Improving Compton camera imaging of multi-energy radioactive sources by using machine learning algorithms for event selection

Event selection and background reduction for Compton camera imaging of multi-energy radioactive sources has been performed by employing neural networks. A Compton camera prototype with detectors made of LaBr<inf>3</inf> crystals coupled to silicon photomultiplier arrays was used to acqui...

ver descrição completa

Detalhes bibliográficos
Autores: Pérez-Curbelo, J., Roser, J., Muñoz, Enrique, Barrientos, Luis, Sanz, Verónica, Llosá, Gabriela
Formato: artículo
Estado:Versión publicada
Fecha de publicación:2025
País:España
Recursos:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:dnet:digitalcsic_::2e358fad5d2de4032fbf41940e2f9c38
Acesso em linha:http://hdl.handle.net/10261/430705
https://api.elsevier.com/content/abstract/scopus_id/85204640347
Access Level:acceso abierto
Palavra-chave:Compton cameras imaging
Event selection
Image reconstruction
Neural networks
id ES_5fb280d48ffb75ef3adaf333978fbe7f
oai_identifier_str oai:dnet:digitalcsic_::2e358fad5d2de4032fbf41940e2f9c38
network_acronym_str ES
network_name_str España
repository_id_str
spelling Improving Compton camera imaging of multi-energy radioactive sources by using machine learning algorithms for event selectionPérez-Curbelo, J.Roser, J.Muñoz, EnriqueBarrientos, LuisSanz, VerónicaLlosá, GabrielaCompton cameras imagingEvent selectionImage reconstructionNeural networksEvent selection and background reduction for Compton camera imaging of multi-energy radioactive sources has been performed by employing neural networks. A Compton camera prototype with detectors made of LaBr<inf>3</inf> crystals coupled to silicon photomultiplier arrays was used to acquire experimental data from a circular array of <sup>22</sup>Na sources. The prototype and two arrays of <sup>22</sup>Na sources were simulated with GATE v8.2 Monte Carlo code, to obtain data for neural network training. Neural network models were trained on simulated data for event classification. The optimum models were found by using Weights & Biases platform tools. The trained models were used to classify simulated and real data for selecting signal events and rejecting background prior to image reconstruction. The models performed well on simulated data. The image obtained with experimental data showed an improvement with respect to event selection with energy cuts. The method is promising for Compton camera imaging of multi-energy radioactive sources.This work has received funding from Ministerio de Ciencia e Innovación, Agencia Estatal de Investigación (PID2019-110657RB-I00) and from the Generalitat Valenciana, Spain (GRISOLIAP/2021/099).Peer reviewedElsevierMinisterio de Ciencia e Innovación (España)Agencia Estatal de Investigación (España)Generalitat ValencianaPérez-Curbelo, J. [0000-0002-8939-766X]Consejo Superior de Investigaciones Científicas [https://ror.org/02gfc7t72]202620262025info:eu-repo/semantics/articlehttp://purl.org/coar/resource_type/c_6501Publisher's versioninfo:eu-repo/semantics/publishedVersionhttp://hdl.handle.net/10261/430705https://api.elsevier.com/content/abstract/scopus_id/85204640347reponame:DIGITAL.CSIC. Repositorio Institucional del CSICinstname:Consejo Superior de Investigaciones Científicas (CSIC)Inglés#PLACEHOLDER_PARENT_METADATA_VALUE#info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/PID2019-110657RB-I00https://doi.org/10.1016/j.radphyschem.2024.112166Síinfo:eu-repo/semantics/openAccessoai:dnet:digitalcsic_::2e358fad5d2de4032fbf41940e2f9c382026-05-22T06:33:51Z
dc.title.none.fl_str_mv Improving Compton camera imaging of multi-energy radioactive sources by using machine learning algorithms for event selection
title Improving Compton camera imaging of multi-energy radioactive sources by using machine learning algorithms for event selection
spellingShingle Improving Compton camera imaging of multi-energy radioactive sources by using machine learning algorithms for event selection
Pérez-Curbelo, J.
Compton cameras imaging
Event selection
Image reconstruction
Neural networks
title_short Improving Compton camera imaging of multi-energy radioactive sources by using machine learning algorithms for event selection
title_full Improving Compton camera imaging of multi-energy radioactive sources by using machine learning algorithms for event selection
title_fullStr Improving Compton camera imaging of multi-energy radioactive sources by using machine learning algorithms for event selection
title_full_unstemmed Improving Compton camera imaging of multi-energy radioactive sources by using machine learning algorithms for event selection
title_sort Improving Compton camera imaging of multi-energy radioactive sources by using machine learning algorithms for event selection
dc.creator.none.fl_str_mv Pérez-Curbelo, J.
Roser, J.
Muñoz, Enrique
Barrientos, Luis
Sanz, Verónica
Llosá, Gabriela
author Pérez-Curbelo, J.
author_facet Pérez-Curbelo, J.
Roser, J.
Muñoz, Enrique
Barrientos, Luis
Sanz, Verónica
Llosá, Gabriela
author_role author
author2 Roser, J.
Muñoz, Enrique
Barrientos, Luis
Sanz, Verónica
Llosá, Gabriela
author2_role author
author
author
author
author
dc.contributor.none.fl_str_mv Ministerio de Ciencia e Innovación (España)
Agencia Estatal de Investigación (España)
Generalitat Valenciana
Pérez-Curbelo, J. [0000-0002-8939-766X]
Consejo Superior de Investigaciones Científicas [https://ror.org/02gfc7t72]
dc.subject.none.fl_str_mv Compton cameras imaging
Event selection
Image reconstruction
Neural networks
topic Compton cameras imaging
Event selection
Image reconstruction
Neural networks
description Event selection and background reduction for Compton camera imaging of multi-energy radioactive sources has been performed by employing neural networks. A Compton camera prototype with detectors made of LaBr<inf>3</inf> crystals coupled to silicon photomultiplier arrays was used to acquire experimental data from a circular array of <sup>22</sup>Na sources. The prototype and two arrays of <sup>22</sup>Na sources were simulated with GATE v8.2 Monte Carlo code, to obtain data for neural network training. Neural network models were trained on simulated data for event classification. The optimum models were found by using Weights & Biases platform tools. The trained models were used to classify simulated and real data for selecting signal events and rejecting background prior to image reconstruction. The models performed well on simulated data. The image obtained with experimental data showed an improvement with respect to event selection with energy cuts. The method is promising for Compton camera imaging of multi-energy radioactive sources.
publishDate 2025
dc.date.none.fl_str_mv 2025
2026
2026
dc.type.none.fl_str_mv info:eu-repo/semantics/article
http://purl.org/coar/resource_type/c_6501
Publisher's version
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10261/430705
https://api.elsevier.com/content/abstract/scopus_id/85204640347
url http://hdl.handle.net/10261/430705
https://api.elsevier.com/content/abstract/scopus_id/85204640347
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv #PLACEHOLDER_PARENT_METADATA_VALUE#
info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/PID2019-110657RB-I00
https://doi.org/10.1016/j.radphyschem.2024.112166
Sí
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:DIGITAL.CSIC. Repositorio Institucional del CSIC
instname:Consejo Superior de Investigaciones Científicas (CSIC)
instname_str Consejo Superior de Investigaciones Científicas (CSIC)
reponame_str DIGITAL.CSIC. Repositorio Institucional del CSIC
collection DIGITAL.CSIC. Repositorio Institucional del CSIC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869409226452893696
score 15.812429

Registos relacionados