Encoding upper nasal airway structure with U-Net for respiratory healthcare applications

Autores
Pazos, Bruno Alfredo; Navarro, Jose Pablo; de Azevedo, Soledad; Delrieux, Claudio Augusto; Gonzalez-Jose, Rolando
Año de publicación
2022
Idioma
inglés
Tipo de recurso
documento de conferencia
Estado
versión publicada
Descripción
The human upper nasal airway is an anatomical structure with a complex geometry that performs essential functions required by the rest of the respiratory system. An accurate and precise segmentation process that captures its intricate shape and variability becomes indispensable to fully understand its performance under different circumstances and to study its anatomy from multiple perspectives. As currently performed, the manual or semi-automatic segmentation process for these structures is extremely time-consuming, may demand extensive manual post-processing steps to correct over-or under-segmentation, and is subject to considerable intra- and inter-operator variance. Further, in developing countries, healthcare institutions modernize their medical imaging devices at different rates;thus, specialists and proposed solutions have to deal with a wide range of image characteristics and quality variability to execute their diagnostics. In this paper we develop an automatic segmentation strategy for the human upper nasal airway, based on a deep convolutional network trained with >3000 CT scans acquired from different devices of a national hospital in Argentina, Hospital Italiano de Buenos Aires (2010). This  process achieves a remarkable preliminary results with a low error rate (0.07%) and an acceptable similarity score (86.9%).
Fil: Pazos, Bruno Alfredo. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Centro Nacional Patagónico. Instituto Patagónico de Ciencias Sociales y Humanas; Argentina
Fil: Navarro, Jose Pablo. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Centro Nacional Patagónico. Instituto Patagónico de Ciencias Sociales y Humanas; Argentina
Fil: de Azevedo, Soledad. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Centro Nacional Patagónico. Instituto Patagónico de Ciencias Sociales y Humanas; Argentina
Fil: Delrieux, Claudio Augusto. Universidad Nacional del Sur. Departamento de Ingeniería Eléctrica y de Computadoras. Laboratorio de Ciencias de Las Imágenes; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Fil: Gonzalez-Jose, Rolando. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Centro Nacional Patagónico. Instituto Patagónico de Ciencias Sociales y Humanas; Argentina
3rd Practical Machine Learning for Developing Countries: learning under limited/low resource scenarios
Argentina
Comité organizador del Practical Machine Learning for Developing Countries
Materia
SEGMENTATION
3D RECONSTRUCTION
CONVOLUTIONAL NEURAL NETWORKS
RESPIRATORY HEALTHCARE
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/225584
Acceder
id CONICETDig_b647c2d6a2990f672979e05176d147a8
oai_identifier_str oai:ri.conicet.gov.ar:11336/225584
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Encoding upper nasal airway structure with U-Net for respiratory healthcare applicationsPazos, Bruno AlfredoNavarro, Jose Pablode Azevedo, SoledadDelrieux, Claudio AugustoGonzalez-Jose, RolandoSEGMENTATION3D RECONSTRUCTIONCONVOLUTIONAL NEURAL NETWORKSRESPIRATORY HEALTHCAREhttps://purl.org/becyt/ford/2.11https://purl.org/becyt/ford/2The human upper nasal airway is an anatomical structure with a complex geometry that performs essential functions required by the rest of the respiratory system. An accurate and precise segmentation process that captures its intricate shape and variability becomes indispensable to fully understand its performance under different circumstances and to study its anatomy from multiple perspectives. As currently performed, the manual or semi-automatic segmentation process for these structures is extremely time-consuming, may demand extensive manual post-processing steps to correct over-or under-segmentation, and is subject to considerable intra- and inter-operator variance. Further, in developing countries, healthcare institutions modernize their medical imaging devices at different rates;thus, specialists and proposed solutions have to deal with a wide range of image characteristics and quality variability to execute their diagnostics. In this paper we develop an automatic segmentation strategy for the human upper nasal airway, based on a deep convolutional network trained with >3000 CT scans acquired from different devices of a national hospital in Argentina, Hospital Italiano de Buenos Aires (2010). This  process achieves a remarkable preliminary results with a low error rate (0.07%) and an acceptable similarity score (86.9%).Fil: Pazos, Bruno Alfredo. