Filters








680 Hits in 6.4 sec

Motion compensated compressed sensing dynamic MRI with low-rank patch-based residual reconstruction

Huisu Yoon, Kyung Sang Kim, Jong Chul Ye
2013 2013 IEEE 10th International Symposium on Biomedical Imaging  
motion compensated k-t FOCUSS.  ...  To address this, this paper proposes a novel patch-based residual encoding scheme to exploit geometric similarity in the residual images.  ...  More specifically, we perform a novel patch-based non-local ME/MC using a diastole phase reconstruction as a reference, after which the patch-based low rank penalty is applied for residual encoding.  ... 
doi:10.1109/isbi.2013.6556475 dblp:conf/isbi/YoonKY13 fatcat:ijmassvuxzfezlmqpzxnjc46ny

Accelerated dynamic MRI using patch regularization for implicit motion compensation

Yasir Q. Mohsin, Sajan Goud Lingala, Edward DiBella, Mathews Jacob
2016 Magnetic Resonance in Medicine  
Purpose-To introduce a fast algorithm for motion-compensated accelerated dynamic MRI.  ...  Methods-An efficient patch smoothness regularization scheme, which implicitly compensates for inter-frame motion, is introduced to recover dynamic MRI data from highly undersampled measurements.  ...  This approach is similar to the patch-based low-rank method introduced for breathheld cardiac cine MRI (24) .  ... 
doi:10.1002/mrm.26215 pmid:27091812 pmcid:PMC5300957 fatcat:7l26nwh5mzc4bcm7sgsohk2fhe

Deformation Corrected Compressed Sensing (DC-CS): A Novel Framework for Accelerated Dynamic MRI

Sajan Goud Lingala, Edward DiBella, Mathews Jacob
2015 IEEE Transactions on Medical Imaging  
We propose a novel deformation corrected compressed sensing (DC-CS) framework to recover contrast enhanced dynamic magnetic resonance images from undersampled measurements.  ...  Through experiments on numerical phantom and in vivo myocardial perfusion MRI datasets, we observe superior image quality of the proposed DC-CS scheme in comparison to the classical k-t FOCUSS with motion  ...  The proposed approach enables us to use arbitrary signal priors (e.g., sparsity in specified transform domain, low-rank property, patch-based low-rank priors) in the reconstruction; the appropriate method  ... 
doi:10.1109/tmi.2014.2343953 pmid:25095251 pmcid:PMC4411243 fatcat:scuitzrulffafpauzsvuwtghvi

Deformation corrected compressed sensing (DC-CS): a novel framework for accelerated dynamic MRI [article]

Sajan Goud Lingala, Edward DiBella, Mathews Jacob
2014 arXiv   pre-print
Through experiments on numerical phantom and in vivo myocardial perfusion MRI datasets, we demonstrate the utility of the proposed DC-CS scheme in providing robust reconstructions with reduced motion artifacts  ...  We propose a novel deformation corrected compressed sensing (DC-CS) framework to recover dynamic magnetic resonance images from undersampled measurements.  ...  compressed sensing reconstructions.  ... 
arXiv:1405.7718v2 fatcat:bncnnznwpnebjgp2tyafo4o2ye

From Compressed-Sensing to Artificial Intelligence-Based Cardiac MRI Reconstruction

Aurélien Bustin, Niccolo Fuin, René M. Botnar, Claudia Prieto
2020 Frontiers in Cardiovascular Medicine  
The underlying assumptions of established techniques such as compressed sensing and low-rank reconstruction are briefly summarized, while a greater focus is given to recent advances in dictionary learning  ...  and deep learning based CMR reconstruction.  ...  FIGURE 2 | 2 FIGURE 2 | Schematic diagram of compressed sensing and patch-based low-rank reconstructions for CMR. FIGURE 3 | 3 FIGURE 3 | Reconstruction comparisons for coronary MR angiography.  ... 
doi:10.3389/fcvm.2020.00017 pmid:32158767 pmcid:PMC7051921 fatcat:xbge626jhzeulfjlssdlqnalze

