<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>8120</id>
    <completedYear/>
    <publishedYear>2021</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>367</pageFirst>
    <pageLast>370</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Unsupervised Detection of Disturbances in 2D Radiographs</title>
    <abstract language="eng">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>
    <parentTitle language="eng">2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)</parentTitle>
    <identifier type="doi">10.1109/ISBI48211.2021.9434091</identifier>
    <enrichment key="PeerReviewed">yes</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <author>Laura Estacio</author>
    <submitter>Alexander Tack</submitter>
    <author>Moritz Ehlke</author>
    <author>Alexander Tack</author>
    <author>Eveling Castro-Gutierrez</author>
    <author>Hans Lamecker</author>
    <author>Rensso Mora</author>
    <author>Stefan Zachow</author>
    <collection role="institutes" number="vis">Visual Data Analysis</collection>
    <collection role="persons" number="ehlke">Ehlke, Moritz</collection>
    <collection role="persons" number="lamecker">Lamecker, Hans</collection>
    <collection role="persons" number="zachow">Zachow, Stefan</collection>
    <collection role="projects" number="BSRT-3DFromXray">BSRT-3DFromXray</collection>
    <collection role="projects" number="MODAL-MedLab">MODAL-MedLab</collection>
    <collection role="projects" number="Overload-PrevOP-SP4">Overload-PrevOP-SP4</collection>
    <collection role="projects" number="MODAL-Gesamt">MODAL-Gesamt</collection>
    <collection role="institutes" number="VDcC">Visual and Data-centric Computing</collection>
  </doc>
</export-example>
