From nuclear track characterization to machine learning based image classification in neutron autoradiography for boron neutron capture therapy

Autores
Viglietti, Julia S.; Espain, Maria Sol; Díaz, Rodrigo Fernando; Nieto, Luis Agustin; Szewc, Manuel; Bernardi, Guillermo Carlos; Rodríguez, Luis M.; Fregenal, Daniel Eduardo; Saint Martin, María Laura Gisela; Portu, Agustina Mariana
Año de publicación
2023
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Knowledge of the 10B microdistribution is of great relevance in BNCT studies. Since 10B concentration assesment through neutron autoradiography depends on the correct quantification of tracks in a nuclear track detector, image acquisition and processing conditions should be controlled and verified, in order to obtain accurate results to be applied in the frame of BNCT. With this aim, an image verification process was proposed, based on parameters extracted from the quantified nuclear tracks. Track characterization was performed by selecting a set of morphological and pixel-intensity uniformity parameters from the quantified objects (area, diameter, roundness, aspect ratio, heterogeneity and clumpiness). Their distributions were studied, leading to the observation of varying behaviours in images generated by different samples and acquisition conditions. The distributions corresponding to samples coming from the BNC reaction showed similar attributes in each analyzed parameter, proving to be robust to the experimental process, but sensitive to light and focus conditions. Considering those observations, a manual feature extraction was performed as a pre-processing step. A Support Vector Machine (SVM) and a fully dense Neural Network (NN) were optimized, trained, and tested. The final performance metrics were similar for both models: 93%-93% for the SVM, vs 94%-95% for the NN in accuracy and precision respectively. Based on the distribution of the predicted class probabilities, the latter had a better capacity to reject inadequate images, so the NN was selected to perform the image verification step prior to quantification. The trained NN was able to correctly classify the images regardless of their track density. The exhaustive characterization of the nuclear tracks provided new knowledge related to the autoradiographic images generation. The inclusion of machine learning in the analysis workflow proves to optimize the boron determination process and paves the way for further applications in the field of boron imaging.
Fil: Viglietti, Julia S.. Comisión Nacional de Energía Atómica. Gerencia de Área de Aplicaciones de la Tecnología Nuclear. Departamento de Radiobiología; Argentina
Fil: Espain, Maria Sol. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad Nacional de San Martín. Escuela de Ciencia y Tecnología; Argentina. Comisión Nacional de Energía Atómica. Gerencia de Área de Aplicaciones de la Tecnología Nuclear. Departamento de Radiobiología; Argentina
Fil: Díaz, Rodrigo Fernando. Universidad Nacional de San Martín. Escuela de Ciencia y Tecnología. Centro Internacional de Estudios Avanzados; Argentina. Consejo Nacional de Investigaciones Cientificas y Tecnicas. Instituto de Ciencias Fisicas. - Universidad Nacional de San Martin. Instituto de Ciencias Fisicas.; Argentina
Fil: Nieto, Luis Agustin. Universidad Nacional de San Martín. Escuela de Ciencia y Tecnología. Centro Internacional de Estudios Avanzados; Argentina. Consejo Nacional de Investigaciones Cientificas y Tecnicas. Instituto de Ciencias Fisicas. - Universidad Nacional de San Martin. Instituto de Ciencias Fisicas.; Argentina. Comisión Nacional de Energía Atómica. Centro Atómico Constituyentes; Argentina
Fil: Szewc, Manuel. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. University of Cincinnati; Estados Unidos
Fil: Bernardi, Guillermo Carlos. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Comisión Nacional de Energía Atómica. Centro Atómico Bariloche; Argentina
Fil: Rodríguez, Luis M.. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Fil: Fregenal, Daniel Eduardo. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Comisión Nacional de Energía Atómica. Centro Atómico Bariloche; Argentina
Fil: Saint Martin, María Laura Gisela. Comisión Nacional de Energía Atómica. Gerencia de Área de Aplicaciones de la Tecnología Nuclear. Departamento de Radiobiología; Argentina
Fil: Portu, Agustina Mariana. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad Nacional de San Martín. Escuela de Ciencia y Tecnología; Argentina. Comisión Nacional de Energía Atómica. Gerencia de Área de Aplicaciones de la Tecnología Nuclear. Departamento de Radiobiología; Argentina
Materia
AUTORADIOGRAPHY
NEUTRON
MACHINE LEARNING
NUCLEAR TRACKS
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/222662

id CONICETDig_67f815e1cd580c752f43fc8f3cf4d574
oai_identifier_str oai:ri.conicet.gov.ar:11336/222662
