Unsupervised detection of disturbances in 2D radiographs

Descripción del Articulo

This work was supported by grant 234-2015-FONDECYT (Master Program) from Cienciactiva of CONCYTEC-PERU and German BMBF research campus MODAL (grant no. 3FO18501). The authors thank CiTeSoft-UNSA for the database access. The authors report no conflicts of interest.
Detalles Bibliográficos
Autores: Estacio L., Ehlke M., Tack A., Castro E., Lamecker H., Mora R., Zachow S.
Formato: objeto de conferencia
Fecha de Publicación:2021
Institución:Consejo Nacional de Ciencia Tecnología e Innovación
Repositorio:CONCYTEC-Institucional
Lenguaje:inglés
OAI Identifier:oai:repositorio.concytec.gob.pe:20.500.12390/3075
Enlace del recurso:https://hdl.handle.net/20.500.12390/3075
https://doi.org/10.1109/ISBI48211.2021.9434091
Nivel de acceso:acceso abierto
Materia:Generative models
Anomaly detection
https://purl.org/pe-repo/ocde/ford#3.02.12
id CONC_e283b860782402f6d88f39fd9945e02b
oai_identifier_str oai:repositorio.concytec.gob.pe:20.500.12390/3075
network_acronym_str CONC
network_name_str CONCYTEC-Institucional
repository_id_str 4689
dc.title.none.fl_str_mv Unsupervised detection of disturbances in 2D radiographs
title Unsupervised detection of disturbances in 2D radiographs
spellingShingle Unsupervised detection of disturbances in 2D radiographs
Estacio L.
Generative models
Anomaly detection
https://purl.org/pe-repo/ocde/ford#3.02.12
title_short Unsupervised detection of disturbances in 2D radiographs
title_full Unsupervised detection of disturbances in 2D radiographs
title_fullStr Unsupervised detection of disturbances in 2D radiographs
title_full_unstemmed Unsupervised detection of disturbances in 2D radiographs
title_sort Unsupervised detection of disturbances in 2D radiographs
author Estacio L.
author_facet Estacio L.
Ehlke M.
Tack A.
Castro E.
Lamecker H.
Mora R.
Zachow S.
author_role author
author2 Ehlke M.
Tack A.
Castro E.
Lamecker H.
Mora R.
Zachow S.
author2_role author
author
author
author
author
author
dc.contributor.author.fl_str_mv Estacio L.
Ehlke M.
Tack A.
Castro E.
Lamecker H.
Mora R.
Zachow S.
dc.subject.none.fl_str_mv Generative models
topic Generative models
Anomaly detection
https://purl.org/pe-repo/ocde/ford#3.02.12
dc.subject.es_PE.fl_str_mv Anomaly detection
dc.subject.ocde.none.fl_str_mv https://purl.org/pe-repo/ocde/ford#3.02.12
description This work was supported by grant 234-2015-FONDECYT (Master Program) from Cienciactiva of CONCYTEC-PERU and German BMBF research campus MODAL (grant no. 3FO18501). The authors thank CiTeSoft-UNSA for the database access. The authors report no conflicts of interest.
publishDate 2021
dc.date.accessioned.none.fl_str_mv 2024-05-30T23:13:38Z
dc.date.available.none.fl_str_mv 2024-05-30T23:13:38Z
dc.date.issued.fl_str_mv 2021
dc.type.none.fl_str_mv info:eu-repo/semantics/conferenceObject
format conferenceObject
dc.identifier.uri.none.fl_str_mv https://hdl.handle.net/20.500.12390/3075
dc.identifier.doi.none.fl_str_mv https://doi.org/10.1109/ISBI48211.2021.9434091
dc.identifier.scopus.none.fl_str_mv 2-s2.0-85107194158
url https://hdl.handle.net/20.500.12390/3075
https://doi.org/10.1109/ISBI48211.2021.9434091
identifier_str_mv 2-s2.0-85107194158
dc.language.iso.none.fl_str_mv eng
language eng
dc.relation.ispartof.none.fl_str_mv Proceedings - International Symposium on Biomedical Imaging
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv IEEE Computer Society
publisher.none.fl_str_mv IEEE Computer Society
dc.source.none.fl_str_mv reponame:CONCYTEC-Institucional
instname:Consejo Nacional de Ciencia Tecnología e Innovación
instacron:CONCYTEC
instname_str Consejo Nacional de Ciencia Tecnología e Innovación
instacron_str CONCYTEC
institution CONCYTEC
reponame_str CONCYTEC-Institucional
collection CONCYTEC-Institucional
repository.name.fl_str_mv Repositorio Institucional CONCYTEC
repository.mail.fl_str_mv repositorio@concytec.gob.pe
_version_ 1844883024917823488
