<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>6243</id>
    <completedYear/>
    <publishedYear>2017</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>1013</pageFirst>
    <pageLast>1020</pageLast>
    <pageNumber>8</pageNumber>
    <edition/>
    <issue>6</issue>
    <volume>12</volume>
    <type>article</type>
    <publisherName>Springer</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2017-03-29</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Addressing multi-label imbalance problem of Surgical Tool Detection using CNN</title>
    <abstract language="eng">Purpose: A fully automated surgical tool detection framework is proposed for endoscopic video streams. State-of-the-art surgical tool detection methods rely on supervised one-vs-all or multi-class classification techniques, completely ignoring the co-occurrence relationship of the tools and the associated class imbalance.&#13;
&#13;
Methods: In this paper, we formulate tool detection as a multi-label classification task where tool co-occurrences are treated as separate classes. In addition, imbalance on tool co-occurrences is analyzed and stratification techniques are employed to address the imbalance during Convolutional Neural Network (CNN) training. Moreover, temporal smoothing is introduced as an online post-processing step to enhance run time prediction.&#13;
&#13;
Results: Quantitative analysis is performed on the M2CAI16 tool detection dataset to highlight the importance of stratification, temporal smoothing and the overall framework for tool detection. &#13;
&#13;
Conclusion: The analysis on tool imbalance, backed by the empirical results indicates the need and superiority of the proposed framework over state-of-the-art techniques.</abstract>
    <parentTitle language="eng">International Journal of Computer Assisted Radiology and Surgery</parentTitle>
    <identifier type="doi">10.1007/s11548-017-1565-x</identifier>
    <identifier type="url">https://link.springer.com/article/10.1007/s11548-017-1565-x</identifier>
    <note>Selected for final oral presentation</note>
    <enrichment key="PeerReviewed">yes</enrichment>
    <author>Manish Sahu</author>
    <submitter>Manish Sahu</submitter>
    <author>Anirban Mukhopadhyay</author>
    <author>Angelika Szengel</author>
    <author>Stefan Zachow</author>
    <collection role="institutes" number="vis">Visual Data Analysis</collection>
    <collection role="institutes" number="medplan">Therapy Planning</collection>
    <collection role="persons" number="zachow">Zachow, Stefan</collection>
    <collection role="projects" number="MODAL-MedLab">MODAL-MedLab</collection>
    <collection role="projects" number="BMBF-BiOPAss">BMBF-BiOPAss</collection>
    <collection role="projects" number="MODAL-Gesamt">MODAL-Gesamt</collection>
    <collection role="institutes" number="VDcC">Visual and Data-centric Computing</collection>
    <file>https://opus4.kobv.de/opus4-zib/files/6243/preprint.pdf</file>
  </doc>
</export-example>
