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

Vista sencilla de ítem
dc.contributor.authorCarrilero Mardones, Mikel
dc.contributor.authorParras Jurado, Manuela
dc.contributor.authorNogales, Alberto
dc.contributor.authorPérez Martín, Jorge
dc.contributor.authorDíez Vegas, Francisco Javier
dc.contributor.orcidhttps://orcid.org/0000-0003-4951-8102
dc.date.accessioned2025-02-11T10:35:58Z
dc.date.available2025-02-11T10:35:58Z
dc.date.issued2024
dc.descriptionThis is the Accepted Manuscript of an article published by Springer in "The Journal of Imaging Informatics in Medicine" 2024, available online: https://doi.org/10.1007/s10278-024-01155-1 Este es el manuscrito aceptado de un artículo publicado por Springer in "The Journal of Imaging Informatics in Medicine" 2024, disponible en línea: https://doi.org/10.1007/s10278-024-01155-1
dc.description.abstractBreast 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.en
dc.description.versionversión final
dc.identifier.citationCarrilero-Mardones, M., Parras-Jurado, M., Nogales, A. et al. Deep Learning for Describing Breast Ultrasound Images with BI-RADS Terms. J Digit Imaging. Inform. med. 37, 2940–2954 (2024). https://doi.org/10.1007/s10278-024-01155-1
dc.identifier.doihttps://doi.org/10.1007/s10278-024-01155-1
dc.identifier.issn2948-2925, 2948-2933
dc.identifier.urihttps://hdl.handle.net/20.500.14468/25891
dc.journal.issue6
dc.journal.titleThe Journal of Imaging Informatics in Medicine
dc.journal.volume37
dc.language.isoen
dc.page.final2954
dc.page.initial2940
dc.publisherSpringer
dc.relation.centerFacultades y escuelas::E.T.S. de Ingeniería Informática
dc.relation.departmentInteligencia Artificial
dc.rightsinfo:eu-repo/semantics/openAccess
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/deed.es
dc.subject33 Ciencias Tecnológicas
dc.subject.keywordsbreast ultrasounden
dc.subject.keywordsBI-RADSen
dc.subject.keywordsmedical image captioningen
dc.subject.keywordscomputer aided diagnosisen
dc.subject.keywordsattention mechanismsen
dc.subject.keywordsexplainable artificial intelligenceen
dc.titleDeep Learning for Describing Breast Ultrasound Images with BI-RADS Termsen
dc.typeartículoes
dc.typejournal articleen
dspace.entity.typePublication
relation.isAuthorOfPublicationdedabd0e-bc3e-4af4-a1b9-f4a022f1f4f8
relation.isAuthorOfPublicationfda2a608-1b8f-46a1-87cc-777559fcf158
relation.isAuthorOfPublicationc6032e20-a1d0-49b9-92e3-5c9f624ab143
relation.isAuthorOfPublication.latestForDiscoverydedabd0e-bc3e-4af4-a1b9-f4a022f1f4f8
Archivos
Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
Carrilero_Mardones_Deep_Learning_for_Describi.pdf
Tamaño:
2.93 MB
Formato:
Adobe Portable Document Format
Descargar
Bloque de licencias
Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
license.txt
Tamaño:
3.62 KB
Formato:
Item-specific license agreed to upon submission
Descripción:
Descargar
Colecciones
Artículos y papers