TY - JOUR
T1 - A fast neural network approach to predict lung tumor motion during respiration for radiation therapy applications
AU - Bukovsky, Ivo
AU - Homma, Noriyasu
AU - Ichiji, Kei
AU - Cejnek, Matous
AU - Slama, Matous
AU - Benes, Peter M.
AU - Bila, Jiri
N1 - Publisher Copyright:
© 2015 Ivo Bukovsky et al.
PY - 2015
Y1 - 2015
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=84928313253&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84928313253&partnerID=8YFLogxK
U2 - 10.1155/2015/489679
DO - 10.1155/2015/489679
M3 - Article
C2 - 25893194
AN - SCOPUS:84928313253
VL - 2015
JO - BioMed Research International
JF - BioMed Research International
SN - 2314-6133
M1 - 489679
ER -