Artemisia: Validation of a deep learning model for automatic breast density categorization

Autores
Tajerian, Matías N.; Pesce, Karina; Frangella, Julia; Quiroga, Ezequiel; Boietti, Bruno Rafael; Chico, Maria José; Swiecicki, María Paz; Benitez, Sonia; Rabellino, Martín; Luna, Daniel Roberto
Año de publicación
2021
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Background: The aim of this study is to validate a deep learning model for the classification of breast density according to American College of Radiology’s breast density patterns. Methods: A convolutional neural network was developed with 10,229 digital screening mammogram images. Once the network was developed and tested, its performance was evaluated before a group of six professionals, the majority report and a commercial software application. We selected randomly 451 new mammographic images from different studies and patients. The categorization process by professionals was repeated in two stages. Results: The agreement between the convolutional neural network and the majority report was k=0.64 (95% CI: 0.58–0.69) in the first stage and k=0.57 (95% CI: 0.52–0.63) in the second stage. The agreement between the CNN and the commercial software application was k=0.54 (95% CI: 0.48–0.60). In both cases, we observed that the concordances of the CNN were within or above the range of professionals’ concordances values. Conclusions: Considering the internal reference standard (majority report) and the external reference standard (commercial software application), we can affirm the CNN achieved professional level performance.
Fil: Tajerian, Matías N.. Hospital Italiano. Instituto Universitario. Escuela de Medicina; Argentina
Fil: Pesce, Karina. Hospital Italiano. Instituto Universitario. Escuela de Medicina; Argentina
Fil: Frangella, Julia. Hospital Italiano. Instituto Universitario. Escuela de Medicina; Argentina
Fil: Quiroga, Ezequiel. Hospital Italiano. Instituto Universitario. Escuela de Medicina; Argentina
Fil: Boietti, Bruno Rafael. Hospital Italiano. Instituto Universitario. Escuela de Medicina; Argentina
Fil: Chico, Maria José. Hospital Italiano. Instituto Universitario. Escuela de Medicina; Argentina
Fil: Swiecicki, María Paz. Hospital Italiano. Instituto Universitario. Escuela de Medicina; Argentina
Fil: Benitez, Sonia. Hospital Italiano. Instituto Universitario. Escuela de Medicina; Argentina
Fil: Rabellino, Martín. Hospital Italiano. Instituto Universitario. Escuela de Medicina; Argentina
Fil: Luna, Daniel Roberto. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Houssay. Instituto de Medicina Traslacional e Ingeniería Biomédica - Hospital Italiano. Instituto de Medicina Traslacional e Ingeniería Biomédica.- Instituto Universitario Hospital Italiano de Buenos Aires. Instituto de Medicina Traslacional e Ingeniería Biomédica; Argentina
Materia
ALGORITHM DEVELOPMENT
ARTIFICIAL INTELLIGENCE
BREAST DENSITY
DEEP LEARNING
MEDICAL IMAGING
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-nd/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/161290
Acceder
id CONICETDig_e01d863ba5a0667e875559bc8b5a8d30
oai_identifier_str oai:ri.conicet.gov.ar:11336/161290
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Artemisia: Validation of a deep learning model for automatic breast density categorizationTajerian, Matías N.Pesce, KarinaFrangella, JuliaQuiroga, EzequielBoietti, Bruno RafaelChico, Maria JoséSwiecicki, María PazBenitez, SoniaRabellino, MartínLuna, Daniel RobertoALGORITHM DEVELOPMENTARTIFICIAL INTELLIGENCEBREAST DENSITYDEEP LEARNINGMEDICAL IMAGINGhttps://purl.org/becyt/ford/3.3https://purl.org/becyt/ford/3Background: The aim of this study is to validate a deep learning model for the classification of breast density according to American College of Radiology’s breast density patterns. Methods: A convolutional neural network was developed with 10,229 digital screening mammogram images. Once the network was developed and tested, its performance was evaluated before a group of six professionals, the majority report and a commercial software application. We selected randomly 451 new mammographic images from different studies and patients. The categorization process by professionals was repeated in two stages. Results: The agreement between the convolutional neural network and the majority report was k=0.64 (95% CI: 0.58–0.69) in the first stage and k=0.57 (95% CI: 0.52–0.63) in the second stage. The agreement between the CNN and the commercial software application was k=0.54 (95% CI: 0.48–0.60). In both cases, we observed that the concordances of the CNN were within or above the range of professionals’ concordances values. Conclusions: Considering the internal reference standard (majority report) and the external reference standard (commercial software application), we can affirm the CNN achieved professional level performance.Fil: Tajerian, Matías N.. Hospital Italiano. Instituto Universitario. Escuela de Medicina; ArgentinaFil: Pesce, Karina. Hospital Italiano. Instituto Universitario. Escuela de Medicina; ArgentinaFil: Frangella, Julia. Hospital Italiano. Instituto Universitario. Escuela de Medicina; ArgentinaFil: Quiroga, Ezequiel. Hospital Italiano. Instituto Universitario. Escuela de Medicina; ArgentinaFil: Boietti, Bruno Rafael. Hospital Italiano. Instituto Universitario. Escuela de Medicina; ArgentinaFil: Chico, Maria José. Hospital Italiano. Instituto Universitario. Escuela de Medicina; ArgentinaFil: Swiecicki, María Paz. Hospital Italiano. Instituto Universitario. Escuela de Medicina; ArgentinaFil: Benitez, Sonia. Hospital Italiano. Instituto Universitario. Escuela de Medicina; ArgentinaFil: Rabellino, Martín. Hospital Italiano. Instituto Universitario. Escuela de Medicina; ArgentinaFil: Luna, Daniel Roberto. