<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>3381</id>
    <completedYear/>
    <publishedYear>2022</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>267</pageFirst>
    <pageLast>272</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>Springer Vieweg</publisherName>
    <publisherPlace>Wiesbaden</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2022-04-06</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Classification of Vascular Malformations Based on T2 STIR Magnetic Resonance Imaging</title>
    <abstract language="eng">Vascular malformations (VMs) are a rare condition. They can be categorized into high-ﬂow and low-ﬂow VMs, which is a challenging task for radiologists. In this work, a very heterogeneous set of MRI images with only rough annotations are used for classification with a convolutional neural network. The main focus is to describe the challenging data set and strategies to deal with such data in terms of preprocessing, annotation usage and choice of the network architecture. We achieved a classification result of 89.47 % F1-score with a 3D ResNet 18.</abstract>
    <parentTitle language="eng">Bildverarbeitung für die Medizin 2022: Proceedings, German Workshop on Medical Image Computing, Heidelberg, June 26-28, 2022</parentTitle>
    <identifier type="doi">10.1007/978-3-658-36932-3_57</identifier>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Danilo Weber Nunes</author>
    <author>Michael Hammer</author>
    <author>Simone Hammer</author>
    <author>Wibke Uller</author>
    <author>Christoph Palm</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Deep Learning</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Magnetic Resonance Imaging</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Vascular Malformations</value>
    </subject>
    <collection role="ddc" number="0">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="ddc" number="6">Technik, Medizin, angewandte Wissenschaften</collection>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="institutes" number="RCBE">Regensburg Center of Biomedical Engineering - RCBE</collection>
    <collection role="persons" number="palmremic">Palm, Christoph (Prof. Dr.) - ReMIC</collection>
    <collection role="othforschungsschwerpunkt" number="16314">Lebenswissenschaften und Ethik</collection>
    <collection role="institutes" number="">Labor Regensburg Medical Image Computing (ReMIC)</collection>
  </doc>
  <doc>
    <id>7021</id>
    <completedYear/>
    <publishedYear>2024</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>1</pageFirst>
    <pageLast>15</pageLast>
    <pageNumber/>
    <edition>Pre-press</edition>
    <issue/>
    <volume/>
    <type>article</type>
    <publisherName>IOP Press</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Deep learning-based differentiation of peripheral high-flow and low-flow vascular malformations in T2-weighted short tau inversion recovery MRI</title>
    <abstract language="eng">BACKGROUND&#13;
Differentiation of high-flow from low-flow vascular malformations (VMs) is crucial for therapeutic management of this orphan disease.&#13;
OBJECTIVE&#13;
A convolutional neural network (CNN) was evaluated for differentiation of peripheral vascular malformations (VMs) on T2-weighted short tau inversion recovery (STIR) MRI.&#13;
METHODS&#13;
527 MRIs (386 low-flow and 141 high-flow VMs) were randomly divided into training, validation and test set for this single-center study. 1) Results of the CNN's diagnostic performance were compared with that of two expert and four junior radiologists. 2) The influence of CNN's prediction on the radiologists' performance and diagnostic certainty was evaluated. 3) Junior radiologists' performance after self-training was compared with that of the CNN.&#13;
RESULTS&#13;
Compared with the expert radiologists the CNN achieved similar accuracy (92% vs. 97%, p = 0.11), sensitivity (80% vs. 93%, p = 0.16) and specificity (97% vs. 100%, p = 0.50). In comparison to the junior radiologists, the CNN had a higher specificity and accuracy (97% vs. 80%, p &lt;  0.001; 92% vs. 77%, p &lt;  0.001). CNN assistance had no significant influence on their diagnostic performance and certainty. After self-training, the junior radiologists' specificity and accuracy improved and were comparable to that of the CNN.&#13;
CONCLUSIONS&#13;
Diagnostic performance of the CNN for differentiating high-flow from low-flow VM was comparable to that of expert radiologists. CNN did not significantly improve the simulated daily practice of junior radiologists, self-training was more effective.</abstract>
    <parentTitle language="eng">Clinical hemorheology and microcirculation</parentTitle>
    <identifier type="doi">10.3233/CH-232071</identifier>
    <identifier type="pmid">38306026</identifier>
    <enrichment key="opus.import.date">2024-02-09T09:33:27+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Simone Hammer</author>
    <author>Danilo Weber Nunes</author>
    <author>Michael Hammer</author>
    <author>Florian Zeman</author>
    <author>Michael Akers</author>
    <author>Andrea Götz</author>
    <author>Annika Balla</author>
    <author>Michael Christian Doppler</author>
    <author>Claudia Fellner</author>
    <author>Natascha Da Platz Batista Silva</author>
    <author>Sylvia Thurn</author>
    <author>Niklas Verloh</author>
    <author>Christian Stroszczynski</author>
    <author>Walter Alexander Wohlgemuth</author>
    <author>Christoph Palm</author>
    <author>Wibke Uller</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>magnetic resonance imaging</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>deep learning</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Vascular malformation</value>
    </subject>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="persons" number="palmremic">Palm, Christoph (Prof. Dr.) - ReMIC</collection>
    <collection role="othforschungsschwerpunkt" number="16314">Lebenswissenschaften und Ethik</collection>
    <collection role="institutes" number="">Labor Regensburg Medical Image Computing (ReMIC)</collection>
  </doc>
</export-example>
