Explainable COVID-19 Detection Using Chest CT Scans and Deep Learning
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 ar...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-01-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/2/455 |
id |
doaj-560dffe72ab948bc92aa9a662be2e51d |
---|---|
record_format |
Article |
spelling |
doaj-560dffe72ab948bc92aa9a662be2e51d2021-01-12T00:01:15ZengMDPI AGSensors1424-82202021-01-012145545510.3390/s21020455Explainable COVID-19 Detection Using Chest CT Scans and Deep LearningHammam Alshazly0Christoph Linse1Erhardt Barth2Thomas Martinetz3Institute for Neuro- and Bioinformatics, University of Lübeck, 23562 Lübeck, GermanyInstitute for Neuro- and Bioinformatics, University of Lübeck, 23562 Lübeck, GermanyInstitute for Neuro- and Bioinformatics, University of Lübeck, 23562 Lübeck, GermanyInstitute for Neuro- and Bioinformatics, University of Lübeck, 23562 Lübeck, GermanyThis 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 <inline-formula><math display="inline"><semantics><mrow><mn>99.4</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math display="inline"><semantics><mrow><mn>99.6</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math display="inline"><semantics><mrow><mn>99.8</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math display="inline"><semantics><mrow><mn>99.6</mn><mo>%</mo></mrow></semantics></math></inline-formula>, and <inline-formula><math display="inline"><semantics><mrow><mn>99.4</mn><mo>%</mo></mrow></semantics></math></inline-formula> on the SARS-CoV-2 dataset, and <inline-formula><math display="inline"><semantics><mrow><mn>92.9</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math display="inline"><semantics><mrow><mn>91.3</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math display="inline"><semantics><mrow><mn>93.7</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math display="inline"><semantics><mrow><mn>92.2</mn><mo>%</mo></mrow></semantics></math></inline-formula>, and <inline-formula><math display="inline"><semantics><mrow><mn>92.5</mn><mo>%</mo></mrow></semantics></math></inline-formula> 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.https://www.mdpi.com/1424-8220/21/2/455coronavirusCOVID-19 detectionSARS-CoV-2explainable deep learningfeature visualization |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Hammam Alshazly Christoph Linse Erhardt Barth Thomas Martinetz |
spellingShingle |
Hammam Alshazly Christoph Linse Erhardt Barth Thomas Martinetz Explainable COVID-19 Detection Using Chest CT Scans and Deep Learning Sensors coronavirus COVID-19 detection SARS-CoV-2 explainable deep learning feature visualization |
author_facet |
Hammam Alshazly Christoph Linse Erhardt Barth Thomas Martinetz |
author_sort |
Hammam Alshazly |
title |
Explainable COVID-19 Detection Using Chest CT Scans and Deep Learning |
title_short |
Explainable COVID-19 Detection Using Chest CT Scans and Deep Learning |
title_full |
Explainable COVID-19 Detection Using Chest CT Scans and Deep Learning |
title_fullStr |
Explainable COVID-19 Detection Using Chest CT Scans and Deep Learning |
title_full_unstemmed |
Explainable COVID-19 Detection Using Chest CT Scans and Deep Learning |
title_sort |
explainable covid-19 detection using chest ct scans and deep learning |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2021-01-01 |
description |
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 <inline-formula><math display="inline"><semantics><mrow><mn>99.4</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math display="inline"><semantics><mrow><mn>99.6</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math display="inline"><semantics><mrow><mn>99.8</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math display="inline"><semantics><mrow><mn>99.6</mn><mo>%</mo></mrow></semantics></math></inline-formula>, and <inline-formula><math display="inline"><semantics><mrow><mn>99.4</mn><mo>%</mo></mrow></semantics></math></inline-formula> on the SARS-CoV-2 dataset, and <inline-formula><math display="inline"><semantics><mrow><mn>92.9</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math display="inline"><semantics><mrow><mn>91.3</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math display="inline"><semantics><mrow><mn>93.7</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math display="inline"><semantics><mrow><mn>92.2</mn><mo>%</mo></mrow></semantics></math></inline-formula>, and <inline-formula><math display="inline"><semantics><mrow><mn>92.5</mn><mo>%</mo></mrow></semantics></math></inline-formula> 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. |
topic |
coronavirus COVID-19 detection SARS-CoV-2 explainable deep learning feature visualization |
url |
https://www.mdpi.com/1424-8220/21/2/455 |
work_keys_str_mv |
AT hammamalshazly explainablecovid19detectionusingchestctscansanddeeplearning AT christophlinse explainablecovid19detectionusingchestctscansanddeeplearning AT erhardtbarth explainablecovid19detectionusingchestctscansanddeeplearning AT thomasmartinetz explainablecovid19detectionusingchestctscansanddeeplearning |
_version_ |
1724341106392432640 |