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Houssay. Instituto de Medicina Traslacional e Ingeniería Biomédica - Hospital Italiano. Instituto de Medicina Traslacional e Ingeniería Biomédica.- Instituto Universitario Hospital Italiano de Buenos Aires. Instituto de Medicina Traslacional e Ingeniería Biomédica; ArgentinaAME Publishing Company2021-06info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/161290Tajerian, Matías N.; Pesce, Karina; Frangella, Julia; Quiroga, Ezequiel; Boietti, Bruno Rafael; et al.; Artemisia: Validation of a deep learning model for automatic breast density categorization; AME Publishing Company; Journal of Medical Artificial Intelligence; 4; June; 6-2021; 1-92617-2496CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/doi/10.21037/jmai-20-43info:eu-repo/semantics/altIdentifier/url/https://jmai.amegroups.com/article/view/6302/htmlinfo:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-nd/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-29T09:45:28Zoai:ri.conicet.gov.ar:11336/161290instacron: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 09:45:28.43CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Artemisia: Validation of a deep learning model for automatic breast density categorization
title Artemisia: Validation of a deep learning model for automatic breast density categorization
spellingShingle Artemisia: Validation of a deep learning model for automatic breast density categorization
Tajerian, Matías N.
ALGORITHM DEVELOPMENT
ARTIFICIAL INTELLIGENCE
BREAST DENSITY
DEEP LEARNING
MEDICAL IMAGING
title_short Artemisia: Validation of a deep learning model for automatic breast density categorization
title_full Artemisia: Validation of a deep learning model for automatic breast density categorization
title_fullStr Artemisia: Validation of a deep learning model for automatic breast density categorization
title_full_unstemmed Artemisia: Validation of a deep learning model for automatic breast density categorization
title_sort Artemisia: Validation of a deep learning model for automatic breast density categorization
dc.creator.none.fl_str_mv Tajerian, Matías N.
Pesce, Karina
Frangella, Julia
Quiroga, Ezequiel
Boietti, Bruno Rafael
Chico, Maria José
Swiecicki, María Paz
Benitez, Sonia
Rabellino, Martín
Luna, Daniel Roberto
author Tajerian, Matías N.
author_facet Tajerian, Matías N.
Pesce, Karina
Frangella, Julia
Quiroga, Ezequiel
Boietti, Bruno Rafael
Chico, Maria José
Swiecicki, María Paz
Benitez, Sonia
Rabellino, Martín
Luna, Daniel Roberto
author_role author
author2 Pesce, Karina
Frangella, Julia
Quiroga, Ezequiel
Boietti, Bruno Rafael
Chico, Maria José
Swiecicki, María Paz
Benitez, Sonia
Rabellino, Martín
Luna, Daniel Roberto
author2_role author
author
author
author
author
author
author
author
author
dc.subject.none.fl_str_mv ALGORITHM DEVELOPMENT
ARTIFICIAL INTELLIGENCE
BREAST DENSITY
DEEP LEARNING
MEDICAL IMAGING
topic ALGORITHM DEVELOPMENT
ARTIFICIAL INTELLIGENCE
BREAST DENSITY
DEEP LEARNING
MEDICAL IMAGING
purl_subject.fl_str_mv https://purl.org/becyt/ford/3.3
https://purl.org/becyt/ford/3
dc.description.none.fl_txt_mv Background: The aim of this study is to validate a deep learning model for the classification of breast density according to American College of Radiology’s breast density patterns. Methods: A convolutional neural network was developed with 10,229 digital screening mammogram images. Once the network was developed and tested, its performance was evaluated before a group of six professionals, the majority report and a commercial software application. We selected randomly 451 new mammographic images from different studies and patients. The categorization process by professionals was repeated in two stages. Results: The agreement between the convolutional neural network and the majority report was k=0.64 (95% CI: 0.58–0.69) in the first stage and k=0.57 (95% CI: 0.52–0.63) in the second stage. The agreement between the CNN and the commercial software application was k=0.54 (95% CI: 0.48–0.60). In both cases, we observed that the concordances of the CNN were within or above the range of professionals’ concordances values. Conclusions: Considering the internal reference standard (majority report) and the external reference standard (commercial software application), we can affirm the CNN achieved professional level performance.
