-
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,
Jazyk angličtina Země Spojené státy americké
Typ dokumentu časopisecké články, práce podpořená grantem
NLK
Free Medical Journals
od 2013
PubMed Central
od 2013
Europe PubMed Central
od 2013
ProQuest Central
od 2013
Open Access Digital Library
od 2001-01-01
Open Access Digital Library
od 2012-12-04
Open Access Digital Library
od 2013-01-01
CINAHL Plus with Full Text (EBSCOhost)
od 2013-01-01
Medline Complete (EBSCOhost)
od 2013-01-01
Health & Medicine (ProQuest)
od 2013
Wiley-Blackwell Open Access Titles
od 2001
ROAD: Directory of Open Access Scholarly Resources
od 2013
PubMed
25893194
DOI
10.1155/2015/489679
Knihovny.cz E-zdroje
- MeSH
- biologické modely * MeSH
- lidé MeSH
- mechanika dýchání * MeSH
- nádory plic patologie patofyziologie radioterapie MeSH
- neuronové sítě * MeSH
- pohyb těles * MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
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