TY - JOUR
T1 - Explainable COVID-19 detection using chest CT scans and deep learning
AU - Alshazly, Hammam
AU - Linse, Christoph
AU - Barth, Erhardt
AU - Martinetz, Thomas
N1 - Funding Information:
The work of Hammam Alshazly was funded by the Bundesministerium f?r Bildung und Forschung (BMBF) through the KI-Lab Project. The work of Christoph Linse was funded by the Bun-desministeriums f?r Wirtschaft und Energie (BMWi) through the Mittelstand 4.0-Kompetenzzentrum Kiel Project. The authors gratefully acknowledge the constructive feedback from J?rg Barkhausen from the Clinic for Radiology and Nuclear Medicine at the Universit?tsklinikum Schleswig-Holstein (UKSH), L?beck.
Publisher Copyright:
© 2021 by the authors. Licensee MDPI, Basel, Switzerland.
Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.
PY - 2021/1/11
Y1 - 2021/1/11
N2 - This paper explores how well deep learning models trained on chest CT images can diagnose COVID-19 infected people in a fast and automated process. To this end, we adopted advanced deep network architectures and proposed a transfer learning strategy using custom-sized input tailored for each deep architecture to achieve the best performance. We conducted extensive sets of experiments on two CT image datasets, namely, the SARS-CoV-2 CT-scan and the COVID19-CT. The results show superior performances for our models compared with previous studies. Our best models achieved average accuracy, precision, sensitivity, specificity, and F1-score values of 99.4%, 99.6%, 99.8%, 99.6%, and 99.4% on the SARS-CoV-2 dataset, and 92.9%, 91.3%, 93.7%, 92.2%, and 92.5% on the COVID19-CT dataset, respectively. For better interpretability of the results, we applied visualization techniques to provide visual explanations for the models’ predictions. Feature visualizations of the learned features show well-separated clusters representing CT images of COVID-19 and non-COVID-19 cases. Moreover, the visualizations indicate that our models are not only capable of identifying COVID-19 cases but also provide accurate localization of the COVID-19-associated regions, as indicated by well-trained radiologists.
AB - This paper explores how well deep learning models trained on chest CT images can diagnose COVID-19 infected people in a fast and automated process. To this end, we adopted advanced deep network architectures and proposed a transfer learning strategy using custom-sized input tailored for each deep architecture to achieve the best performance. We conducted extensive sets of experiments on two CT image datasets, namely, the SARS-CoV-2 CT-scan and the COVID19-CT. The results show superior performances for our models compared with previous studies. Our best models achieved average accuracy, precision, sensitivity, specificity, and F1-score values of 99.4%, 99.6%, 99.8%, 99.6%, and 99.4% on the SARS-CoV-2 dataset, and 92.9%, 91.3%, 93.7%, 92.2%, and 92.5% on the COVID19-CT dataset, respectively. For better interpretability of the results, we applied visualization techniques to provide visual explanations for the models’ predictions. Feature visualizations of the learned features show well-separated clusters representing CT images of COVID-19 and non-COVID-19 cases. Moreover, the visualizations indicate that our models are not only capable of identifying COVID-19 cases but also provide accurate localization of the COVID-19-associated regions, as indicated by well-trained radiologists.
UR - http://www.scopus.com/inward/record.url?scp=85099214827&partnerID=8YFLogxK
U2 - 10.3390/s21020455
DO - 10.3390/s21020455
M3 - Journal articles
C2 - 33440674
AN - SCOPUS:85099214827
SN - 1424-8220
VL - 21
SP - 1
EP - 22
JO - Sensors (Switzerland)
JF - Sensors (Switzerland)
IS - 2
M1 - 455
ER -