Compressed sensing for body MRI

Li Feng, Thomas Benkert, Kai Tobias Block, Daniel K. Sodickson, Ricardo Otazo, Hersh Chandarana
2016 Journal of Magnetic Resonance Imaging  
This paper presents a brief overview of the application of compressed sensing techniques in body MRI, where imaging speed is crucial due to the presence of respiratory motion along with stringent constraints  ...  Compressed sensing aims to reconstruct unaliased images from fewer measurements than that are traditionally required in MRI by exploiting image compressibility or sparsity.  ...  Low-Rank Plus Sparse Motion Compensation Respiratory motion is one of the most common sources of artifacts in body MRI and remains a major challenge for clinical exams.  ... 
doi:10.1002/jmri.25547 pmid:27981664 pmcid:PMC5352490 fatcat:ulfop3kccrg4tdpqsybotylccy

Compressed sensing MRI: a review from signal processing perspective

Jong Chul Ye
2019 BMC Biomedical Engineering  
For the last two decades, one of the most important breakthroughs in this direction is the introduction of compressed sensing (CS) that allows accurate reconstruction from sparsely sampled k-space data  ...  The recent FDA approval of compressed sensing products for clinical scans clearly reflect the maturity of this technology.  ...  [20] proposes motion estimated and compensated modification of k-t FOCUSS to make the residual signal much sparser.  ... 
doi:10.1186/s42490-019-0006-z pmid:32903346 pmcid:PMC7412677 fatcat:csxgccdfsndf5gqqstxdlejo44

Blind Compressive Sensing Dynamic MRI

S. G. Lingala, M. Jacob
2013 IEEE Transactions on Medical Imaging  
We observe superior reconstruction performance with the BCS scheme in comparison to existing low rank and compressed sensing schemes.  ...  We propose a novel blind compressive sensing (BCS) frame work to recover dynamic magnetic resonance images from undersampled measurements.  ...  We finally compare the reconstructions of blind CS against existing low rank and compressed sensing schemes using invivo Cartesian and radial free breathing myocardial perfusion MRI datasets (section III.D  ... 
doi:10.1109/tmi.2013.2255133 pmid:23542951 pmcid:PMC3902976 fatcat:xqxr277qurdtlnvxdmoh5ybjae

Motion-compensated compressed sensing for dynamic contrast-enhanced MRI using regional spatiotemporal sparsity and region tracking: Block low-rank sparsity with motion-guidance (BLOSM)

Xiao Chen, Michael Salerno, Yang Yang, Frederick H. Epstein
2013 Magnetic Resonance in Medicine  
Purpose-Dynamic contrast-enhanced MRI of the heart is well-suited for acceleration with compressed sensing (CS) due to its spatiotemporal sparsity; however, respiratory motion can degrade sparsity and  ...  Methods-A new method, Block LOw-rank Sparsity with Motion-guidance (BLOSM), was developed to accelerate first-pass cardiac MRI, even in the presence of respiratory motion.  ...  Acknowledgments We are grateful to Craig Meyer for insightful discussions on many aspects of advanced image reconstruction techniques.  ... 
doi:10.1002/mrm.25018 pmid:24243528 pmcid:PMC4097987 fatcat:rb6lfpi5xffmxpckteuoz5iopm

Learning Optical Flow for Fast MRI Reconstruction [article]

T. Schmoderer, A.I Aviles-Rivero, V. Corona, N. Debroux, C-B. Schönlieb
2020 arXiv   pre-print
Our proposed approach combines - in a multi-task and hybrid model - the traditional compressed sensing formulation for the reconstruction of dynamic MRI with motion compensation by learning an optical  ...  In this work, we propose a new mathematical model for the reconstruction of high-quality medical MRI from few measurements.  ...  Our proposed approach combines -in a multi-task and hybrid model -the traditional compressed sensing formulation for the reconstruction of dynamic MRI with motion compensation by learnt optical flow approximation  ... 
arXiv:2004.10464v3 fatcat:5ka6b4wztrb7njo24pgjrer52m

