Modeling of radiation dose of human head during CT scanning using neural networks

In this study the authors present the method for determination of exposure dose on human head during computer tomography (CT) scanning procedure. The method is based on the use of the feed-forward neural network (FFNN) model to predict the exposure dose on human head. The neural network with Levenberg-Marquardt learning is constructed. The training data are obtained using the Monte Carlo method simulation. The simulation is performed by generating random numbers for determination of photon direction and for quantification of interaction between X-ray photon and head tissue. Spectra of photon energy is used for 3DCT scanner, X-ray tube Model XRS-125-7K-P. The FFNN predicted values are in accordance with the values obtained by the simulation with correlation coefficient around 0.99.