January 30, 2018 Dataset Open Access

Sara Moccia; Gabriele Omodeo Vanone; Elena De Momi; Leonardo S. Mattos

MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nmm##2200000uu#4500</leader>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Frame selection, NBI endoscopy, machine learning, classification</subfield>
  </datafield>
  <controlfield tag="005">20200124192531.0</controlfield>
  <controlfield tag="001">1162784</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Politecnico di Milano</subfield>
    <subfield code="a">Gabriele Omodeo Vanone</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Politecnico di Milano</subfield>
    <subfield code="a">Elena De Momi</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Istituto Italiano di Tecnologia</subfield>
    <subfield code="a">Leonardo S. Mattos</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">171473464</subfield>
    <subfield code="z">md5:c624858e2dda6070cf2179ace28d8f10</subfield>
    <subfield code="u">https://zenodo.org/record/1162784/files/FRAMES.zip</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2018-01-30</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire_data</subfield>
    <subfield code="o">oai:zenodo.org:1162784</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Istituto Italiano di Tecnologia / Politecnico di Milano</subfield>
    <subfield code="0">(orcid)0000-0002-4494-8907</subfield>
    <subfield code="a">Sara Moccia</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">NBI-InfFrames</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://creativecommons.org/licenses/by-nc/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution Non Commercial 4.0 International</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;The&amp;nbsp;&lt;strong&gt;NBI-InfFrames &lt;/strong&gt;dataset&lt;strong&gt;&amp;nbsp;&lt;/strong&gt;aims to provide the surgical data science&amp;nbsp;community with a&amp;nbsp;labeled dataset for the identification of informative endoscopic video&amp;nbsp;frames.&amp;nbsp;&lt;/p&gt;

&lt;p&gt;It&amp;nbsp;is&amp;nbsp;composed&amp;nbsp;of 720&amp;nbsp;video frames. The frames are manually&amp;nbsp;extracted and labeled from 18 narrow-band laryngoscopic videos of 18 different patients affected by laryngeal spinocellular carcinoma (diagnosed after histopathological examination).&amp;nbsp;&lt;/p&gt;

&lt;p&gt;The frames include 180 informative (&lt;strong&gt;I&lt;/strong&gt;) video frames, 180 blurred (&lt;strong&gt;B&lt;/strong&gt;)&amp;nbsp;frames, 180 frames with saliva or specular reflections (&lt;strong&gt;S&lt;/strong&gt;) and 180 underexposed (&lt;strong&gt;U&lt;/strong&gt;) frames.&lt;/p&gt;

&lt;p&gt;The dataset was created for testing the method proposed in S. Moccia, et al. &amp;quot;&lt;em&gt;Learning-based classification of informative laryngoscopic frames.&lt;/em&gt;&amp;quot; COMPUTER METHODS AND PROGRAM IN BIOMEDICINE, (accepted for publication).&lt;/p&gt;

&lt;p&gt;The folder&lt;em&gt;&amp;nbsp;&lt;strong&gt;FRAMES.zip&lt;/strong&gt;&amp;nbsp;&lt;/em&gt;contains 3 subfolders (FOLD1, FOLD2, FOLD3), which are the 3 folds used for cross-validation purpose in the frame&amp;nbsp;classification performance assessment. Data separation in the folds is performed both at image- and patient-level.&lt;/p&gt;

&lt;p&gt;Each subfolder contains 4 folders relative to the four frame classes, i.e., &lt;strong&gt;I&lt;/strong&gt;, &lt;strong&gt;B&lt;/strong&gt;, &lt;strong&gt;S&lt;/strong&gt; and &lt;strong&gt;U&lt;/strong&gt;.&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.1162783</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.1162784</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">dataset</subfield>
  </datafield>
</record>