Iranian Journal of Medical Physics

Iranian Journal of Medical Physics

Assessment of Different Training Methods in an Artificial Neural Network to Calculate 2D Dose Distribution in Radiotherapy

Document Type : Original Paper

Authors
Mahdi Saeedi-Moghadam 1
Kamal Hadad 2
Banafsheh Zeinali-Rafsanjani 3
Reza Jalli 4
1 Medical Imaging Research Center, Shiraz University of Medical Sciences, Shiraz, Iran
2 Nuclear Engineering Department, School of Mechanical Engineering, Shiraz University, Shiraz, Iran.
3 Medical imaging research center, Shiraz University of medical sciences, Shiraz, Iran
4 Medical imaging research center, Shiraz university of medical sciences, Shiraz, Iran
10.22038/ijmp.2019.39429.1522
Abstract
Introduction: Treatment planning is the most important part of treatment. One of the important entries into treatment planning systems is the beam dose distribution data which maybe typically measured or calculated in a long time. This study aimed at shortening the time of dose calculations using artificial neural network (ANN) and finding the best method of training the ANN using Monte Carlo-N-particle (MCNP5) modeling.
Material and Methods: Back-propagation learning algorithm was applied to design the neural network. The ANN was trained by MCNP5 calculations, and different kinds of methods were tested to determine the best method for training. In order to evaluate the accuracy of the ANN, the beam profiles and percentage depth dose (PDD) in the field size of 15×15 cm2 were anticipated by ANN using various training methods. Eventually, the results were compared with those obtained from the MCNP5 code.
Results: There were good agreements between the results of comparing MCNP5 calculations with experimental measurements. Among the different training methods, Trainbfg had the least error for calculation of PDD and beam profile.
Conclusion: The best training method was found to be Trainbfg, and the results revealed the sufficient accuracy of the modeled ANN.
Keywords
Simulation Training
Radiation Dosage
Radiotherapy Planning Computer-Assisted
Subjects

  1. References

     

