Dataset Open Access

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

Dominik Müller; Iñaki Soto Rey; Frank Kramer


DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.5281/zenodo.4279398</identifier>
  <creators>
    <creator>
      <creatorName>Dominik Müller</creatorName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0003-0838-9885</nameIdentifier>
      <affiliation>IT-Infrastructure for Translational Medical Research, Faculty of Applied Computer Science, Faculty of Medicine, University of Augsburg, Germany</affiliation>
    </creator>
    <creator>
      <creatorName>Iñaki Soto Rey</creatorName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0003-3061-5818</nameIdentifier>
      <affiliation>IT-Infrastructure for Translational Medical Research, Faculty of Applied Computer Science, Faculty of Medicine, University of Augsburg, Germany</affiliation>
    </creator>
    <creator>
      <creatorName>Frank Kramer</creatorName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-2857-7122</nameIdentifier>
      <affiliation>IT-Infrastructure for Translational Medical Research, Faculty of Applied Computer Science, Faculty of Medicine, University of Augsburg, Germany</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Robust Chest CT Image Segmentation of COVID-19 Lung Infection based on limited data</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2020</publicationYear>
  <subjects>
    <subject>COVID-19</subject>
    <subject>segmentation</subject>
    <subject>computed tomography</subject>
    <subject>deep learning</subject>
    <subject>artificial intelligence</subject>
    <subject>clinical decision support</subject>
    <subject>medical image analysis</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2020-06-29</date>
  </dates>
  <resourceType resourceTypeGeneral="Dataset"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/4279398</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsSupplementTo" resourceTypeGeneral="Software">https://github.com/frankkramer-lab/covid19.MIScnn</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.3902292</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/covid-19</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/zenodo</relatedIdentifier>
  </relatedIdentifiers>
  <version>1.0</version>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&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;</description>
    <description descriptionType="Other">Code: https://github.com/frankkramer-lab/covid19.MIScnn</description>
  </descriptions>
</resource>
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