Deep learning for COVID-19 detection based on CT images
Abstract COVID-19 has tremendously impacted patients and medical systems globally. Computed tomography images can effectively complement the reverse transcription-polymerase chain reaction testing. This study adopted a convolutional neural network for COVID-19 testing. We examined the performance of...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Publishing Group
2021-07-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-021-93832-2 |
id |
doaj-c3add19cf23746b086c31d653063cc3e |
---|---|
record_format |
Article |
spelling |
doaj-c3add19cf23746b086c31d653063cc3e2021-07-18T11:24:40ZengNature Publishing GroupScientific Reports2045-23222021-07-0111111210.1038/s41598-021-93832-2Deep learning for COVID-19 detection based on CT imagesWentao Zhao0Wei Jiang1Xinguo Qiu2College of Mechanical Engineering, Zhejiang University of TechnologyCollege of Mechanical Engineering, Zhejiang University of TechnologyCollege of Mechanical Engineering, Zhejiang University of TechnologyAbstract COVID-19 has tremendously impacted patients and medical systems globally. Computed tomography images can effectively complement the reverse transcription-polymerase chain reaction testing. This study adopted a convolutional neural network for COVID-19 testing. We examined the performance of different pre-trained models on CT testing and identified that larger, out-of-field datasets boost the testing power of the models. This suggests that a priori knowledge of the models from out-of-field training is also applicable to CT images. The proposed transfer learning approach proves to be more successful than the current approaches described in literature. We believe that our approach has achieved the state-of-the-art performance in identification thus far. Based on experiments with randomly sampled training datasets, the results reveal a satisfactory performance by our model. We investigated the relevant visual characteristics of the CT images used by the model; these may assist clinical doctors in manual screening.https://doi.org/10.1038/s41598-021-93832-2 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Wentao Zhao Wei Jiang Xinguo Qiu |
spellingShingle |
Wentao Zhao Wei Jiang Xinguo Qiu Deep learning for COVID-19 detection based on CT images Scientific Reports |
author_facet |
Wentao Zhao Wei Jiang Xinguo Qiu |
author_sort |
Wentao Zhao |
title |
Deep learning for COVID-19 detection based on CT images |
title_short |
Deep learning for COVID-19 detection based on CT images |
title_full |
Deep learning for COVID-19 detection based on CT images |
title_fullStr |
Deep learning for COVID-19 detection based on CT images |
title_full_unstemmed |
Deep learning for COVID-19 detection based on CT images |
title_sort |
deep learning for covid-19 detection based on ct images |
publisher |
Nature Publishing Group |
series |
Scientific Reports |
issn |
2045-2322 |
publishDate |
2021-07-01 |
description |
Abstract COVID-19 has tremendously impacted patients and medical systems globally. Computed tomography images can effectively complement the reverse transcription-polymerase chain reaction testing. This study adopted a convolutional neural network for COVID-19 testing. We examined the performance of different pre-trained models on CT testing and identified that larger, out-of-field datasets boost the testing power of the models. This suggests that a priori knowledge of the models from out-of-field training is also applicable to CT images. The proposed transfer learning approach proves to be more successful than the current approaches described in literature. We believe that our approach has achieved the state-of-the-art performance in identification thus far. Based on experiments with randomly sampled training datasets, the results reveal a satisfactory performance by our model. We investigated the relevant visual characteristics of the CT images used by the model; these may assist clinical doctors in manual screening. |
url |
https://doi.org/10.1038/s41598-021-93832-2 |
work_keys_str_mv |
AT wentaozhao deeplearningforcovid19detectionbasedonctimages AT weijiang deeplearningforcovid19detectionbasedonctimages AT xinguoqiu deeplearningforcovid19detectionbasedonctimages |
_version_ |
1721296269562871808 |