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling From nuclear track characterization to machine learning based image classification in neutron autoradiography for boron neutron capture therapyViglietti, Julia S.Espain, Maria SolDíaz, Rodrigo FernandoNieto, Luis AgustinSzewc, ManuelBernardi, Guillermo CarlosRodríguez, Luis M.Fregenal, Daniel EduardoSaint Martin, María Laura GiselaPortu, Agustina MarianaAUTORADIOGRAPHYNEUTRONMACHINE LEARNINGNUCLEAR TRACKShttps://purl.org/becyt/ford/1.3https://purl.org/becyt/ford/1Knowledge of the 10B microdistribution is of great relevance in BNCT studies. Since 10B concentration assesment through neutron autoradiography depends on the correct quantification of tracks in a nuclear track detector, image acquisition and processing conditions should be controlled and verified, in order to obtain accurate results to be applied in the frame of BNCT. With this aim, an image verification process was proposed, based on parameters extracted from the quantified nuclear tracks. Track characterization was performed by selecting a set of morphological and pixel-intensity uniformity parameters from the quantified objects (area, diameter, roundness, aspect ratio, heterogeneity and clumpiness). Their distributions were studied, leading to the observation of varying behaviours in images generated by different samples and acquisition conditions. The distributions corresponding to samples coming from the BNC reaction showed similar attributes in each analyzed parameter, proving to be robust to the experimental process, but sensitive to light and focus conditions. Considering those observations, a manual feature extraction was performed as a pre-processing step. A Support Vector Machine (SVM) and a fully dense Neural Network (NN) were optimized, trained, and tested. The final performance metrics were similar for both models: 93%-93% for the SVM, vs 94%-95% for the NN in accuracy and precision respectively. Based on the distribution of the predicted class probabilities, the latter had a better capacity to reject inadequate images, so the NN was selected to perform the image verification step prior to quantification. The trained NN was able to correctly classify the images regardless of their track density. The exhaustive characterization of the nuclear tracks provided new knowledge related to the autoradiographic images generation. The inclusion of machine learning in the analysis workflow proves to optimize the boron determination process and paves the way for further applications in the field of boron imaging.Fil: Viglietti, Julia S.. Comisión Nacional de Energía Atómica. Gerencia de Área de Aplicaciones de la Tecnología Nuclear. Departamento de Radiobiología; ArgentinaFil: Espain, Maria Sol. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad Nacional de San Martín. Escuela de Ciencia y Tecnología; Argentina. Comisión Nacional de Energía Atómica. Gerencia de Área de Aplicaciones de la Tecnología Nuclear. Departamento de Radiobiología; ArgentinaFil: Díaz, Rodrigo Fernando. Universidad Nacional de San Martín. Escuela de Ciencia y Tecnología. Centro Internacional de Estudios Avanzados; Argentina. Consejo Nacional de Investigaciones Cientificas y Tecnicas. Instituto de Ciencias Fisicas. - Universidad Nacional de San Martin. Instituto de Ciencias Fisicas.; ArgentinaFil: Nieto, Luis Agustin. Universidad Nacional de San Martín. Escuela de Ciencia y Tecnología. Centro Internacional de Estudios Avanzados; Argentina. Consejo Nacional de Investigaciones Cientificas y Tecnicas. Instituto de Ciencias Fisicas. - Universidad Nacional de San Martin. Instituto de Ciencias Fisicas.; Argentina. Comisión Nacional de Energía Atómica. Centro Atómico Constituyentes; ArgentinaFil: Szewc, Manuel. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. University of Cincinnati; Estados UnidosFil: Bernardi, Guillermo Carlos. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Comisión Nacional de Energía Atómica. Centro Atómico Bariloche; ArgentinaFil: Rodríguez, Luis M.. Consejo Nacional de Investigaciones Científicas y Técnicas; ArgentinaFil: Fregenal, Daniel Eduardo. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Comisión Nacional de Energía Atómica. Centro Atómico Bariloche; ArgentinaFil: Saint Martin, María Laura Gisela. Comisión Nacional de Energía Atómica. Gerencia de Área de Aplicaciones de la Tecnología Nuclear. Departamento de Radiobiología; ArgentinaFil: Portu, Agustina Mariana. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad Nacional de San Martín. Escuela de Ciencia y Tecnología; Argentina. Comisión Nacional de Energía Atómica. Gerencia de Área de Aplicaciones de la Tecnología Nuclear. Departamento de Radiobiología; ArgentinaPublic Library of Science2023-12info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/222662Viglietti, Julia S.; Espain, Maria Sol; Díaz, Rodrigo Fernando; Nieto, Luis Agustin; Szewc, Manuel; et al.; From nuclear track characterization to machine learning based image classification in neutron autoradiography for boron neutron capture therapy; Public Library of Science; Plos One; 18; 12; e0293891; 12-2023; 1-231932-6203CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0293891info:eu-repo/semantics/altIdentifier/doi/10.1371/journal.pone.0293891info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-29T10:20:53Zoai:ri.conicet.gov.ar:11336/222662instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-29 10:20:53.747CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv From nuclear track characterization to machine learning based image classification in neutron autoradiography for boron neutron capture therapy
title From nuclear track characterization to machine learning based image classification in neutron autoradiography for boron neutron capture therapy
spellingShingle From nuclear track characterization to machine learning based image classification in neutron autoradiography for boron neutron capture therapy
Viglietti, Julia S.
