Using ANN for thermal neutron shield designing for BNCT treatment room

Abstract

Occupational radiation protection should be applied to the design of treatment rooms for various radiation therapy techniques, including BNCT, where escaping particles from the beam port of the beam shaping assembly (BSA) may reach the walls or penetrate through the entrance door. The focus of the present study is to design an alternative shielding material, other than the conventional material of lead, that can be considered as the material used in the door and be able to effectively absorb the BSA neutrons which have slowed down to the thermal energy range of $$< 1$$ < 1 eV after passing through the walls and the maze of the room. To this aim, a thermal neutron shield, composed of polymer composite and polyethylene, has been simulated using the Geant4 Monte Carlo code. The neutron flux and dose values were predicted using an artificial neural network (ANN), eliminating the need for time-consuming Monte Carlo simulations in all possible suggestions. Additionally, this technique enables simultaneous optimization of the parameters involved, which is more effective than the traditional sequential and separate optimization process. The results indicated that the optimized shielding material, chosen through ANN calculations that determined the appropriate thickness and weight percent of its compositions, can decrease the dose behind the door to lower than the allowable limit for occupational exposure. The stability of ANN was tested by considering uncertainties with the Gaussian distributions of random numbers to the testing data. The results are promising as they indicate that ANNs could be used as a reliable tool for accurately predicting the dosimetric results, providing a drastically powerful alternative approach to the time-consuming Monte Carlo simulations.