Using Magnitude and Phase Networks (2018, background): “2821699 lel MRI (pMRI) [1], [2] and compressed sensing (CS) MRI (CS-MRI) [3], [4] to provide accurate reconstruction from insufficient k-space samples.”
Compressed Sensing MRI Reconstruction Using a Generative Adversarial Network With a Cyclic Loss (2017, methodology): “Conventional CS-MRI reconstruction methods have been developed to leverage the sparsity of signal by using universal sparsifying transforms, such as Fourier transform, Total Variation (TV), and Wavelets [5], and to exploit the spatio-temporal correlations, such as k − t FOCUSS [21], [22] This sparsi”
DAGAN: Deep De-Aliasing Generative Adversarial Networks for Fast Compressed Sensing MRI Reconstruction (2018, methodology): “The regularisation terms R typically involve l q -norms (0 ≤ q ≤ 1) in the sparsifying domain of x [2].”