AUTORADIOGRAPHY
NEUTRON
MACHINE LEARNING
NUCLEAR TRACKS
title_short From nuclear track characterization to machine learning based image classification in neutron autoradiography for boron neutron capture therapy
title_full From nuclear track characterization to machine learning based image classification in neutron autoradiography for boron neutron capture therapy
title_fullStr From nuclear track characterization to machine learning based image classification in neutron autoradiography for boron neutron capture therapy
title_full_unstemmed From nuclear track characterization to machine learning based image classification in neutron autoradiography for boron neutron capture therapy
title_sort From nuclear track characterization to machine learning based image classification in neutron autoradiography for boron neutron capture therapy
dc.creator.none.fl_str_mv Viglietti, Julia S.
Espain, Maria Sol
Díaz, Rodrigo Fernando
Nieto, Luis Agustin
Szewc, Manuel
Bernardi, Guillermo Carlos
Rodríguez, Luis M.
Fregenal, Daniel Eduardo
Saint Martin, María Laura Gisela
Portu, Agustina Mariana
author Viglietti, Julia S.
author_facet Viglietti, Julia S.
Espain, Maria Sol
Díaz, Rodrigo Fernando
Nieto, Luis Agustin
Szewc, Manuel
Bernardi, Guillermo Carlos
Rodríguez, Luis M.
Fregenal, Daniel Eduardo
Saint Martin, María Laura Gisela
Portu, Agustina Mariana
author_role author
author2 Espain, Maria Sol
Díaz, Rodrigo Fernando
Nieto, Luis Agustin
Szewc, Manuel
Bernardi, Guillermo Carlos
Rodríguez, Luis M.
Fregenal, Daniel Eduardo
Saint Martin, María Laura Gisela
Portu, Agustina Mariana
author2_role author
author
author
author
author
author
author
author
author
dc.subject.none.fl_str_mv AUTORADIOGRAPHY
NEUTRON
MACHINE LEARNING
NUCLEAR TRACKS
topic AUTORADIOGRAPHY
NEUTRON
MACHINE LEARNING
NUCLEAR TRACKS
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.3
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv Knowledge of the 10B microdistribution is of great relevance in BNCT studies. Since 10B concentration assesment through neutron autoradiography depends on the correct quantification of tracks in a nuclear track detector, image acquisition and processing conditions should be controlled and verified, in order to obtain accurate results to be applied in the frame of BNCT. With this aim, an image verification process was proposed, based on parameters extracted from the quantified nuclear tracks. Track characterization was performed by selecting a set of morphological and pixel-intensity uniformity parameters from the quantified objects (area, diameter, roundness, aspect ratio, heterogeneity and clumpiness). Their distributions were studied, leading to the observation of varying behaviours in images generated by different samples and acquisition conditions. The distributions corresponding to samples coming from the BNC reaction showed similar attributes in each analyzed parameter, proving to be robust to the experimental process, but sensitive to light and focus conditions. Considering those observations, a manual feature extraction was performed as a pre-processing step. A Support Vector Machine (SVM) and a fully dense Neural Network (NN) were optimized, trained, and tested. The final performance metrics were similar for both models: 93%-93% for the SVM, vs 94%-95% for the NN in accuracy and precision respectively. Based on the distribution of the predicted class probabilities, the latter had a better capacity to reject inadequate images, so the NN was selected to perform the image verification step prior to quantification. The trained NN was able to correctly classify the images regardless of their track density. The exhaustive characterization of the nuclear tracks provided new knowledge related to the autoradiographic images generation. The inclusion of machine learning in the analysis workflow proves to optimize the boron determination process and paves the way for further applications in the field of boron imaging.