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Centro Nacional Patagónico. Instituto Patagónico de Ciencias Sociales y Humanas; ArgentinaFil: Navarro, Jose Pablo. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Centro Nacional Patagónico. Instituto Patagónico de Ciencias Sociales y Humanas; ArgentinaFil: de Azevedo, Soledad. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Centro Nacional Patagónico. Instituto Patagónico de Ciencias Sociales y Humanas; ArgentinaFil: Delrieux, Claudio Augusto. Universidad Nacional del Sur. Departamento de Ingeniería Eléctrica y de Computadoras. Laboratorio de Ciencias de Las Imágenes; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; ArgentinaFil: Gonzalez-Jose, Rolando. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Centro Nacional Patagónico. Instituto Patagónico de Ciencias Sociales y Humanas; Argentina3rd Practical Machine Learning for Developing Countries: learning under limited/low resource scenariosArgentinaComité organizador del Practical Machine Learning for Developing CountriesComité organizador del Practical Machine Learning for Developing Countries2022info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObjectWorkshopBookhttp://purl.org/coar/resource_type/c_5794info:ar-repo/semantics/documentoDeConferenciaapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/225584Encoding upper nasal airway structure with U-Net for respiratory healthcare applications; 3rd Practical Machine Learning for Developing Countries: learning under limited/low resource scenarios; Argentina; 2022; 1-7CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://pml4dc.github.io/iclr2022/papers.htmlInternacionalinfo:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-29T09:35:14Zoai:ri.conicet.gov.ar:11336/225584instacron: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 09:35:14.523CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Encoding upper nasal airway structure with U-Net for respiratory healthcare applications
title Encoding upper nasal airway structure with U-Net for respiratory healthcare applications
spellingShingle Encoding upper nasal airway structure with U-Net for respiratory healthcare applications
Pazos, Bruno Alfredo
SEGMENTATION
3D RECONSTRUCTION
CONVOLUTIONAL NEURAL NETWORKS
RESPIRATORY HEALTHCARE
title_short Encoding upper nasal airway structure with U-Net for respiratory healthcare applications
title_full Encoding upper nasal airway structure with U-Net for respiratory healthcare applications
title_fullStr Encoding upper nasal airway structure with U-Net for respiratory healthcare applications
title_full_unstemmed Encoding upper nasal airway structure with U-Net for respiratory healthcare applications
title_sort Encoding upper nasal airway structure with U-Net for respiratory healthcare applications
dc.creator.none.fl_str_mv Pazos, Bruno Alfredo
Navarro, Jose Pablo
de Azevedo, Soledad
Delrieux, Claudio Augusto
Gonzalez-Jose, Rolando
author Pazos, Bruno Alfredo
author_facet Pazos, Bruno Alfredo
Navarro, Jose Pablo
de Azevedo, Soledad
Delrieux, Claudio Augusto
Gonzalez-Jose, Rolando
author_role author
author2 Navarro, Jose Pablo
de Azevedo, Soledad
Delrieux, Claudio Augusto
Gonzalez-Jose, Rolando
author2_role author
author
author
author
dc.subject.none.fl_str_mv SEGMENTATION
3D RECONSTRUCTION
CONVOLUTIONAL NEURAL NETWORKS
RESPIRATORY HEALTHCARE
topic SEGMENTATION
3D RECONSTRUCTION
CONVOLUTIONAL NEURAL NETWORKS
RESPIRATORY HEALTHCARE
purl_subject.fl_str_mv https://purl.org/becyt/ford/2.11
https://purl.org/becyt/ford/2
dc.description.none.fl_txt_mv The human upper nasal airway is an anatomical structure with a complex geometry that performs essential functions required by the rest of the respiratory system. An accurate and precise segmentation process that captures its intricate shape and variability becomes indispensable to fully understand its performance under different circumstances and to study its anatomy from multiple perspectives. As currently performed, the manual or semi-automatic segmentation process for these structures is extremely time-consuming, may demand extensive manual post-processing steps to correct over-or under-segmentation, and is subject to considerable intra- and inter-operator variance. Further, in developing countries, healthcare institutions modernize their medical imaging devices at different rates;thus, specialists and proposed solutions have to deal with a wide range of image characteristics and quality variability to execute their diagnostics. In this paper we develop an automatic segmentation strategy for the human upper nasal airway, based on a deep convolutional network trained with >3000 CT scans acquired from different devices of a national hospital in Argentina, Hospital Italiano de Buenos Aires (2010). This  process achieves a remarkable preliminary results with a low error rate (0.07%) and an acceptable similarity score (86.9%).
