Detail
Článek
Článek online
FT
Medvik - BMČ
  • Je něco špatně v tomto záznamu ?

A fast neural network approach to predict lung tumor motion during respiration for radiation therapy applications

I. Bukovsky, N. Homma, K. Ichiji, M. Cejnek, M. Slama, PM. Benes, J. Bila,

. 2015 ; 2015 (-) : 489679. [pub] 20150329

Jazyk angličtina Země Spojené státy americké

Typ dokumentu časopisecké články, práce podpořená grantem

Perzistentní odkaz   https://www.medvik.cz/link/bmc16010301

During radiotherapy treatment for thoracic and abdomen cancers, for example, lung cancers, respiratory motion moves the target tumor and thus badly affects the accuracy of radiation dose delivery into the target. A real-time image-guided technique can be used to monitor such lung tumor motion for accurate dose delivery, but the system latency up to several hundred milliseconds for repositioning the radiation beam also affects the accuracy. In order to compensate the latency, neural network prediction technique with real-time retraining can be used. We have investigated real-time prediction of 3D time series of lung tumor motion on a classical linear model, perceptron model, and on a class of higher-order neural network model that has more attractive attributes regarding its optimization convergence and computational efficiency. The implemented static feed-forward neural architectures are compared when using gradient descent adaptation and primarily the Levenberg-Marquardt batch algorithm as the ones of the most common and most comprehensible learning algorithms. The proposed technique resulted in fast real-time retraining, so the total computational time on a PC platform was equal to or even less than the real treatment time. For one-second prediction horizon, the proposed techniques achieved accuracy less than one millimeter of 3D mean absolute error in one hundred seconds of total treatment time.

Citace poskytuje Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc16010301
003      
CZ-PrNML
005      
20160408112315.0
007      
ta
008      
160408s2015 xxu f 000 0|eng||
009      
AR
024    7_
$a 10.1155/2015/489679 $2 doi
024    7_
$a 10.1155/2015/489679 $2 doi
035    __
$a (PubMed)25893194
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a xxu
100    1_
$a Bukovsky, Ivo $u Department of Instrumentation and Control Engineering, Faculty of Mechanical Engineering, Czech Technical University in Prague, 16607 Prague, Czech Republic.
245    12
$a A fast neural network approach to predict lung tumor motion during respiration for radiation therapy applications / $c I. Bukovsky, N. Homma, K. Ichiji, M. Cejnek, M. Slama, PM. Benes, J. Bila,
520    9_
$a During radiotherapy treatment for thoracic and abdomen cancers, for example, lung cancers, respiratory motion moves the target tumor and thus badly affects the accuracy of radiation dose delivery into the target. A real-time image-guided technique can be used to monitor such lung tumor motion for accurate dose delivery, but the system latency up to several hundred milliseconds for repositioning the radiation beam also affects the accuracy. In order to compensate the latency, neural network prediction technique with real-time retraining can be used. We have investigated real-time prediction of 3D time series of lung tumor motion on a classical linear model, perceptron model, and on a class of higher-order neural network model that has more attractive attributes regarding its optimization convergence and computational efficiency. The implemented static feed-forward neural architectures are compared when using gradient descent adaptation and primarily the Levenberg-Marquardt batch algorithm as the ones of the most common and most comprehensible learning algorithms. The proposed technique resulted in fast real-time retraining, so the total computational time on a PC platform was equal to or even less than the real treatment time. For one-second prediction horizon, the proposed techniques achieved accuracy less than one millimeter of 3D mean absolute error in one hundred seconds of total treatment time.
650    _2
$a lidé $7 D006801
650    _2
$a nádory plic $x patologie $x patofyziologie $x radioterapie $7 D008175
650    12
$a biologické modely $7 D008954
650    12
$a pohyb těles $7 D009038
650    12
$a neuronové sítě $7 D016571
650    12
$a mechanika dýchání $7 D015656
655    _2
$a časopisecké články $7 D016428
655    _2
$a práce podpořená grantem $7 D013485
700    1_
$a Homma, Noriyasu $u Department of Radiological Imaging and Informatics, Graduate School of Medicine, Tohoku University, Sendai 980-8575, Japan.
700    1_
$a Ichiji, Kei $u Division on Advanced Information Technology, Yoshizawa Laboratory, Tohoku University, Sendai 980-8578, Japan.
700    1_
$a Cejnek, Matous $u Department of Instrumentation and Control Engineering, Faculty of Mechanical Engineering, Czech Technical University in Prague, 16607 Prague, Czech Republic.
700    1_
$a Slama, Matous $u Department of Instrumentation and Control Engineering, Faculty of Mechanical Engineering, Czech Technical University in Prague, 16607 Prague, Czech Republic.
700    1_
$a Benes, Peter M $u Department of Instrumentation and Control Engineering, Faculty of Mechanical Engineering, Czech Technical University in Prague, 16607 Prague, Czech Republic.
700    1_
$a Bila, Jiri $u Department of Instrumentation and Control Engineering, Faculty of Mechanical Engineering, Czech Technical University in Prague, 16607 Prague, Czech Republic.
773    0_
$w MED00182164 $t BioMed research international $x 2314-6141 $g Roč. 2015, č. - (2015), s. 489679
856    41
$u https://pubmed.ncbi.nlm.nih.gov/25893194 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y a $z 0
990    __
$a 20160408 $b ABA008
991    __
$a 20160408112353 $b ABA008
999    __
$a ok $b bmc $g 1113730 $s 934669
BAS    __
$a 3
BAS    __
$a PreBMC
BMC    __
$a 2015 $b 2015 $c - $d 489679 $e 20150329 $i 2314-6141 $m BioMed research international $n Biomed Res Int $x MED00182164
LZP    __
$a Pubmed-20160408

Najít záznam

Citační ukazatele

Nahrávání dat ...

Možnosti archivace

Nahrávání dat ...