Fil: Viglietti, Julia S.. Comisión Nacional de Energía Atómica. Gerencia de Área de Aplicaciones de la Tecnología Nuclear. Departamento de Radiobiología; Argentina
Fil: Espain, Maria Sol. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad Nacional de San Martín. Escuela de Ciencia y Tecnología; Argentina. Comisión Nacional de Energía Atómica. Gerencia de Área de Aplicaciones de la Tecnología Nuclear. Departamento de Radiobiología; Argentina
Fil: Díaz, Rodrigo Fernando. Universidad Nacional de San Martín. Escuela de Ciencia y Tecnología. Centro Internacional de Estudios Avanzados; Argentina. Consejo Nacional de Investigaciones Cientificas y Tecnicas. Instituto de Ciencias Fisicas. - Universidad Nacional de San Martin. Instituto de Ciencias Fisicas.; Argentina
Fil: Nieto, Luis Agustin. Universidad Nacional de San Martín. Escuela de Ciencia y Tecnología. Centro Internacional de Estudios Avanzados; Argentina. Consejo Nacional de Investigaciones Cientificas y Tecnicas. Instituto de Ciencias Fisicas. - Universidad Nacional de San Martin. Instituto de Ciencias Fisicas.; Argentina. Comisión Nacional de Energía Atómica. Centro Atómico Constituyentes; Argentina
Fil: Szewc, Manuel. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. University of Cincinnati; Estados Unidos
Fil: Bernardi, Guillermo Carlos. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Comisión Nacional de Energía Atómica. Centro Atómico Bariloche; Argentina
Fil: Rodríguez, Luis M.. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Fil: Fregenal, Daniel Eduardo. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Comisión Nacional de Energía Atómica. Centro Atómico Bariloche; Argentina
Fil: Saint Martin, María Laura Gisela. Comisión Nacional de Energía Atómica. Gerencia de Área de Aplicaciones de la Tecnología Nuclear. Departamento de Radiobiología; Argentina
Fil: Portu, Agustina Mariana. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad Nacional de San Martín. Escuela de Ciencia y Tecnología; Argentina. Comisión Nacional de Energía Atómica. Gerencia de Área de Aplicaciones de la Tecnología Nuclear. Departamento de Radiobiología; Argentina
description Knowledge of the 10B microdistribution is of great relevance in BNCT studies. Since 10B concentration assesment through neutron autoradiography depends on the correct quantification of tracks in a nuclear track detector, image acquisition and processing conditions should be controlled and verified, in order to obtain accurate results to be applied in the frame of BNCT. With this aim, an image verification process was proposed, based on parameters extracted from the quantified nuclear tracks. Track characterization was performed by selecting a set of morphological and pixel-intensity uniformity parameters from the quantified objects (area, diameter, roundness, aspect ratio, heterogeneity and clumpiness). Their distributions were studied, leading to the observation of varying behaviours in images generated by different samples and acquisition conditions. The distributions corresponding to samples coming from the BNC reaction showed similar attributes in each analyzed parameter, proving to be robust to the experimental process, but sensitive to light and focus conditions. Considering those observations, a manual feature extraction was performed as a pre-processing step. A Support Vector Machine (SVM) and a fully dense Neural Network (NN) were optimized, trained, and tested. The final performance metrics were similar for both models: 93%-93% for the SVM, vs 94%-95% for the NN in accuracy and precision respectively. Based on the distribution of the predicted class probabilities, the latter had a better capacity to reject inadequate images, so the NN was selected to perform the image verification step prior to quantification. The trained NN was able to correctly classify the images regardless of their track density. The exhaustive characterization of the nuclear tracks provided new knowledge related to the autoradiographic images generation. The inclusion of machine learning in the analysis workflow proves to optimize the boron determination process and paves the way for further applications in the field of boron imaging.
publishDate 2023
dc.date.none.fl_str_mv 2023-12
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/222662
Viglietti, Julia S.; Espain, Maria Sol; Díaz, Rodrigo Fernando; Nieto, Luis Agustin; Szewc, Manuel; et al.; From nuclear track characterization to machine learning based image classification in neutron autoradiography for boron neutron capture therapy; Public Library of Science; Plos One; 18; 12; e0293891; 12-2023; 1-23
1932-6203
CONICET Digital
CONICET
url http://hdl.handle.net/11336/222662
identifier_str_mv Viglietti, Julia S.; Espain, Maria Sol; Díaz, Rodrigo Fernando; Nieto, Luis Agustin; Szewc, Manuel; et al.; From nuclear track characterization to machine learning based image classification in neutron autoradiography for boron neutron capture therapy; Public Library of Science; Plos One; 18; 12; e0293891; 12-2023; 1-23
1932-6203
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0293891
info:eu-repo/semantics/altIdentifier/doi/10.1371/journal.pone.0293891
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Public Library of Science
publisher.none.fl_str_mv Public Library of Science
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1844614193580343296
score 13.070432