4875738
doi
10.5281/zenodo.4875738
oai:zenodo.org:4875738
user-covid-19
Iñaki Soto Rey
IT-Infrastructure for Translational Medical Research, Faculty of Applied Computer Science, Faculty of Medicine, University of Augsburg, Germany
Frank Kramer
IT-Infrastructure for Translational Medical Research, Faculty of Applied Computer Science, Faculty of Medicine, University of Augsburg, Germany
Robust Chest CT Image Segmentation of COVID-19 Lung Infection based on limited data
Dominik Müller
IT-Infrastructure for Translational Medical Research, Faculty of Applied Computer Science, Faculty of Medicine, University of Augsburg, Germany
url:https://github.com/frankkramer-lab/covid19.MIScnn
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/legalcode
COVID-19
segmentation
computed tomography
deep learning
artificial intelligence
clinical decision support
medical image analysis
<p><strong>Background:</strong> The coronavirus disease 2019 (COVID-19) affects billions of lives around the world and has a significant impact on public healthcare. For quantitative assessment and disease monitoring medical imaging like computed tomography offers great potential as alternative to RT-PCR methods. For this reason, automated image segmentation is highly desired as clinical decision support. However, publicly available COVID-19 imaging data is limited which leads to overfitting of traditional approaches.</p>
<p><strong>Methods:</strong> To address this problem, we propose an innovative automated segmentation pipeline for COVID-19 infected regions, which is able to handle small datasets by utilization as variant databases. Our method focuses on on-the-fly generation of unique and random image patches for training by performing several preprocessing methods and exploiting extensive data augmentation. For further reduction of the overfitting risk, we implemented a standard 3D U-Net architecture instead of new or computational complex neural network architectures.</p>
<p><strong>Results:</strong> Through a k-fold cross-validation on 20 CT scans as training and validation of COVID-19, we were able to develop a highly accurate as well as robust segmentation model for lungs and COVID-19 infected regions without overfitting on limited data. We performed an in-detail analysis and discussion on the robustness of our pipeline through a sensitivity analysis based on the cross-validation and impact on model generalizability of applied preprocessing techniques. Our method achieved Dice similarity coefficients for COVID-19 infection between predicted and annotated segmentation from radiologists of 0.804 on validation and 0.661 on a separate testing set consisting of 100 patients.</p>
<p><strong>Conclusions:</strong> We demonstrated that the proposed method outperforms related approaches, advances the state-of-the-art for COVID-19 segmentation and improves robust medical image analysis based on limited data.</p>
<p>The code and model are available under the following link:<br>
https://github.com/frankkramer-lab/covid19.MIScnn</p>
Code: https://github.com/frankkramer-lab/covid19.MIScnn
Zenodo
2021-05-30
info:eu-repo/semantics/other
3902292
user-covid-19
2.0
1622468892.730489
4260382
md5:2a67cc8a134b7f89996e1321e4465402
https://zenodo.org/records/4875738/files/supplementary.zip
2524272040
md5:20ac6f5186d7e98edbd54bc547d50ad6
https://zenodo.org/records/4875738/files/models.zip
662048089
md5:74c65427c595986c41d74ed5b1ee9bfc
https://zenodo.org/records/4875738/files/evaluation.zip
17639032
md5:3fb40f3f9c05f224ec22421a7b9ad450
https://zenodo.org/records/4875738/files/predictions.zip
public
https://github.com/frankkramer-lab/covid19.MIScnn
Is supplement to
url
10.5281/zenodo.3902292
isVersionOf
doi