734 Hits in 7.2 sec

Accelerating iterative field-compensated MR image reconstruction on GPUs

Yue Zhuo, Xiao-Long Wu, Justin P. Haldar, Wen-mei Hwu, Zhi-pei Liang, Bradley P. Sutton
2010 2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro  
We propose a fast implementation for iterative MR image reconstruction using Graphics Processing Units (GPU).  ...  To remedy this problem, one can utilize the fact that these iterative MR image reconstruction algorithms are highly parallelizable.  ...  We implement an advanced MR image reconstruction model on GPU using iterative conjugate gradients algorithm with magnetic field inhomogeneity compensation for geometric distortion and signal losses.  ... 
doi:10.1109/isbi.2010.5490112 dblp:conf/isbi/ZhuoWHHLS10 fatcat:qifszujt6vamddcth24rf2qge4

Sparse regularization in MRI iterative reconstruction using GPUs

Yue Zhuo, Bradley Sutton, Xiao-Long Wu, Justin Haldar, Wen-mei Hwu, Zhi-pei Liang
2010 2010 3rd International Conference on Biomedical Engineering and Informatics  
In this work, we extend our previous Graphics Processing Unit (GPU) implementation of MR image reconstruction with compensation for susceptibility-induced field inhomogeneity effects by incorporating an  ...  Regularization is a common technique used to improve image quality in inverse problems such as MR image reconstruction.  ...  Performance comparison The performance of the iterative reconstruction method on CPU and proposed accelerating reconstruction with field inhomogeneity compensation using GPU are compared in Table 1 .  ... 
doi:10.1109/bmei.2010.5640008 fatcat:fbkgzs3ptvco3g7tgt5fsoapvy

Learning-based and unrolled motion-compensated reconstruction for cardiac MR CINE imaging [article]

Jiazhen Pan and Daniel Rueckert and Thomas Küstner and Kerstin Hammernik
2022 arXiv   pre-print
Experiments on 40 acquired 2D cardiac MR CINE datasets demonstrate that the proposed unrolled MCMR framework can reconstruct high quality MR images at high acceleration rates where other state-of-the-art  ...  Motion-compensated MR reconstruction (MCMR) is a powerful concept with considerable potential, consisting of two coupled sub-problems: Motion estimation, assuming a known image, and image reconstruction  ...  [6] has pioneered the field of motion-compensated MR reconstruction (MCMR).  ... 
arXiv:2209.03671v1 fatcat:55kreoghhrbxvlphm7bx2w5hhe

Cardiac MRI compressed sensing image reconstruction with a graphics processing unit

Majid Sabbagh, Martin Uecker, Andrew J. Powell, Miriam Leeser, Mehdi H. Moghari
2016 2016 10th International Symposium on Medical Information and Communication Technology (ISMICT)  
GPU implementation was also used for accelerating CS reconstruction on 2D cine MRI datasets [32] .Kulkarni et al. and a few other research groups accelerated 1D or 2D CS reconstruction process using Field  ...  INTRODUCTION In this thesis, parallel processing is used to accelerate CS reconstruction for 3D cardiac MR imaging datasets acquired from patients.  ... 
doi:10.1109/ismict.2016.7498891 dblp:conf/ismict/SabbaghUPLM16 fatcat:gtoybnqx6zc3db7kj5cto3l33q

Compressed sensing reconstruction for whole-heart imaging with 3D radial trajectories: A graphics processing unit implementation

Seunghoon Nam, Mehmet Akçakaya, Tamer Basha, Christian Stehning, Warren J. Manning, Vahid Tarokh, Reza Nezafat
2012 Magnetic Resonance in Medicine  
In this paper, a parallelized implementation of an iterative CS reconstruction method for 3D radial acquisitions using a commercial graphics processing unit (GPU) is presented.  ...  Compressed sensing (CS) reconstruction can provide further acceleration in the acquisition by removing the incoherent artifacts due to undersampling and improving the image quality.  ...  regularization and 1000 iterations on GPU.  ... 
doi:10.1002/mrm.24234 pmid:22392604 pmcid:PMC3371294 fatcat:cuhxbw7pmjdkrakjihkvhxxc6y

