An open B-mode ultrasound database for deep learning-based atherosclerotic plaque segmentation

Autores
Rulloni, Valeria Soledad; Perez, Hernan A.; Dori, Trinidad; Borchi, Nahuel A.; Gil, Francisco N.; de Vargas Guterres, Bruna; Garcia, Nestor Horacio
Año de publicación
2026
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Cardiovascular events, predominantly ischemic, account for approximately 32% of global mortality and are expected to increase approximately 30% by 2030. A substantial proportion of these events is preventable through the control of established risk factors. Atherosclerosis is defined by the progressive development of arterial plaques and remains the main cause of ischemic cardiovascular disease. In this context, plaque detection in medical images is required for early diagnosis and longitudinal assessment, which is commonly based on total plaque area. Manual plaque annotation in B-mode ultrasound images requires specialized expertise and is affected by inter- and intra-operator variability. Automatic methods trained on expert-annotated data are therefore required to improve standardization and reproducibility. However, the research community faces a limited availability of open access databases designed for image segmentation and benchmarking under traditional and heterogeneous imaging conditions inherent to B mode ultrasound data. This work presents an open-access B-mode ultrasound image database designed for atherosclerotic plaque segmentation. The dataset includes 541 ultrasound images with a resolution of 800 × 800 pixels, each paired with a binary segmentation mask validated by clinical specialists. The database captures heterogeneous imaging conditions, including plaque-free cases, single and multiple plaques, and non-centralized plaque locations. To assess its suitability for algorithm development, the dataset was used to train a U-Net ensemble. The evaluation provided a median error of 0.35 mm2 on plaque free test images and a mean Dice coefficient of 0.62 on test images containing plaques.
Fil: Rulloni, Valeria Soledad. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba; Argentina
Fil: Perez, Hernan A.. Universidad Católica de Córdoba. Facultad de Ciencias Químicas; Argentina
Fil: Dori, Trinidad. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales; Argentina
Fil: Borchi, Nahuel A.. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales; Argentina
Fil: Gil, Francisco N.. Servicio Central de Informática Universitaria (seciu) ; Oficinas Centrales ; Universidad de la Republica;
Fil: de Vargas Guterres, Bruna. Servicio Central de Informática Universitaria (seciu) ; Oficinas Centrales ; Universidad de la Republica;
Fil: Garcia, Nestor Horacio. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba. Instituto de Investigaciones en Ciencias de la Salud. Universidad Nacional de Córdoba. Instituto de Investigaciones en Ciencias de la Salud; Argentina
Materia
Aterosclerosis
Inteligencia Artificial
Redes NEuronales
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:11336/287792

id CONICETDig_bfee764fcb35fac2c0e86091eb1c5418
oai_identifier_str oai:ri.conicet.gov.ar:11336/287792
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling An open B-mode ultrasound database for deep learning-based atherosclerotic plaque segmentationRulloni, Valeria SoledadPerez, Hernan A.Dori, TrinidadBorchi, Nahuel A.Gil, Francisco N.de Vargas Guterres, BrunaGarcia, Nestor HoracioAterosclerosisInteligencia ArtificialRedes NEuronaleshttps://purl.org/becyt/ford/3.2https://purl.org/becyt/ford/3Cardiovascular events, predominantly ischemic, account for approximately 32% of global mortality and are expected to increase approximately 30% by 2030. A substantial proportion of these events is preventable through the control of established risk factors. Atherosclerosis is defined by the progressive development of arterial plaques and remains the main cause of ischemic cardiovascular disease. In this context, plaque detection in medical images is required for early diagnosis and longitudinal assessment, which is commonly based on total plaque area. Manual plaque annotation in B-mode ultrasound images requires specialized expertise and is affected by inter- and intra-operator variability. Automatic methods trained on expert-annotated data are therefore required to improve standardization and reproducibility. However, the research community faces a limited availability of open access databases designed for image segmentation and benchmarking under traditional and heterogeneous imaging conditions inherent to B mode ultrasound data. This work presents an open-access B-mode ultrasound image database designed for atherosclerotic plaque segmentation. The dataset includes 541 ultrasound images with a resolution of 800 × 800 pixels, each paired with a binary segmentation mask validated by clinical specialists. The database captures heterogeneous imaging conditions, including plaque-free cases, single and multiple plaques, and non-centralized plaque locations. To assess its suitability for algorithm development, the dataset was used to train a U-Net ensemble. The evaluation provided a median error of 0.35 mm2 on plaque free test images and a mean Dice coefficient of 0.62 on test images containing plaques.Fil: Rulloni, Valeria Soledad. