Undersampled radial MRI with multiple coils. Iterative image reconstruction using a total variation constraint

By K. Block, Martin Uecker, Jens Frahm. Magnetic Resonance in Medicine, 2007

901 citations recorded by the source corpus.

Subfields: Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/316e2eceaf0a9e153ec111a9630029cc63b6d770

How researchers see this paper

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

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Accelerating SENSE using compressed sensing (2009, methodology): “2 as in Block et al. (11) and Ying et al. (26), and the other used SparseMRI for a full FOV image in each channel and a SoS combination.”
Prior image constrained compressed sensing (PICCS) (2008, background): “(3)] of the total variation (TV), viz.”
An efficient algorithm for compressed MR imaging using total variation and wavelets (2008, methodology): “[1] used total variation as a constraint, and the work by He et al.”
Deep-Learning Methods for Parallel Magnetic Resonance Imaging Reconstruction: A Survey of the Current Approaches, Trends, and Issues (2019, methodology): “Total Variation based methods have been used successfully in combination with radial [19] and spiral [28] acquisitions as well as in dynamic imaging [29].”
Self‐supervised learning of physics‐guided reconstruction neural networks without fully sampled reference data (2019, methodology): “ points in Λ are used to define the loss function. Thus, to enable training without using fully-sampled data, the following loss function is minimized 𝑖min 𝜽 1 𝑁 ∑ℒ(�Λ 𝑖,𝐄 Λ@𝑓(yΘ 𝑖,𝐄 Θ;𝜽)A) � 𝑖=1 . (10) In other words, the unrolled network output image 𝑓(yΘ𝑖,𝐄 Θ 𝑖;𝜽) which only uses t”
Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction (2021, methodology): “Results of the MR reconstruction task: (a) TV [3], (b) UNet [41], (c) score-POCS [6] using 1000 steps starting from T = 1, (d) proposed method (CCDF) using 20 steps from t0 = 0.”
Deep ADMM-Net for Compressive Sensing MRI (2016, neutral): “Total Variation (TV) regularization in gradient domain has been widely utilized in MRI [3, 4].”
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).”
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.”
A Deep Cascade of Convolutional Neural Networks for MR Image Reconstruction (2017, methodology): “s. While Cartesian acquisition is the most common protocol in practice and offers straightforward implementation using fast Fourier transform (FFT), other practical sampling strategies such as radial [34] or spiral [35] could be considered, which achieve greater aliasing incoherence. Nevertheless, t”
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).”
A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstruction (2017, methodology): “in practice and offers straightforward implementation using fast Fourier transform (FFT), other practical sampling strategies such as radial [34] or spiral [35] could be considered, which achieve greater aliasing incoherence.”
Low-rank and Sparse Matrix Decomposition for Accelerated Dynamic MRI with Separation of Background and Dynamic Components (2014, background): “A key advantage for MRI is that CS can be combined with parallel imaging to further increase imaging speed by exploiting joint sparsity in the multicoil image ensemble rather than in each coil separately (5-8).”
MODEL-BASED IMAGE RECONSTRUCTION FOR MRI (2010, methodology): “…iterative reconstruction that has been adopted in commercial positron emission tomography scanners is to use an unregularized algorithm, initialize it with a uniform image, stop iterating just as the image gets unacceptably noisy, and then perhaps apply a bit of post-filtering to reduce the noise.”
Sparse MRI: The application of compressed sensing for rapid MR imaging (2007, methodology): “In the Appendix we describe our approach which is similar to (19,21,35), using non-linear conjugate gradients and backtracking line-search.”
Second order total generalized variation (TGV) for MRI (2011, methodology): “, gP , we follow the approach of (7) and assume that there are”