Medical image processing on the GPU – Past, present and future

Anders Eklund, Paul Dufort, Daniel Forsberg, Stephen M. LaConte
2013 Medical Image Analysis  
This review presents the past and present work on GPU accelerated medical image processing, and is meant to serve as an overview and introduction to existing GPU implementations.  ...  In the field of medical imaging, GPUs are in some cases crucial for enabling practical use of computationally demanding algorithms.  ...  Conflicts of interest Anders Eklund owns the company Wanderine Consulting, which has done consulting work for the company Accelereyes (the creators of the Matlab GPU interface Jacket).  ... 
doi:10.1016/ pmid:23906631 fatcat:vsoek36pb5cuxdcmhlvfojwjuu

More IMPATIENT: A gridding-accelerated Toeplitz-based strategy for non-Cartesian high-resolution 3D MRI on GPUs

Jiading Gai, Nady Obeid, Joseph L. Holtrop, Xiao-Long Wu, Fan Lam, Maojing Fu, Justin P. Haldar, Wen-mei W. Hwu, Zhi-Pei Liang, Bradley P. Sutton
2013 Journal of Parallel and Distributed Computing  
Through implementation of optimized gridding into our iterative reconstruction scheme, speed-ups of more than a factor of 200 are provided in the improved GPU implementation compared to the previous accelerated  ...  Previously, we implemented a GPU-based image reconstruction technique called the Illinois Massively Parallel Acquisition Toolkit for Image reconstruction with ENhanced Throughput in MRI (IMPATIENT MRI)  ...  Acknowledgments The project described was supported by Award Number R21EB009768 from the National Institute of Biomedical Imaging and Bioengineering.  ... 
doi:10.1016/j.jpdc.2013.01.001 pmid:23682203 pmcid:PMC3652469 fatcat:2abeklmiufabpdgpje5ea23zr4

Impatient MRI: Illinois Massively Parallel Acceleration Toolkit for image reconstruction with enhanced throughput in MRI

Xiao-Long Wu, Jiading Gai, Fan Lam, Maojing Fu, Justin P. Haldar, Yue Zhuo, Zhi-Pei Liang, Wen-Mei Hwu, Bradley P. Sutton
2011 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro  
We present the Illinois Massively Parallel Acceleration Toolkit for Image reconstruction with ENhanced Throughput in MRI (IMPATIENT MRI), a reconstruction utility that enables advanced techniques within  ...  effects, including magnetic field inhomogeneity.  ...  This package builds on our previous work in GPUbased acceleration of MR algorithms [1, 2] , integrating new features and improved computational efficiency.  ... 
doi:10.1109/isbi.2011.5872356 dblp:conf/isbi/WuGLFHZLHS11 fatcat:rwl4hb3kfrdcxdkvyvni3bfqty

Fast Volume Reconstruction From Motion Corrupted Stacks of 2D Slices

Bernhard Kainz, Markus Steinberger, Wolfgang Wein, Maria Kuklisova-Murgasova, Christina Malamateniou, Kevin Keraudren, Thomas Torsney-Weir, Mary Rutherford, Paul Aljabar, Joseph V. Hajnal, Daniel Rueckert
2015 IEEE Transactions on Medical Imaging  
In this paper, we present a fast multi-GPU accelerated framework for slice-to-volume reconstruction.  ...  Motion between slice acquisitions results in spatial inconsistencies that can be resolved by slice-to-volume reconstruction (SVR) methods to provide high quality 3D image data.  ...  The Image Registration Toolkit was used under creative commons public licence from IXICO Ltd.  ... 
doi:10.1109/tmi.2015.2415453 pmid:25807565 pmcid:PMC7115883 fatcat:reultq2l25canki3hfyhsnuce4