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba; ArgentinaFil: Perez, Hernan A.. Universidad Católica de Córdoba. Facultad de Ciencias Químicas; ArgentinaFil: Dori, Trinidad. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales; ArgentinaFil: Borchi, Nahuel A.. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales; ArgentinaFil: Gil, Francisco N.. Servicio Central de Informática Universitaria (seciu) ; Oficinas Centrales ; Universidad de la Republica;Fil: de Vargas Guterres, Bruna. Servicio Central de Informática Universitaria (seciu) ; Oficinas Centrales ; Universidad de la Republica;Fil: Garcia, Nestor Horacio. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba. Instituto de Investigaciones en Ciencias de la Salud. Universidad Nacional de Córdoba. Instituto de Investigaciones en Ciencias de la Salud; ArgentinaNature Publishing Group2026-03info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/287792Rulloni, Valeria Soledad; Perez, Hernan A.; Dori, Trinidad; Borchi, Nahuel A.; Gil, Francisco N.; et al.; An open B-mode ultrasound database for deep learning-based atherosclerotic plaque segmentation; Nature Publishing Group; Scientific Data; 3-2026; 1-112052-4463CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://www.nature.com/articles/s41597-026-06952-7info:eu-repo/semantics/altIdentifier/doi/10.1038/s41597-026-06952-7info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2026-08-25T14:39:46Zoai:ri.conicet.gov.ar:11336/287792instacron: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:34982026-08-25 14:39:46.513CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv An open B-mode ultrasound database for deep learning-based atherosclerotic plaque segmentation
title An open B-mode ultrasound database for deep learning-based atherosclerotic plaque segmentation
spellingShingle An open B-mode ultrasound database for deep learning-based atherosclerotic plaque segmentation
Rulloni, Valeria Soledad
Aterosclerosis
Inteligencia Artificial
Redes NEuronales
title_short An open B-mode ultrasound database for deep learning-based atherosclerotic plaque segmentation
title_full An open B-mode ultrasound database for deep learning-based atherosclerotic plaque segmentation
title_fullStr An open B-mode ultrasound database for deep learning-based atherosclerotic plaque segmentation
title_full_unstemmed An open B-mode ultrasound database for deep learning-based atherosclerotic plaque segmentation
title_sort An open B-mode ultrasound database for deep learning-based atherosclerotic plaque segmentation
dc.creator.none.fl_str_mv Rulloni, Valeria Soledad
Perez, Hernan A.
Dori, Trinidad
Borchi, Nahuel A.
Gil, Francisco N.
de Vargas Guterres, Bruna
Garcia, Nestor Horacio
author Rulloni, Valeria Soledad
author_facet Rulloni, Valeria Soledad
Perez, Hernan A.
Dori, Trinidad
Borchi, Nahuel A.
Gil, Francisco N.
de Vargas Guterres, Bruna
Garcia, Nestor Horacio
author_role author
author2 Perez, Hernan A.
Dori, Trinidad
Borchi, Nahuel A.
Gil, Francisco N.
de Vargas Guterres, Bruna
Garcia, Nestor Horacio
author2_role author
author
author
author
author
author
dc.subject.none.fl_str_mv Aterosclerosis
Inteligencia Artificial
Redes NEuronales
topic Aterosclerosis
Inteligencia Artificial
Redes NEuronales
purl_subject.fl_str_mv https://purl.org/becyt/ford/3.2
https://purl.org/becyt/ford/3
dc.description.none.fl_txt_mv Cardiovascular events, predominantly ischemic, account for approximately 32% of global mortality and are expected to increase approximately 30% by 2030. A substantial proportion of these events is preventable through the control of established risk factors. Atherosclerosis is defined by the progressive development of arterial plaques and remains the main cause of ischemic cardiovascular disease. In this context, plaque detection in medical images is required for early diagnosis and longitudinal assessment, which is commonly based on total plaque area. Manual plaque annotation in B-mode ultrasound images requires specialized expertise and is affected by inter- and intra-operator variability. Automatic methods trained on expert-annotated data are therefore required to improve standardization and reproducibility. However, the research community faces a limited availability of open access databases designed for image segmentation and benchmarking under traditional and heterogeneous imaging conditions inherent to B mode ultrasound data. This work presents an open-access B-mode ultrasound image database designed for atherosclerotic plaque segmentation. The dataset includes 541 ultrasound images with a resolution of 800 × 800 pixels, each paired with a binary segmentation mask validated by clinical specialists. The database captures heterogeneous imaging conditions, including plaque-free cases, single and multiple plaques, and non-centralized plaque locations. To assess its suitability for algorithm development, the dataset was used to train a U-Net ensemble. The evaluation provided a median error of 0.35 mm2 on plaque free test images and a mean Dice coefficient of 0.62 on test images containing plaques.
