Modeling of the mass attenuation coefficients of X ray beams using deep neural networks (DNN) and NIST database

Attenuation coefficients are essential physical parameters for many applications, such as the calculation of photon penetration and energy deposition to evaluate biological shielding. Estimating these parameters is complex, making it necessary to apply more sophisticated methodologies. The objective...

Full description

Saved in:
Bibliographic Details
Main Authors: GUSTAVO BERNARDES DA SILVA, VIVIANE RODRIGUES BOTELHO, Carla Diniz Lopes Becker, Cassiana Viccari, Thatiane A. Pianoschi
Format: Article
Language:English
Published: Brazilian Radiation Protection Society (Sociedade Brasileira de Proteção Radiológica, SBPR) 2024-04-01
Series:Brazilian Journal of Radiation Sciences
Subjects:
Online Access:https://bjrs.org.br/revista/index.php/REVISTA/article/view/2201
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849715024611770368
author GUSTAVO BERNARDES DA SILVA
VIVIANE RODRIGUES BOTELHO
Carla Diniz Lopes Becker
Cassiana Viccari
Thatiane A. Pianoschi
author_facet GUSTAVO BERNARDES DA SILVA
VIVIANE RODRIGUES BOTELHO
Carla Diniz Lopes Becker
Cassiana Viccari
Thatiane A. Pianoschi
author_sort GUSTAVO BERNARDES DA SILVA
collection DOAJ
description Attenuation coefficients are essential physical parameters for many applications, such as the calculation of photon penetration and energy deposition to evaluate biological shielding. Estimating these parameters is complex, making it necessary to apply more sophisticated methodologies. The objective of the present study was to propose a model for estimating the attenuation coefficients using artificial neural networks. The NIST database was used to estimate the attenuation coefficients in terms of energy and atomic number from a regression problem using two approaches: the proposition of an automated model using the framework Talos and a manual model using Keras. The characteristics of the best model proposed in Talos were applied in manual training via Keras with cross-validation to evaluate the learning curves. The following were also assessed: the comparison of the curves of the attenuation coefficients predicted by the model compared with the reference data and the general comparison of the vectors X and y of the two models discussed. The Talos framework reference model obtained the following values ​​of Loss and MSE error metric: 0.13 and 0.037, respectively. The best model of the manual approach received the following results: 0.19 and 0.08 for the loss function and MSE error metric, respectively. The absolute percentage error (MAE) of the difference in the results between the two models was: 0.065 and 0.044 for the Loss and MSE metrics. Despite applying two distinct propositions, both models had the same difficulties in predicting discontinuities in the physical behavior associated with the attenuation coefficients.
format Article
id doaj-art-a12a2ec5d7fd47d7a7d45d231a6b2fca
institution DOAJ
issn 2319-0612
language English
publishDate 2024-04-01
publisher Brazilian Radiation Protection Society (Sociedade Brasileira de Proteção Radiológica, SBPR)
record_format Article
series Brazilian Journal of Radiation Sciences
spelling doaj-art-a12a2ec5d7fd47d7a7d45d231a6b2fca2025-08-20T03:13:32ZengBrazilian Radiation Protection Society (Sociedade Brasileira de Proteção Radiológica, SBPR)Brazilian Journal of Radiation Sciences2319-06122024-04-01111A (Suppl.)12010.15392/2319-0612.2023.22011819Modeling of the mass attenuation coefficients of X ray beams using deep neural networks (DNN) and NIST databaseGUSTAVO BERNARDES DA SILVA0VIVIANE RODRIGUES BOTELHO1Carla Diniz Lopes Becker2Cassiana Viccari3Thatiane A. Pianoschi4UFCSPAUFCSPAUFCSPAUSP RIBEIRÃO PRETO UFCSPAAttenuation coefficients are essential physical parameters for many applications, such as the calculation of photon penetration and energy deposition to evaluate biological shielding. Estimating these parameters is complex, making it necessary to apply more sophisticated methodologies. The objective of the present study was to propose a model for estimating the attenuation coefficients using artificial neural networks. The NIST database was used to estimate the attenuation coefficients in terms of energy and atomic number from a regression problem using two approaches: the proposition of an automated model using the framework Talos and a manual model using Keras. The characteristics of the best model proposed in Talos were applied in manual training via Keras with cross-validation to evaluate the learning curves. The following were also assessed: the comparison of the curves of the attenuation coefficients predicted by the model compared with the reference data and the general comparison of the vectors X and y of the two models discussed. The Talos framework reference model obtained the following values ​​of Loss and MSE error metric: 0.13 and 0.037, respectively. The best model of the manual approach received the following results: 0.19 and 0.08 for the loss function and MSE error metric, respectively. The absolute percentage error (MAE) of the difference in the results between the two models was: 0.065 and 0.044 for the Loss and MSE metrics. Despite applying two distinct propositions, both models had the same difficulties in predicting discontinuities in the physical behavior associated with the attenuation coefficients.https://bjrs.org.br/revista/index.php/REVISTA/article/view/2201mass attenuation coefficientneural networkdeep learning
spellingShingle GUSTAVO BERNARDES DA SILVA
VIVIANE RODRIGUES BOTELHO
Carla Diniz Lopes Becker
Cassiana Viccari
Thatiane A. Pianoschi
Modeling of the mass attenuation coefficients of X ray beams using deep neural networks (DNN) and NIST database
Brazilian Journal of Radiation Sciences
mass attenuation coefficient
neural network
deep learning
title Modeling of the mass attenuation coefficients of X ray beams using deep neural networks (DNN) and NIST database
title_full Modeling of the mass attenuation coefficients of X ray beams using deep neural networks (DNN) and NIST database
title_fullStr Modeling of the mass attenuation coefficients of X ray beams using deep neural networks (DNN) and NIST database
title_full_unstemmed Modeling of the mass attenuation coefficients of X ray beams using deep neural networks (DNN) and NIST database
title_short Modeling of the mass attenuation coefficients of X ray beams using deep neural networks (DNN) and NIST database
title_sort modeling of the mass attenuation coefficients of x ray beams using deep neural networks dnn and nist database
topic mass attenuation coefficient
neural network
deep learning
url https://bjrs.org.br/revista/index.php/REVISTA/article/view/2201
work_keys_str_mv AT gustavobernardesdasilva modelingofthemassattenuationcoefficientsofxraybeamsusingdeepneuralnetworksdnnandnistdatabase
AT vivianerodriguesbotelho modelingofthemassattenuationcoefficientsofxraybeamsusingdeepneuralnetworksdnnandnistdatabase
AT carladinizlopesbecker modelingofthemassattenuationcoefficientsofxraybeamsusingdeepneuralnetworksdnnandnistdatabase
AT cassianaviccari modelingofthemassattenuationcoefficientsofxraybeamsusingdeepneuralnetworksdnnandnistdatabase
AT thatianeapianoschi modelingofthemassattenuationcoefficientsofxraybeamsusingdeepneuralnetworksdnnandnistdatabase