Magnetic Resonance Sequences and Rapid Acquisition for MR-Guided Interventions

Adrienne E. Campbell-Washburn, Anthony Z. Faranesh, Robert J. Lederman, Michael S. Hansen
2015 Magnetic Resonance Imaging Clinics of North America  
Synopsis Interventional MR uses rapid imaging to guide diagnostic and therapeutic procedures. One of the attractions of MR-guidance is the abundance of inherent contrast mechanisms available.  ...  Dynamic procedural guidance with real-time imaging has pushed the limits of MR technology, demanding rapid acquisition and reconstruction paired with interactive control and device visualization.  ...  The software contains standard reconstruction tools, iterative solvers, and GPU components.  ... 
doi:10.1016/j.mric.2015.05.006 pmid:26499283 pmcid:PMC4621782 fatcat:jhyfecgj3je37kl22agzvpnjw4

Technical note: Accelerated nonrigid motion-compensated isotropic 3D coronary MR angiography

Teresa Correia, Gastão Cruz, Torben Schneider, René M. Botnar, Claudia Prieto
2017 Medical Physics (Lancaster)  
Currently, parallel imaging techniques are widely used in clinical MR, but often limited to a moderate two-fold acceleration.  ...  Nonrigid motion fields were incorporated into an undersampled motion-compensated reconstruction, which combines CS with the general matrix description formalism.  ... 
doi:10.1002/mp.12663 pmid:29131353 pmcid:PMC5814733 fatcat:7zysugafizf2ne7dfuvwt7defu

A Clinically Viable Vendor-Independent and Device-Agnostic Solution for Accelerated Cardiac MRI Reconstruction

Elena Martín-González, Elisa Moya-Sáez, Rosa-María Menchón-Lara, Javier Royuela-del-Val, César Palencia-de-Lara, Manuel Rodríguez-Cayetano, Federico Simmross-Wattenberg, Carlos Alberola-López
2021 Computer Methods and Programs in Biomedicine  
Recent research has reported methods that reconstruct cardiac MR images acquired with acceleration factors as high as 15 in Cartesian coordinates.  ...  If motion compensation is included, reconstruction time is in the order of one minute.  ...  Related work The field of MR reconstruction is very active and quite an activity has been focused on algorithm implementation on GPUs.  ... 
doi:10.1016/j.cmpb.2021.106143 pmid:34029830 fatcat:rzj4vaothvh2ppe5mytecy2yqq

Towards the clinical implementation of iterative low-dose cone-beam CT reconstruction in image-guided radiation therapy: Cone/ring artifact correction and multiple GPU implementation

Hao Yan, Xiaoyu Wang, Feng Shi, Ti Bai, Michael Folkerts, Laura Cervino, Steve B. Jiang, Xun Jia
2014 Medical Physics (Lancaster)  
Purpose: Compressed sensing (CS)-based iterative reconstruction (IR) techniques are able to reconstruct cone-beam CT (CBCT) images from undersampled noisy data, allowing for imaging dose reduction.  ...  On the reconstruction efficiency side, the long computation time hinders clinical use in image-guided radiation therapy (IGRT).  ...  Multiresolution (MR) Multiresolution is another feature employed in our iterative CBCT reconstructions. 17, 22 To allow the freedom of handling reconstructions at different image resolutions, each of  ... 
doi:10.1118/1.4898324 pmid:25370645 pmcid:PMC4241832 fatcat:ce4dflwi55ca5oz4s3nqlafswq

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
300 x 300-450 on a single GPU.  ...  We compared block-wise learning reconstructions against L1 wavelet compressed reconstructions and proxy ground truth images.  ...  However, one barrier to the clinical adoption of non-Cartesian imaging is the need for lengthy iterative reconstructions for parallel imaging and constrained reconstruction.  ... 
arXiv:2204.13862v2 fatcat:widvl3uknjcvdfuc76iwaa2ai4

Accelerating the computation for real-time application of the sinc function using graphics processing units

Sangwoo Kim, Chulhyun Lee
2020 Journal of Analytical Science and Technology  
We implemented an accelerated convolution function with the sinc kernel using GPUs computing and evaluated the reconstruction performance.  ...  In magnetic resonance imaging, the fidelity of image reconstruction is an important criterion.  ...  Availability of data and materials The computational code sets used in this study are available on a reasonable request from the corresponding author.  ... 
doi:10.1186/s40543-020-0205-1 fatcat:ol3ipeaqjng6zotyymfyasbx7a
« Previous Showing results 1 — 15 out of 734 results