Deep Learning for Describing Breast Ultrasound Images with BI-RADS Terms

Breast cancer is the most common cancer in women. Ultrasound is one of the most used techniques for diagnosis, but an expert in the field is necessary to interpret the test. Computer-aided diagnosis (CAD) systems aim to help physicians during this process. Experts use the Breast Imaging-Reporting an...

Descripción completa

Detalles Bibliográficos
Autores: Carrilero Mardones, Mikel, Parras Jurado, Manuela, Nogales, Alberto, Pérez Martín, Jorge, Díez Vegas, Francisco Javier
Tipo de recurso: artículo
Fecha de publicación:2024
País:España
Institución:Universidad Nacional de Educación a Distancia
Repositorio:e-spacio. Repositorio Institucional de la UNED
Idioma:inglés
OAI Identifier:oai:e-spacio.uned.es:20.500.14468/25891
Acceso en línea:https://hdl.handle.net/20.500.14468/25891
Access Level:acceso abierto
Palabra clave:33 Ciencias Tecnológicas
breast ultrasound
BI-RADS
medical image captioning
computer aided diagnosis
attention mechanisms
explainable artificial intelligence
id ES_e8ea95c0f3282d69bd413f9ca922a30d
oai_identifier_str oai:e-spacio.uned.es:20.500.14468/25891
network_acronym_str ES
network_name_str España
repository_id_str
spelling Deep Learning for Describing Breast Ultrasound Images with BI-RADS TermsCarrilero Mardones, MikelParras Jurado, ManuelaNogales, AlbertoPérez Martín, JorgeDíez Vegas, Francisco Javier33 Ciencias Tecnológicasbreast ultrasoundBI-RADSmedical image captioningcomputer aided diagnosisattention mechanismsexplainable artificial intelligenceBreast cancer is the most common cancer in women. Ultrasound is one of the most used techniques for diagnosis, but an expert in the field is necessary to interpret the test. Computer-aided diagnosis (CAD) systems aim to help physicians during this process. Experts use the Breast Imaging-Reporting and Data System (BI-RADS) to describe tumors according to several features (shape, margin, orientation...) and estimate their malignancy, with a common language. To aid in tumor diagnosis with BI-RADS explanations, this paper presents a deep neural network for tumor detection, description, and classification. An expert radiologist described with BI-RADS terms 749 nodules taken from public datasets. The YOLO detection algorithm is used to obtain Regions of Interest (ROIs), and then a model, based on a multi-class classification architecture, receives as input each ROI and outputs the BI-RADS descriptors, the BI-RADS classification (with 6 categories), and a Boolean classification of malignancy. Six hundred of the nodules were used for 10-fold cross-validation (CV) and 149 for testing. The accuracy of this model was compared with state-of-the-art CNNs for the same task. This model outperforms plain classifiers in the agreement with the expert (Cohen’s kappa), with a mean over the descriptors of 0.58 in CV and 0.64 in testing, while the second best model yielded kappas of 0.55 and 0.59, respectively. Adding YOLO to the model significantly enhances the performance (0.16 in CV and 0.09 in testing). More importantly, training the model with BI-RADS descriptors enables the explainability of the Boolean malignancy classification without reducing accuracy.Springerhttps://orcid.org/0000-0003-4951-8102e-Spacio UNED20252025-02-1120242024-01-0120242024-01-01journal articlehttp://purl.org/coar/resource_type/c_6501info:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/20.500.14468/25891reponame:e-spacio. Repositorio Institucional de la UNEDinstname:Universidad Nacional de Educación a DistanciaInglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by/4.0/deed.esoai:e-spacio.uned.es:20.500.14468/258912026-06-06T12:38:31Z
dc.title.none.fl_str_mv Deep Learning for Describing Breast Ultrasound Images with BI-RADS Terms
title Deep Learning for Describing Breast Ultrasound Images with BI-RADS Terms
spellingShingle Deep Learning for Describing Breast Ultrasound Images with BI-RADS Terms
Carrilero Mardones, Mikel
33 Ciencias Tecnológicas
