Highly Undersampled Magnetic Resonance Image Reconstruction via Homotopic $\ell_{0}$ -Minimization

By Joshua D. Trzasko, Armando Manduca. IEEE Transactions on Medical Imaging, 2009

528 citations recorded by the source corpus.

Subfields: Computational Mechanics, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/0218f2595e68e974769693a50c6ccaf6ce671147

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

MR Image Reconstruction From Highly Undersampled k-Space Data by Dictionary Learning (2011, methodology): “The same authors claim that homotopic minimization can provide higher undersampling factors than norm based methods [ 19 ].”
Fast algorithms for nonconvex compressive sensing: MRI reconstruction from very few data (2009, background): “Trzasko and Manduca [ 11 ] reproduced this result with a faster algorithm, while also considering real MRI data examples.”
Nonconvex Nonsmooth Low Rank Minimization via Iteratively Reweighted Nuclear Norm (2015, background): “Logarithm [15], Minimax Concave Penalty (MCP) [16], Capped L1 [17], Exponential-Type Penalty (ETP) [18], Geman and Yang [19] and Laplace [20].”
Accelerated dynamic MRI exploiting sparsity and low-rank structure: k-t SLR (2011, unknown): “Motivated by the recent results in the use of non-convex penalties in compressed sensing [18], [19], we introduce novel non-convex spectral penalties to minimize the number of measurements required to recover a low-rank matrix.”
RODEO: Robust DE-aliasing autoencOder for real-time medical image reconstruction (2017, background): “ned version is solved instead. 2 21 n W D D (5) This direct formulation for MRI reconstruction via CS was proposed in [9]. Since then variations of the basic formulation has been proposed by others [10, 11]. So far we have discussed about, static MRI reconstruction. The problem in dynamic MRI is som”
Magnetic resonance image reconstruction from undersampled measurements using a patch-based nonlocal operator (2014, methodology): “Sampling patterns To test the performance of PANO with different sampling patterns, the pseudo radial sampling (Chen et al., 2010; Qu et al., 2010b; Trzasko and Manduca, 2009), shown in Fig.”
Compressive Sensing via Nonlocal Low-Rank Regularization (2014, methodology): “On the other hand, several experimental studies have shown that nonconvex optimization based approach toward CS [22], [23] often leads to more accurate reconstruction than their convex counterpart though at the cost of higher computational complexity.”
Self‐supervised learning of physics‐guided reconstruction neural networks without fully sampled reference data (2019, background): “The network for solving sub-problems (5) and (6) was unrolled for 10 iterations.”
MODEL-BASED IMAGE RECONSTRUCTION FOR MRI (2010, background): “Non-convex methods that enforce sparsity even more strongly are also under investigation[78].”