Unsupervised detection of disturbances in 2D radiographs

Simple item page
dc.contributor.authorEstacio, Laura
dc.contributor.authorMora, Rensso
dc.contributor.authorMoritz, Ehlke
dc.contributor.authorLamecker, Hans
dc.contributor.authorTack, Alexander
dc.contributor.authorZachow, Stefan
dc.contributor.authorCastro, Eveling
dc.date.accessioned2022-03-12T03:52:38Z
dc.date.available2022-03-12T03:52:38Z
dc.date.issued2021
dc.description.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. © 2021 IEEE"es_PE
dc.description.uriTrabajo académicoes_PE
dc.identifier.doi10.1109/ISBI48211.2021.9434091es_PE
dc.identifier.issn19457928
dc.identifier.urihttps://hdl.handle.net/20.500.12590/17095
dc.language.isoenges_PE
dc.publisherIEEE Computer Societyes_PE
dc.publisher.countryPEes_PE
dc.relationinfo:eu-repo/semantics/articlees_PE
dc.relation.urihttps://www.scopus.com/record/display.uri?eid=2-s2.0-85107194158&origin=resultslist&sort=plf-f&src=s&nlo=&nlr=&nls=&sid=7dfce5cde9eda76399a7c5cb6b0ab407&sot=aff&sdt=cl&cluster=scopubyr%2c%222021%22%2ct&sl=48&s=AF-ID%28%22Universidad+Cat%c3%b3lica+San+Pablo%22+60105300%29&relpos=22&citeCnt=0&searchTerm=&featureToggles=FEATURE_NEW_DOC_DETAILS_EXPORT:1es_PE
dc.rightsinfo:eu-repo/semantics/restrictedAccesses_PE
dc.sourceUniversidad Católica San Pabloes_PE
dc.sourceRepositorio Institucional - UCSPes_PE
dc.subjectAnomaly detectiones_PE
dc.subjectGenerative modelses_PE
dc.subjectPelvic radiographses_PE
dc.subjectUnsupervised learninges_PE
dc.subject.ocdehttps://purl.org/pe-repo/ocde/ford#1.02.01es_PE
dc.titleUnsupervised detection of disturbances in 2D radiographses_PE
dc.typeinfo:eu-repo/semantics/article
dc.type.versioninfo:eu-repo/semantics/publishedVersiones_PE
renati.typehttps://purl.org/pe-repo/renati/type#trabajoAcademico
thesis.degree.disciplineCiencia de la Computaciónes_PE
thesis.degree.grantorUniversidad Católica San Pablo. Departamento de Ciencia de la Computaciónes_PE
Files
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Artículos - Ciencias de la Computación