    1. Zurada JM. Introduction to Artificial Neural Systems. New edition ed: Jaico Publishing House; 2012.
    2. Kriesel D. A brief introduction to neural networks 2005. Available from: http://www.dkriesel.com/en/science/neural_networks.
    3. Nakamura E. Inflation forecasting using a neural network. economics letters. 2005;86:373-8.
    4. Mano M, Capi G, Tanaka N, Kawahara S. An artificial neural network based robot controller that
    5. Fernandez FG, Santos ISL, Martinez JL, Izquierdo SI, Redondo FL. Use of Artificial Neural Networks to Predict The Business Success or Failure of Start-Up Firms. Artificial neural networks-architecture and applications. 2013:245-56.
    6. Bondarets A, Kreerenko O. Using of Artificial Neural Networks (ANN) for Aircraft Motion Parameters Identification. In: Palmer-Brown D, Draganova C, Pimenidis E, Mouratidis H, editors. Engineering Applications of Neural Networks. Communications in Computer and Information Science. Springer Berlin Heidelberg. 2009;43:246-56.
    7. Nasr MS, Moustafa MAE, Seif HAE, El Kobrosy G. Application of Artificial Neural Network (ANN) for the prediction of EL-AGAMY wastewater treatment plant performance-EGYPT. Alexandria Engineering Journal. 2012;51(1):37-43.
    8. Himmelblau D. Applications of artificial neural networks in chemical engineering. Korean J Chem Eng. 2000;17(4):373-92.
    9. Haykin S. Neural networks and learning machines. 3rd ed: Pearson; 2009.
    10. IAEA. Review of radiation oncology physics: A handbook for teachers and students. IAEA publication; 2012.
    11. Blake SW. Artificial neural network modelling of megavoltage photon dose distributions. Phys Med Biol. 2004;49(12):2515-26.
    12. 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(5):1019-28.
    13. 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. Nuclear Instruments and Methods in Physics Research Research. 2008;266:1085-93.
    14. Kalantzis G, Vasquez-Quino LA, Zalman T, Pratx G, Lei Y. Toward IMRT 2D dose modeling using artificial neural networks: a feasibility study. Med Phys. 2011;38(10):5807-17.
    15. Hadad K, Moshkriz M, Nedaie H. SU‐E‐T‐703: An Artificial Neural Network Treatment Planning System Based on Monte Carlo Calculation for VARIAN 2100C LINAC. Medical Physics. 2011;38(6):3652.
    16. Varian Medical system. Treatment Planning Systems.Available from: www.varian.com.
    17. Saeedimoghadam M, Zeinali B, Kazempour M, Jalli R, Sina S. Monte Carlo Study of Several Concrete Shielding Materials Containing Galena and Borated Minerals. Iranian Journal of Medical Physics. 2017;14(4):241-50.
    18. Zeinali-Rafsanjani B, Faghihi R, Mosleh-Shirazi M, Saeedi-Moghadam M, Jalli R, Sina S. Effect of age-dependent bone electron density on the calculated dose distribution from kilovoltage and megavoltage photon and electron radiotherapy in paediatric MRI-only treatment planning. The British journal of radiology. 2018;91(1081):20170511.
    19. Zeinali-Rafsanjani B, Mosleh-Shirazi MA, Haghighatafshar M, Jalli R, Saeedi-Moghadam M. Assessment of the dose distribution of Minibeam radiotherapy for lung tumors in an anthropomorphic phantom: a feasibility study. Technology and Health Care. 2017;25(4):683-92.
    20. Tayebi M, Shooli FS, Saeedi-Moghadam M. Evaluation of the scattered radiations of lead and lead-free aprons in diagnostic radiology by MCNPX. Technology and Health Care. 2017;25(3):513-20.
    21. Hadad K, Saeedi-Moghadam M, Zeinali-Rafsanjani B. Voxel dosimetry: Comparison of MCNPX and DOSXYZnrc Monte Carlo codes in patient specific phantom calculations. Technology and Health Care. 2017;25(1):29-35.
    22. Kazempour M, Saeedimoghadam M, Shooli FS, Shokrpour N. Assessment of the radiation attenuation properties of several lead free composites by Monte Carlo simulation. Journal of biomedical physics & engineering. 2015;5(2):67.
    23. Zeinali-Rafsanjani B, Faghihi R, Mosleh-Shirazi M, Mosalaei A, Hadad K. Revision of orthovoltage chest wall treatment using Monte Carlo simulations. Technology and Health Care. 2017;25(3):413-24.
    24. Zeinali-Rafsanjani B, Mosleh-Shirazi M, Faghihi R, Karbasi S, Mosalaei A. Fast and accurate Monte Carlo modeling of a kilovoltage X-ray therapy unit using a photon-source approximation for treatment planning in complex media. Journal of Medical Physics/Association of Medical Physicists of India. 2015;40(2):74.
    25. Zeinali Rafsanjani B, Faghihi R. Calculating of Dose Distribution in Tongue Brachytherapy by Different Radioisotopes using Monte Carlo Simulation and Comparing by Experimental Data. Iranian Journal of Medical Physics. 2011;8(2):35-44.
    26. Mathieu R, Martin E, Gschwind R, Makovicka L, Contassot-Vivier S, Bahi J. Calculations of dose distributions using a neural network model. Physics in Medicine & Biology. 2005;50(5):1019.
    27. IAEA. Commissioning of radiotherapy treatment planning systems: Testing for typical external beam treatment techniques. Austria: TECDOC-1583; 2008.
    28. Fraass B, Doppke K, Hunt M, Kutcher G, Starkschall G, Stern R, et al. Quality assurance for clinical radiotherapy treatment planning. Medical Physics. 1998;25(10):1773-829.
Iranian Journal of Medical Physics
Volume 17, Issue 2 - Serial Number 2
March and April 2020
Pages 114-119

  • Receive Date 08 April 2019
  • Revise Date 04 August 2019
  • Accept Date 04 September 2019