Dataset Open Access

Robust Chest CT Image Segmentation of COVID-19 Lung Infection based on limited data

Dominik Müller; Iñaki Soto Rey; Frank Kramer


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">COVID-19</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">segmentation</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">computed tomography</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">deep learning</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">artificial intelligence</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">clinical decision support</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">medical image analysis</subfield>
  </datafield>
  <controlfield tag="005">20201119002705.0</controlfield>
  <datafield tag="500" ind1=" " ind2=" ">
    <subfield code="a">Code: https://github.com/frankkramer-lab/covid19.MIScnn</subfield>
  </datafield>
  <controlfield tag="001">4279398</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">IT-Infrastructure for Translational Medical Research, Faculty of Applied Computer Science, Faculty of Medicine, University of Augsburg, Germany</subfield>
    <subfield code="0">(orcid)0000-0003-3061-5818</subfield>
    <subfield code="a">Iñaki Soto Rey</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">IT-Infrastructure for Translational Medical Research, Faculty of Applied Computer Science, Faculty of Medicine, University of Augsburg, Germany</subfield>
    <subfield code="0">(orcid)0000-0002-2857-7122</subfield>
    <subfield code="a">Frank Kramer</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">9163457</subfield>
    <subfield code="z">md5:a91ecfc9972194a30438853579dc3165</subfield>
    <subfield code="u">https://zenodo.org/record/4279398/files/evaluation.spe.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">158662589</subfield>
    <subfield code="z">md5:e586bd041f563bbd18d0ec0130ac2fc9</subfield>
    <subfield code="u">https://zenodo.org/record/4279398/files/evaluation.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">2524272040</subfield>
    <subfield code="z">md5:20ac6f5186d7e98edbd54bc547d50ad6</subfield>
    <subfield code="u">https://zenodo.org/record/4279398/files/models.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">17639032</subfield>
    <subfield code="z">md5:3fb40f3f9c05f224ec22421a7b9ad450</subfield>
    <subfield code="u">https://zenodo.org/record/4279398/files/predictions.zip</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2020-06-29</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire_data</subfield>
    <subfield code="p">user-covid-19</subfield>
    <subfield code="p">user-zenodo</subfield>
    <subfield code="o">oai:zenodo.org:4279398</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">IT-Infrastructure for Translational Medical Research, Faculty of Applied Computer Science, Faculty of Medicine, University of Augsburg, Germany</subfield>
    <subfield code="0">(orcid)0000-0003-0838-9885</subfield>
    <subfield code="a">Dominik Müller</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Robust Chest CT Image Segmentation of COVID-19 Lung Infection based on limited data</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-covid-19</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-zenodo</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 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 coronavirus disease 2019 (COVID-19) affects billions of&lt;br&gt;
lives around the world and has a significant impact on public&lt;br&gt;
healthcare. Due to rising skepticism towards the sensitivity of&lt;br&gt;
RT-PCR as screening method, medical imaging like computed&lt;br&gt;
tomography offers great potential as alternative. For this&lt;br&gt;
reason, automated image segmentation is highly desired as&lt;br&gt;
clinical decision support for quantitative assessment and&lt;br&gt;
disease monitoring. However, publicly available COVID-19&lt;br&gt;
imaging data is limited which leads to overfitting of traditional&lt;br&gt;
approaches. To address this problem, we propose an innovative&lt;br&gt;
automated segmentation pipeline for COVID-19 infected&lt;br&gt;
regions, which is able to handle small datasets by utilization as&lt;br&gt;
variant databases. Our method focuses on on-the-fly&lt;br&gt;
generation of unique and random image patches for training&lt;br&gt;
by performing several preprocessing methods and exploiting&lt;br&gt;
extensive data augmentation. For further reduction of the&lt;br&gt;
overfitting risk, we implemented a standard 3D U-Net&lt;br&gt;
architecture instead of new or computational complex neural&lt;br&gt;
network architectures. Through a 5-fold cross-validation on 20&lt;br&gt;
CT scans of COVID-19 patients, we were able to develop a&lt;br&gt;
highly accurate as well as robust segmentation model for lungs&lt;br&gt;
and COVID-19 infected regions without overfitting on the&lt;br&gt;
limited data. Our method achieved Dice similarity coefficients&lt;br&gt;
of 0.956 for lungs and 0.761 for infection. We demonstrated&lt;br&gt;
that the proposed method outperforms related approaches,&lt;br&gt;
advances the state-of-the-art for COVID-19 segmentation and&lt;br&gt;
improves medical image analysis with limited data. The code&lt;br&gt;
and model are available under the following link:&lt;br&gt;
https://github.com/frankkramer-lab/covid19.MIScnn&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">url</subfield>
    <subfield code="i">isSupplementTo</subfield>
    <subfield code="a">https://github.com/frankkramer-lab/covid19.MIScnn</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.3902292</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.4279398</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">dataset</subfield>
  </datafield>
</record>
1,656
441
views
downloads
All versions This version
Views 1,656302
Downloads 44162
Data volume 605.0 GB48.2 GB
Unique views 1,433270
Unique downloads 19126

Share

Cite as