Fil: Pazos, Bruno Alfredo. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Centro Nacional Patagónico. Instituto Patagónico de Ciencias Sociales y Humanas; Argentina
Fil: Navarro, Jose Pablo. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Centro Nacional Patagónico. Instituto Patagónico de Ciencias Sociales y Humanas; Argentina
Fil: de Azevedo, Soledad. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Centro Nacional Patagónico. Instituto Patagónico de Ciencias Sociales y Humanas; Argentina
Fil: Delrieux, Claudio Augusto. Universidad Nacional del Sur. Departamento de Ingeniería Eléctrica y de Computadoras. Laboratorio de Ciencias de Las Imágenes; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Fil: Gonzalez-Jose, Rolando. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Centro Nacional Patagónico. Instituto Patagónico de Ciencias Sociales y Humanas; Argentina
3rd Practical Machine Learning for Developing Countries: learning under limited/low resource scenarios
Argentina
Comité organizador del Practical Machine Learning for Developing Countries
description The human upper nasal airway is an anatomical structure with a complex geometry that performs essential functions required by the rest of the respiratory system. An accurate and precise segmentation process that captures its intricate shape and variability becomes indispensable to fully understand its performance under different circumstances and to study its anatomy from multiple perspectives. As currently performed, the manual or semi-automatic segmentation process for these structures is extremely time-consuming, may demand extensive manual post-processing steps to correct over-or under-segmentation, and is subject to considerable intra- and inter-operator variance. Further, in developing countries, healthcare institutions modernize their medical imaging devices at different rates;thus, specialists and proposed solutions have to deal with a wide range of image characteristics and quality variability to execute their diagnostics. In this paper we develop an automatic segmentation strategy for the human upper nasal airway, based on a deep convolutional network trained with >3000 CT scans acquired from different devices of a national hospital in Argentina, Hospital Italiano de Buenos Aires (2010). This  process achieves a remarkable preliminary results with a low error rate (0.07%) and an acceptable similarity score (86.9%).
publishDate 2022
dc.date.none.fl_str_mv 2022
dc.type.none.fl_str_mv info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/conferenceObject
Workshop
Book
http://purl.org/coar/resource_type/c_5794
info:ar-repo/semantics/documentoDeConferencia
status_str publishedVersion
format conferenceObject
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/225584
Encoding upper nasal airway structure with U-Net for respiratory healthcare applications; 3rd Practical Machine Learning for Developing Countries: learning under limited/low resource scenarios; Argentina; 2022; 1-7
CONICET Digital
CONICET
url http://hdl.handle.net/11336/225584
identifier_str_mv Encoding upper nasal airway structure with U-Net for respiratory healthcare applications; 3rd Practical Machine Learning for Developing Countries: learning under limited/low resource scenarios; Argentina; 2022; 1-7
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://pml4dc.github.io/iclr2022/papers.html
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.coverage.none.fl_str_mv Internacional
dc.publisher.none.fl_str_mv Comité organizador del Practical Machine Learning for Developing Countries
publisher.none.fl_str_mv Comité organizador del Practical Machine Learning for Developing Countries
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_ 1844613096329445376
score 13.070432

Publicaciones similares