Journal of Radiation Protection and Research

The Korean Association for Radiation Protection (대한방사선방어학회)
권호 표지
DOI QR코드

DOI QR Code

A Feasibility Study on Using Neural Network for Dose Calculation in Radiation Treatment

방사선 치료 선량 계산을 위한 신경회로망의 적용 타당성

  • Received : 2015.01.16
  • Accepted : 2015.02.24
  • Published : 2015.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

Dose calculations which are a crucial requirement for radiotherapy treatment planning systems require accuracy and rapid calculations. The conventional radiotherapy treatment planning dose algorithms are rapid but lack precision. Monte Carlo methods are time consuming but the most accurate. The new combined system that Monte Carlo methods calculate part of interesting domain and the rest is calculated by neural can calculate the dose distribution rapidly and accurately. The preliminary study showed that neural networks can map functions which contain discontinuous points and inflection points which the dose distributions in inhomogeneous media also have. Performance results between scaled conjugated gradient algorithm and Levenberg-Marquardt algorithm which are used for training the neural network with a different number of neurons were compared. Finally, the dose distributions of homogeneous phantom calculated by a commercialized treatment planning system were used as training data of the neural network. In the case of homogeneous phantom;the mean squared error of percent depth dose was 0.00214. Further works are programmed to develop the neural network model for 3-dimensinal dose calculations in homogeneous phantoms and inhomogeneous phantoms.

방사선치료계획장치의 핵심기술인 선량분포 계산은 빠르고 정확함을 요구한다. 기존 상용화된 치료계획장치의 선량 계산 방법은 빠르지만 정확성이 부족하고, 몬테칼로 방법은 시뮬레이션 시간과다 문제가 있다. 관심영역의 일부만 몬테칼로 방법이 계산하고 나머지 영역은 비선형함수사상 능력이 뛰어난 신경회로망이 계산하는 시스템은 상대적으로 빠르고 정확한 선량분포를 계산해낼 수 있다. 비균질 매질의 선량분포에 나타나는 불연속점과 변곡점의 특성을 신경회로망이 학습가능 하다는 것을 사전 작업을 통해 확인하였다. 이때 사용된 신경회로망은 Feedforward Multi-Layer Perceptron에 Scaled Conjugated Gradient 알고리즘과 Levenberg-Marquardt 알고리즘으로 각각 학습하여 성능비교를 하였고, 은닉층의 뉴런 개수에 따른 성능비교도 하였다. 마지막으로 균질매질의 팬텀에 대해 상용 치료계획장치의 선량계산 알고리즘으로 계산한 선량분포를 사전작업을 통해 확인된 신경회로망에 학습하여 깊이선량율의 평균제곱오차가 0.00214인 결과를 보여주었다. 균질 및 비균질 매질의 팬텀에 대한 3차원 선량분포를 계산하는 신경회로망 모델 개발 연구가 추가로 진행될 것이다.

Keywords

References

  1. Demarco JJ, Chetty IJ, Solberg TD. A Monte Carlo tutorial and the application for radiotherapy treatment planning. Med Dosim. 2002;27(1):43-50. https://doi.org/10.1016/S0958-3947(02)00087-0
  2. Zhao Y, Mcakenzle M, Kirkby C, Fallone BG. Monte Carlo calculation of helical tomotherapy dose delivery. Med Phys. 2008;35(8):3491-3500. https://doi.org/10.1118/1.2948409
  3. Wu X, Zhu Y. A neural network regression model for relative dose computation. Phys Med Biol. 2000;45:913-922. https://doi.org/10.1088/0031-9155/45/4/307
  4. Blake SW. Artificial neural network modeling of megavoltage photon dose distributions. Phys Med Biol.2004;49:2515-2526. https://doi.org/10.1088/0031-9155/49/12/004
  5. Mathieu R, Martin E, Gschwind R, Makovicka L, Contassot-Vivier S, Bahi J. Calculations of dose distributions using a neural network model. Phys Med Biol. 2005;50:1019-1028. https://doi.org/10.1088/0031-9155/50/5/024
  6. Vasseur A, Makovicka L, Martin E, Sauget M, Contassot-Vivier S, Bahi J. Dose calculations using artificial neural networks: A feasibility study for photon beams. Nucl Instrum Meth B. 2008;266:1085-1093. https://doi.org/10.1016/j.nimb.2008.01.072
  7. Moller M. A scaled conjugate gradient algorithm for fast supervised learning. Neural Networks. 1993;6:525-533. https://doi.org/10.1016/S0893-6080(05)80056-5
  8. Hagan MT, Menhaj M. Training feedforward networks with the Marquardt Algorithms, IEEE T Neural Networks. 1994;5(6):989-993. https://doi.org/10.1109/72.329697

Cited by

  1. Independent dose verification system with Monte Carlo simulations using TOPAS for passive scattering proton therapy at the National Cancer Center in Korea vol.62, pp.19, 2017, https://doi.org/10.1088/1361-6560/aa8663