breast ultrasound
BI-RADS
medical image captioning
computer aided diagnosis
attention mechanisms
explainable artificial intelligence
title_short Deep Learning for Describing Breast Ultrasound Images with BI-RADS Terms
title_full Deep Learning for Describing Breast Ultrasound Images with BI-RADS Terms
title_fullStr Deep Learning for Describing Breast Ultrasound Images with BI-RADS Terms
title_full_unstemmed Deep Learning for Describing Breast Ultrasound Images with BI-RADS Terms
title_sort Deep Learning for Describing Breast Ultrasound Images with BI-RADS Terms
dc.creator.none.fl_str_mv Carrilero Mardones, Mikel
Parras Jurado, Manuela
Nogales, Alberto
Pérez Martín, Jorge
Díez Vegas, Francisco Javier
author Carrilero Mardones, Mikel
author_facet Carrilero Mardones, Mikel
Parras Jurado, Manuela
Nogales, Alberto
Pérez Martín, Jorge
Díez Vegas, Francisco Javier
author_role author
author2 Parras Jurado, Manuela
Nogales, Alberto
Pérez Martín, Jorge
Díez Vegas, Francisco Javier
author2_role author
author
author
author
dc.contributor.none.fl_str_mv https://orcid.org/0000-0003-4951-8102
e-Spacio UNED
dc.subject.none.fl_str_mv 33 Ciencias Tecnológicas
breast ultrasound
BI-RADS
medical image captioning
computer aided diagnosis
attention mechanisms
explainable artificial intelligence
topic 33 Ciencias Tecnológicas
breast ultrasound
BI-RADS
medical image captioning
computer aided diagnosis
attention mechanisms
explainable artificial intelligence
description Breast cancer is the most common cancer in women. Ultrasound is one of the most used techniques for diagnosis, but an expert in the field is necessary to interpret the test. Computer-aided diagnosis (CAD) systems aim to help physicians during this process. Experts use the Breast Imaging-Reporting and Data System (BI-RADS) to describe tumors according to several features (shape, margin, orientation...) and estimate their malignancy, with a common language. To aid in tumor diagnosis with BI-RADS explanations, this paper presents a deep neural network for tumor detection, description, and classification. An expert radiologist described with BI-RADS terms 749 nodules taken from public datasets. The YOLO detection algorithm is used to obtain Regions of Interest (ROIs), and then a model, based on a multi-class classification architecture, receives as input each ROI and outputs the BI-RADS descriptors, the BI-RADS classification (with 6 categories), and a Boolean classification of malignancy. Six hundred of the nodules were used for 10-fold cross-validation (CV) and 149 for testing. The accuracy of this model was compared with state-of-the-art CNNs for the same task. This model outperforms plain classifiers in the agreement with the expert (Cohen’s kappa), with a mean over the descriptors of 0.58 in CV and 0.64 in testing, while the second best model yielded kappas of 0.55 and 0.59, respectively. Adding YOLO to the model significantly enhances the performance (0.16 in CV and 0.09 in testing). More importantly, training the model with BI-RADS descriptors enables the explainability of the Boolean malignancy classification without reducing accuracy.
publishDate 2024
dc.date.none.fl_str_mv 2024
2024-01-01
2024
2024-01-01
2025
2025-02-11
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/20.500.14468/25891
url https://hdl.handle.net/20.500.14468/25891
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by/4.0/deed.es
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
http://creativecommons.org/licenses/by/4.0/deed.es
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Springer
publisher.none.fl_str_mv Springer
dc.source.none.fl_str_mv reponame:e-spacio. Repositorio Institucional de la UNED
instname:Universidad Nacional de Educación a Distancia
instname_str Universidad Nacional de Educación a Distancia
reponame_str e-spacio. Repositorio Institucional de la UNED
collection e-spacio. Repositorio Institucional de la UNED
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869422982699417600
score 15.812429

Similares en LA Referencia