Fil: Rulloni, Valeria Soledad. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba; Argentina
Fil: Perez, Hernan A.. Universidad Católica de Córdoba. Facultad de Ciencias Químicas; Argentina
Fil: Dori, Trinidad. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales; Argentina
Fil: Borchi, Nahuel A.. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales; Argentina
Fil: Gil, Francisco N.. Servicio Central de Informática Universitaria (seciu) ; Oficinas Centrales ; Universidad de la Republica;
Fil: de Vargas Guterres, Bruna. Servicio Central de Informática Universitaria (seciu) ; Oficinas Centrales ; Universidad de la Republica;
Fil: Garcia, Nestor Horacio. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba. Instituto de Investigaciones en Ciencias de la Salud. Universidad Nacional de Córdoba. Instituto de Investigaciones en Ciencias de la Salud; Argentina
description Cardiovascular events, predominantly ischemic, account for approximately 32% of global mortality and are expected to increase approximately 30% by 2030. A substantial proportion of these events is preventable through the control of established risk factors. Atherosclerosis is defined by the progressive development of arterial plaques and remains the main cause of ischemic cardiovascular disease. In this context, plaque detection in medical images is required for early diagnosis and longitudinal assessment, which is commonly based on total plaque area. Manual plaque annotation in B-mode ultrasound images requires specialized expertise and is affected by inter- and intra-operator variability. Automatic methods trained on expert-annotated data are therefore required to improve standardization and reproducibility. However, the research community faces a limited availability of open access databases designed for image segmentation and benchmarking under traditional and heterogeneous imaging conditions inherent to B mode ultrasound data. This work presents an open-access B-mode ultrasound image database designed for atherosclerotic plaque segmentation. The dataset includes 541 ultrasound images with a resolution of 800 × 800 pixels, each paired with a binary segmentation mask validated by clinical specialists. The database captures heterogeneous imaging conditions, including plaque-free cases, single and multiple plaques, and non-centralized plaque locations. To assess its suitability for algorithm development, the dataset was used to train a U-Net ensemble. The evaluation provided a median error of 0.35 mm2 on plaque free test images and a mean Dice coefficient of 0.62 on test images containing plaques.
publishDate 2026
dc.date.none.fl_str_mv 2026-03
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/11336/287792
Rulloni, Valeria Soledad; Perez, Hernan A.; Dori, Trinidad; Borchi, Nahuel A.; Gil, Francisco N.; et al.; An open B-mode ultrasound database for deep learning-based atherosclerotic plaque segmentation; Nature Publishing Group; Scientific Data; 3-2026; 1-11
2052-4463
CONICET Digital
CONICET
url http://hdl.handle.net/11336/287792
identifier_str_mv Rulloni, Valeria Soledad; Perez, Hernan A.; Dori, Trinidad; Borchi, Nahuel A.; Gil, Francisco N.; et al.; An open B-mode ultrasound database for deep learning-based atherosclerotic plaque segmentation; Nature Publishing Group; Scientific Data; 3-2026; 1-11
2052-4463
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://www.nature.com/articles/s41597-026-06952-7
info:eu-repo/semantics/altIdentifier/doi/10.1038/s41597-026-06952-7
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
application/pdf
dc.publisher.none.fl_str_mv Nature Publishing Group
publisher.none.fl_str_mv Nature Publishing Group
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_ 1874774410503651328
score 13.334379