SU-E-T-703: An Artificial Neural Network Treatment Planning System Based on Monte Carlo Calculation for VARIAN 2100C LINAC

This paper proposes to develop a model-based Monte Carlo method for computationally determining the best mean squared error of training for an artificial neural network with feedforward architecture. It is applied for a particular non-linear classification problem of input/output patterns in a computational environment with abundant data. The Monte Carlo method allows computationally checking that balanced data are much better than non-balanced ones for an artificial neural network to learn by means of supervised learning. The major contribution of this investigation is that, the proposed model can be tested by analogy, considering also the fraud detection problem in credit cards, where the amount of training patterns used are high.

Download Full-text

Evaluation of a treatment planning system developed for clinical boron neutron capture therapy and validation against an independent Monte Carlo dose calculation system

Radiation Oncology ◽

10.1186/s13014-021-01968-2 ◽

2021 ◽

Vol 16 (1) ◽

Author(s):

Naonori Hu ◽

Hiroki Tanaka ◽

Ryo Kakino ◽

Syuushi Yoshikawa ◽

Mamoru Miyao ◽

...

Keyword(s):

Monte Carlo ◽

Treatment Planning ◽

Neutron Capture ◽

Gamma Ray ◽

Dose Calculation ◽

Planning System ◽

Treatment Planning System ◽

Neutron Capture Therapy ◽

Boron Neutron Capture ◽

Monte Carlo Dose Calculation

AbstractBoron neutron capture therapy (BNCT) for the treatment of unresectable, locally advanced, and recurrent carcinoma of the head and neck cancer has been approved by the Japanese government for reimbursement under the national health insurance as of June 2020. A new treatment planning system for clinical BNCT has been developed by Sumitomo Heavy Industries, Ltd. (Sumitomo), NeuCure® Dose Engine. To safely implement this system for clinical use, the simulated neutron flux and gamma ray dose rate inside a water phantom was compared against experimental measurements. Furthermore, to validate and verify the new planning system, the dose distribution inside an anthropomorphic head phantom was compared against a BNCT treatment planning system SERA and an in-house developed Monte Carlo dose calculation program. The simulated results closely matched the experimental results, within 5% for the thermal neutron flux and 10% for the gamma ray dose rate. The dose distribution inside the head phantom closely matched with SERA and the in-house developed dose calculation program, within 3% for the tumour and a difference of 0.3 Gyw for the brain.

Download Full-text

Investigating the Electronic Coefficients in Ne-Hg Mixtures: Comparing a Monte Carlo and Artificial Neural Network Model

Journal of Southwest Jiaotong University ◽

10.35741/issn.0258-2724.55.2.59 ◽

2020 ◽

Vol 55 (2) ◽

Author(s):

Rafid Abbas Ali ◽

Faten Sajet Mater ◽

Asmaa Satar Jeeiad Al-Ragehey

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Monte Carlo Simulation ◽

Monte Carlo ◽

Network Architecture ◽

Vapor Concentration ◽

Neural Network Architecture ◽

Marquardt Algorithm ◽

Artificial Neural ◽

New Applications

Electron coefficients such as drift velocity, ionization coefficient, mean electron energy and Townsend energy for different concentrations of Hg 0.1%, 1%, 10% and 50% in the Ne-Hg mixture at a reduced electric field were calculated using two approaches taking into account inelastic collisions: The Monte Carlo simulation, and an artificial neural network. The effect of Hg vapor concentration on the electron coefficients showed that insignificant additions of mercury atom impurities to Neon, starting from fractions of a percent, affect the characteristics of inelastic processes and discharge, respectively. The aim of this paper is to explore the new applications of neural networks. The Levenberg-Marquardt algorithm and artificial neural network architecture employed was presented in this work to calculate the electron coefficients for different concentrations of Hg in Ne-Hg mixtures. The artificial neural network has been trained with four models (M1, M2, M3, M4), and analysis of the regression between the values of an artificial neural network and Monte Carlo simulation indicates that the M2 output provided the best perfect correlation at 100 Epochs, and the output data obtained was closest to the target data required through using the different stages of artificial neural network development starting with design, training and testing.

Download Full-text