Fil: Tajerian, Matías N.. Hospital Italiano. Instituto Universitario. Escuela de Medicina; Argentina
Fil: Pesce, Karina. Hospital Italiano. Instituto Universitario. Escuela de Medicina; Argentina
Fil: Frangella, Julia. Hospital Italiano. Instituto Universitario. Escuela de Medicina; Argentina
Fil: Quiroga, Ezequiel. Hospital Italiano. Instituto Universitario. Escuela de Medicina; Argentina
Fil: Boietti, Bruno Rafael. Hospital Italiano. Instituto Universitario. Escuela de Medicina; Argentina
Fil: Chico, Maria José. Hospital Italiano. Instituto Universitario. Escuela de Medicina; Argentina
Fil: Swiecicki, María Paz. Hospital Italiano. Instituto Universitario. Escuela de Medicina; Argentina
Fil: Benitez, Sonia. Hospital Italiano. Instituto Universitario. Escuela de Medicina; Argentina
Fil: Rabellino, Martín. Hospital Italiano. Instituto Universitario. Escuela de Medicina; Argentina
Fil: Luna, Daniel Roberto. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Houssay. Instituto de Medicina Traslacional e Ingeniería Biomédica - Hospital Italiano. Instituto de Medicina Traslacional e Ingeniería Biomédica.- Instituto Universitario Hospital Italiano de Buenos Aires. Instituto de Medicina Traslacional e Ingeniería Biomédica; Argentina
description Background: The aim of this study is to validate a deep learning model for the classification of breast density according to American College of Radiology’s breast density patterns. Methods: A convolutional neural network was developed with 10,229 digital screening mammogram images. Once the network was developed and tested, its performance was evaluated before a group of six professionals, the majority report and a commercial software application. We selected randomly 451 new mammographic images from different studies and patients. The categorization process by professionals was repeated in two stages. Results: The agreement between the convolutional neural network and the majority report was k=0.64 (95% CI: 0.58–0.69) in the first stage and k=0.57 (95% CI: 0.52–0.63) in the second stage. The agreement between the CNN and the commercial software application was k=0.54 (95% CI: 0.48–0.60). In both cases, we observed that the concordances of the CNN were within or above the range of professionals’ concordances values. Conclusions: Considering the internal reference standard (majority report) and the external reference standard (commercial software application), we can affirm the CNN achieved professional level performance.
publishDate 2021
dc.date.none.fl_str_mv 2021-06
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/11336/161290
Tajerian, Matías N.; Pesce, Karina; Frangella, Julia; Quiroga, Ezequiel; Boietti, Bruno Rafael; et al.; Artemisia: Validation of a deep learning model for automatic breast density categorization; AME Publishing Company; Journal of Medical Artificial Intelligence; 4; June; 6-2021; 1-9
2617-2496
CONICET Digital
CONICET
url http://hdl.handle.net/11336/161290
identifier_str_mv Tajerian, Matías N.; Pesce, Karina; Frangella, Julia; Quiroga, Ezequiel; Boietti, Bruno Rafael; et al.; Artemisia: Validation of a deep learning model for automatic breast density categorization; AME Publishing Company; Journal of Medical Artificial Intelligence; 4; June; 6-2021; 1-9
2617-2496
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/doi/10.21037/jmai-20-43
info:eu-repo/semantics/altIdentifier/url/https://jmai.amegroups.com/article/view/6302/html
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-nd/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-nd/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv AME Publishing Company
publisher.none.fl_str_mv AME Publishing Company
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_ 1844613425880104960
score 13.070432

Publicaciones similares