A multi-scale gated multi-head attention depthwise separable CNN model for recognizing COVID-19
Abstract Coronavirus 2019 (COVID-19) is a new acute respiratory disease that has spread rapidly throughout the world. In this paper, a lightweight convolutional neural network (CNN) model named multi-scale gated multi-head attention depthwise separable CNN (MGMADS-CNN) is proposed, which is based on...
Guardado en:
Autores principales: | , , , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Nature Portfolio
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/a0ee4193f36c4891b41283052878d3c6 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:a0ee4193f36c4891b41283052878d3c6 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:a0ee4193f36c4891b41283052878d3c62021-12-02T18:03:05ZA multi-scale gated multi-head attention depthwise separable CNN model for recognizing COVID-1910.1038/s41598-021-97428-82045-2322https://doaj.org/article/a0ee4193f36c4891b41283052878d3c62021-09-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-97428-8https://doaj.org/toc/2045-2322Abstract Coronavirus 2019 (COVID-19) is a new acute respiratory disease that has spread rapidly throughout the world. In this paper, a lightweight convolutional neural network (CNN) model named multi-scale gated multi-head attention depthwise separable CNN (MGMADS-CNN) is proposed, which is based on attention mechanism and depthwise separable convolution. A multi-scale gated multi-head attention mechanism is designed to extract effective feature information from the COVID-19 X-ray and CT images for classification. Moreover, the depthwise separable convolution layers are adopted as MGMADS-CNN’s backbone to reduce the model size and parameters. The LeNet-5, AlexNet, GoogLeNet, ResNet, VGGNet-16, and three MGMADS-CNN models are trained, validated and tested with tenfold cross-validation on X-ray and CT images. The results show that MGMADS-CNN with three attention layers (MGMADS-3) has achieved accuracy of 96.75% on X-ray images and 98.25% on CT images. The specificity and sensitivity are 98.06% and 96.6% on X-ray images, and 98.17% and 98.05% on CT images. The size of MGMADS-3 model is only 43.6 M bytes. In addition, the detection speed of MGMADS-3 on X-ray images and CT images are 6.09 ms and 4.23 ms for per image, respectively. It is proved that the MGMADS-3 can detect and classify COVID-19 faster with higher accuracy and efficiency.Geng HongXiaoyan ChenJianyong ChenMiao ZhangYumeng RenXinyu ZhangNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-13 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Medicine R Science Q |
spellingShingle |
Medicine R Science Q Geng Hong Xiaoyan Chen Jianyong Chen Miao Zhang Yumeng Ren Xinyu Zhang A multi-scale gated multi-head attention depthwise separable CNN model for recognizing COVID-19 |
description |
Abstract Coronavirus 2019 (COVID-19) is a new acute respiratory disease that has spread rapidly throughout the world. In this paper, a lightweight convolutional neural network (CNN) model named multi-scale gated multi-head attention depthwise separable CNN (MGMADS-CNN) is proposed, which is based on attention mechanism and depthwise separable convolution. A multi-scale gated multi-head attention mechanism is designed to extract effective feature information from the COVID-19 X-ray and CT images for classification. Moreover, the depthwise separable convolution layers are adopted as MGMADS-CNN’s backbone to reduce the model size and parameters. The LeNet-5, AlexNet, GoogLeNet, ResNet, VGGNet-16, and three MGMADS-CNN models are trained, validated and tested with tenfold cross-validation on X-ray and CT images. The results show that MGMADS-CNN with three attention layers (MGMADS-3) has achieved accuracy of 96.75% on X-ray images and 98.25% on CT images. The specificity and sensitivity are 98.06% and 96.6% on X-ray images, and 98.17% and 98.05% on CT images. The size of MGMADS-3 model is only 43.6 M bytes. In addition, the detection speed of MGMADS-3 on X-ray images and CT images are 6.09 ms and 4.23 ms for per image, respectively. It is proved that the MGMADS-3 can detect and classify COVID-19 faster with higher accuracy and efficiency. |
format |
article |
author |
Geng Hong Xiaoyan Chen Jianyong Chen Miao Zhang Yumeng Ren Xinyu Zhang |
author_facet |
Geng Hong Xiaoyan Chen Jianyong Chen Miao Zhang Yumeng Ren Xinyu Zhang |
author_sort |
Geng Hong |
title |
A multi-scale gated multi-head attention depthwise separable CNN model for recognizing COVID-19 |
title_short |
A multi-scale gated multi-head attention depthwise separable CNN model for recognizing COVID-19 |
title_full |
A multi-scale gated multi-head attention depthwise separable CNN model for recognizing COVID-19 |
title_fullStr |
A multi-scale gated multi-head attention depthwise separable CNN model for recognizing COVID-19 |
title_full_unstemmed |
A multi-scale gated multi-head attention depthwise separable CNN model for recognizing COVID-19 |
title_sort |
multi-scale gated multi-head attention depthwise separable cnn model for recognizing covid-19 |
publisher |
Nature Portfolio |
publishDate |
2021 |
url |
https://doaj.org/article/a0ee4193f36c4891b41283052878d3c6 |
work_keys_str_mv |
AT genghong amultiscalegatedmultiheadattentiondepthwiseseparablecnnmodelforrecognizingcovid19 AT xiaoyanchen amultiscalegatedmultiheadattentiondepthwiseseparablecnnmodelforrecognizingcovid19 AT jianyongchen amultiscalegatedmultiheadattentiondepthwiseseparablecnnmodelforrecognizingcovid19 AT miaozhang amultiscalegatedmultiheadattentiondepthwiseseparablecnnmodelforrecognizingcovid19 AT yumengren amultiscalegatedmultiheadattentiondepthwiseseparablecnnmodelforrecognizingcovid19 AT xinyuzhang amultiscalegatedmultiheadattentiondepthwiseseparablecnnmodelforrecognizingcovid19 AT genghong multiscalegatedmultiheadattentiondepthwiseseparablecnnmodelforrecognizingcovid19 AT xiaoyanchen multiscalegatedmultiheadattentiondepthwiseseparablecnnmodelforrecognizingcovid19 AT jianyongchen multiscalegatedmultiheadattentiondepthwiseseparablecnnmodelforrecognizingcovid19 AT miaozhang multiscalegatedmultiheadattentiondepthwiseseparablecnnmodelforrecognizingcovid19 AT yumengren multiscalegatedmultiheadattentiondepthwiseseparablecnnmodelforrecognizingcovid19 AT xinyuzhang multiscalegatedmultiheadattentiondepthwiseseparablecnnmodelforrecognizingcovid19 |
_version_ |
1718378826701996032 |