Real-time patch-based medical image modality propagation by GPU computing

by Eduardo Alcaín, Angel Torrado-Carvajal, Antonio S. Montemayor, Norberto Malpica
Abstract:
The synthesis of patient data of a certain medical image modality by applying an image processing pipeline starting from other modality is receiving a lot of interest recently, as it allows to save acquisition time and sometimes avoid radiation to the patient. An example of this is the creation of computerized tomography volumes from magnetic resonance imaging data, which can be useful for several applications such as electromagnetic simulations, cranial morphometry and attenuation correction in PET/MR systems. We present a fast patch-based algorithm for this purpose, implemented using graphics processing unit computing techniques and gaining up to $}{$backslashtimes$}{$ texttimes 15.9 of speedup against a multicore CPU solution and up to about $}{$backslashtimes$}{$ texttimes 75 against a single core CPU solution.
Reference:
Real-time patch-based medical image modality propagation by GPU computing (Eduardo Alcaín, Angel Torrado-Carvajal, Antonio S. Montemayor, Norberto Malpica), In Journal of Real-Time Image Processing, 2016.
Bibtex Entry:
@Article{Alcaín2016,
author="Alca{'i}n, Eduardo
and Torrado-Carvajal, Angel
and Montemayor, Antonio S.
and Malpica, Norberto",
title="Real-time patch-based medical image modality propagation by GPU computing",
journal="Journal of Real-Time Image Processing",
year="2016",
pages="1--12",
abstract="The synthesis of patient data of a certain medical image modality by applying an image processing pipeline starting from other modality is receiving a lot of interest recently, as it allows to save acquisition time and sometimes avoid radiation to the patient. An example of this is the creation of computerized tomography volumes from magnetic resonance imaging data, which can be useful for several applications such as electromagnetic simulations, cranial morphometry and attenuation correction in PET/MR systems. We present a fast patch-based algorithm for this purpose, implemented using graphics processing unit computing techniques and gaining up to                                                                   {$}{$}{backslash}times{$}{$}                                                      {texttimes}                                                15.9 of speedup against a multicore CPU solution and up to about                                                                   {$}{$}{backslash}times{$}{$}                                                      {texttimes}                                                75 against a single core CPU solution.",
issn="1861-8219",
doi="10.1007/s11554-016-0568-0",
url="http://dx.doi.org/10.1007/s11554-016-0568-0"
}