spelling Publicationrp08874600rp08873600rp08877600rp08872600rp08876600rp06835600rp08875600Estacio L.Ehlke M.Tack A.Castro E.Lamecker H.Mora R.Zachow S.2024-05-30T23:13:38Z2024-05-30T23:13:38Z2021https://hdl.handle.net/20.500.12390/3075https://doi.org/10.1109/ISBI48211.2021.94340912-s2.0-85107194158This work was supported by grant 234-2015-FONDECYT (Master Program) from Cienciactiva of CONCYTEC-PERU and German BMBF research campus MODAL (grant no. 3FO18501). The authors thank CiTeSoft-UNSA for the database access. The authors report no conflicts of interest.We present a method based on a generative model for detection of disturbances such as prosthesis, screws, zippers, and metals in 2D radiographs. The generative model is trained in an unsupervised fashion using clinical radiographs as well as simulated data, none of which contain disturbances. Our approach employs a latent space consistency loss which has the benefit of identifying similarities, and is enforced to reconstruct X-rays without disturbances. In order to detect images with disturbances, an anomaly score is computed also employing the Frechet distance between the input X-ray and the reconstructed one using our generative model. Validation was performed using clinical pelvis radiographs. We achieved an AUC of 0.77 and 0.83 with clinical and synthetic data, respectively. The results demonstrated a good accuracy of our method for detecting outliers as well as the advantage of utilizing synthetic data.Fondo Nacional de Desarrollo Científico y Tecnológico - FondecytengIEEE Computer SocietyProceedings - International Symposium on Biomedical Imaginginfo:eu-repo/semantics/openAccessGenerative modelsAnomaly detection-1https://purl.org/pe-repo/ocde/ford#3.02.12-1Unsupervised detection of disturbances in 2D radiographsinfo:eu-repo/semantics/conferenceObjectreponame:CONCYTEC-Institucionalinstname:Consejo Nacional de Ciencia Tecnología e Innovacióninstacron:CONCYTEC#PLACEHOLDER_PARENT_METADATA_VALUE#20.500.12390/3075oai:repositorio.concytec.gob.pe:20.500.12390/30752024-05-30 15:42:46.512http://purl.org/coar/access_right/c_14cbinfo:eu-repo/semantics/closedAccessmetadata only accesshttps://repositorio.concytec.gob.peRepositorio Institucional CONCYTECrepositorio@concytec.gob.pe#PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE#<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="bf2c9197-d863-43c5-9108-65cb8259abf9"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Language>eng</Language> <Title>Unsupervised detection of disturbances in 2D radiographs</Title> <PublishedIn> <Publication> <Title>Proceedings - International Symposium on Biomedical Imaging</Title> </Publication> </PublishedIn> <PublicationDate>2021</PublicationDate> <DOI>https://doi.org/10.1109/ISBI48211.2021.9434091</DOI> <SCP-Number>2-s2.0-85107194158</SCP-Number> <Authors> <Author> <DisplayName>Estacio L.</DisplayName> <Person id="rp08874" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Ehlke M.</DisplayName> <Person id="rp08873" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Tack A.</DisplayName> <Person id="rp08877" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Castro E.</DisplayName> <Person id="rp08872" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Lamecker H.</DisplayName> <Person id="rp08876" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Mora R.</DisplayName> <Person id="rp06835" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Zachow S.</DisplayName> <Person id="rp08875" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>IEEE Computer Society</DisplayName> <OrgUnit /> </Publisher> </Publishers> <Keyword>Generative models</Keyword> <Keyword>Anomaly detection</Keyword> <Abstract>We present a method based on a generative model for detection of disturbances such as prosthesis, screws, zippers, and metals in 2D radiographs. The generative model is trained in an unsupervised fashion using clinical radiographs as well as simulated data, none of which contain disturbances. Our approach employs a latent space consistency loss which has the benefit of identifying similarities, and is enforced to reconstruct X-rays without disturbances. In order to detect images with disturbances, an anomaly score is computed also employing the Frechet distance between the input X-ray and the reconstructed one using our generative model. Validation was performed using clinical pelvis radiographs. We achieved an AUC of 0.77 and 0.83 with clinical and synthetic data, respectively. The results demonstrated a good accuracy of our method for detecting outliers as well as the advantage of utilizing synthetic data.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication> -1
score 13.425363
Unsupervised detection of disturbances in 2D radiographs
Nota importante:
La información contenida en este registro es de entera responsabilidad de la institución que gestiona el repositorio institucional donde esta contenido este documento o set de datos. El CONCYTEC no se hace responsable por los contenidos (publicaciones y/o datos) accesibles a través del Repositorio Nacional Digital de Ciencia, Tecnología e Innovación de Acceso Abierto (ALICIA).

Ejemplares Similares