Compressed Sensing Plus Motion (CS+M): A New Perspective for Improving Undersampled MR Image Reconstruction [article]

Angelica I. Aviles-Rivero, Noémie Debroux, Guy Williams, Martin J. Graves, Carola-Bibiane Schonlieb
2020 arXiv   pre-print
In this work, we propose a framework for dynamic MRI reconstruction framed under a new multi-task optimisation model called Compressed Sensing Plus Motion (CS+M).  ...  Firstly, we propose a single optimisation problem that simultaneously computes the MRI reconstruction and the physical motion.  ...  Compressed Sensing Plus Motion (CS+M) In this section, we introduce our CS+M model for improving under-sampled MRI reconstruction in dynamic settings.  ... 
arXiv:1810.10828v2 fatcat:qvielfncdnfwli7f2uhwfmmqu4

Low-Rank and Sparse Decomposition Model for Accelerating Dynamic MRI Reconstruction

Junbo Chen, Shouyin Liu, Min Huang
2017 Journal of Healthcare Engineering  
The reconstruction of dynamic magnetic resonance imaging (dMRI) from partially sampled k-space data has to deal with a trade-off between the spatial resolution and temporal resolution.  ...  In this paper, a low-rank and sparse decomposition model is introduced to resolve this issue, which is formulated as an inverse problem regularized by robust principal component analysis (RPCA).  ...  and compensation to compressed sensing framework for cardiac cine MRI.  ... 
doi:10.1155/2017/9856058 pmid:29093806 pmcid:PMC5591906 fatcat:xyxtahai5ffffkogslcczxe45y

Generalized low-rank nonrigid motion-corrected reconstruction for MR fingerprinting

Gastao Cruz, Haikun Qi, Olivier Jaubert, Thomas Kuestner, Torben Schneider, Rene Michael Botnar, Claudia Prieto
2021 Magnetic Resonance in Medicine  
This is achieved by integrating low-rank dictionary-based compression into the generalized MC model to reconstruct MC singular images, reducing motion artifacts in the resulting parametric maps.  ...  Develop a novel low-rank motion-corrected (LRMC) reconstruction for nonrigid motion-corrected MR fingerprinting (MRF).  ...  Moreover, the reconstruction is regularized with a patch-based low-rank tensor approximation (HD-PROST) 32 for improved performance.  ... 
doi:10.1002/mrm.29027 pmid:34601737 fatcat:lnp7qrhlvfhhpenr7du5stnkk4

High-Accuracy Total Variation With Application to Compressed Video Sensing

Mahdi S. Hosseini, Konstantinos N. Plataniotis
2014 IEEE Transactions on Image Processing  
We adopt this design to regulate the spatial and temporal redundancy in compressed video sensing problem to jointly recover frames from under-sampled measurements.  ...  We then seek the solution via alternating direction methods of multipliers and find a unique solution to quadratic minimization step with capability of handling different boundary conditions.  ...  The second part is carried out by compensating the estimated motion known as Motion Compensation (MC).  ... 
doi:10.1109/tip.2014.2332755 pmid:24988593 fatcat:iq5lleo3bnemfennbnitbu6n3e

Memory Efficient Model Based Deep Learning Reconstructions for High Spatial Resolution 3D Non-Cartesian Acquisitions [article]

Zachary Miller, Ali Pirasteh, Kevin M. Johnson
2022 arXiv   pre-print
Main results: MBDL with block-wise learning significantly improved image quality relative to L1 wavelet compressed sensing while simultaneously reducing average reconstruction time 38x.  ...  Objective: Model based deep learning (MBDL) has been challenging to apply to the reconstruction of 3D non-Cartesian MRI acquisitions due to extreme GPU memory demand (>250 GB using traditional backpropagation  ...  Common regularizers include L1-sparsity in a transform domain or low rankness for dynamic acquisitions.  ... 
arXiv:2204.13862v2 fatcat:widvl3uknjcvdfuc76iwaa2ai4
« Previous Showing results 1 — 15 out of 680 results