DCML: Deep contrastive mutual learning for COVID-19 recognition
COVID-19 is a form of disease triggered by a new strain of coronavirus. Automatic COVID-19 recognition using computer-aided methods is beneficial for speeding up diagnosis efficiency. Current researches usually focus on a deeper or wider neural network for COVID-19 recognition. And the implicit cont...
Published in: | Biomedical Signal Processing and Control |
---|---|
Main Authors: | , , , , , , |
Format: | Text |
Language: | English |
Published: |
Elsevier Ltd.
2022
|
Subjects: | |
Online Access: | http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9058053/ https://doi.org/10.1016/j.bspc.2022.103770 |
id |
ftpubmed:oai:pubmedcentral.nih.gov:9058053 |
---|---|
record_format |
openpolar |
spelling |
ftpubmed:oai:pubmedcentral.nih.gov:9058053 2023-05-15T16:01:54+02:00 DCML: Deep contrastive mutual learning for COVID-19 recognition Zhang, Hongbin Liang, Weinan Li, Chuanxiu Xiong, Qipeng Shi, Haowei Hu, Lang Li, Guangli 2022-08 http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9058053/ https://doi.org/10.1016/j.bspc.2022.103770 en eng Elsevier Ltd. http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9058053/ http://dx.doi.org/10.1016/j.bspc.2022.103770 © 2022 Elsevier Ltd. All rights reserved. Since January 2020 Elsevier has created a COVID-19 resource centre with free information in English and Mandarin on the novel coronavirus COVID-19. The COVID-19 resource centre is hosted on Elsevier Connect, the company's public news and information website. Elsevier hereby grants permission to make all its COVID-19-related research that is available on the COVID-19 resource centre - including this research content - immediately available in PubMed Central and other publicly funded repositories, such as the WHO COVID database with rights for unrestricted research re-use and analyses in any form or by any means with acknowledgement of the original source. These permissions are granted for free by Elsevier for as long as the COVID-19 resource centre remains active. Biomed Signal Process Control Article Text 2022 ftpubmed https://doi.org/10.1016/j.bspc.2022.103770 2022-05-08T00:57:44Z COVID-19 is a form of disease triggered by a new strain of coronavirus. Automatic COVID-19 recognition using computer-aided methods is beneficial for speeding up diagnosis efficiency. Current researches usually focus on a deeper or wider neural network for COVID-19 recognition. And the implicit contrastive relationship between different samples has not been fully explored. To address these problems, we propose a novel model, called deep contrastive mutual learning (DCML), to diagnose COVID-19 more effectively. A multi-way data augmentation strategy based on Fast AutoAugment (FAA) was employed to enrich the original training dataset, which helps reduce the risk of overfitting. Then, we incorporated the popular contrastive learning idea into the conventional deep mutual learning (DML) framework to mine the relationship between diverse samples and created more discriminative image features through a new adaptive model fusion method. Experimental results on three public datasets demonstrate that the DCML model outperforms other state-of-the-art baselines. More importantly, DCML is easier to reproduce and relatively efficient, strengthening its high practicality. Text DML PubMed Central (PMC) Biomedical Signal Processing and Control 77 103770 |
institution |
Open Polar |
collection |
PubMed Central (PMC) |
op_collection_id |
ftpubmed |
language |
English |
topic |
Article |
spellingShingle |
Article Zhang, Hongbin Liang, Weinan Li, Chuanxiu Xiong, Qipeng Shi, Haowei Hu, Lang Li, Guangli DCML: Deep contrastive mutual learning for COVID-19 recognition |
topic_facet |
Article |
description |
COVID-19 is a form of disease triggered by a new strain of coronavirus. Automatic COVID-19 recognition using computer-aided methods is beneficial for speeding up diagnosis efficiency. Current researches usually focus on a deeper or wider neural network for COVID-19 recognition. And the implicit contrastive relationship between different samples has not been fully explored. To address these problems, we propose a novel model, called deep contrastive mutual learning (DCML), to diagnose COVID-19 more effectively. A multi-way data augmentation strategy based on Fast AutoAugment (FAA) was employed to enrich the original training dataset, which helps reduce the risk of overfitting. Then, we incorporated the popular contrastive learning idea into the conventional deep mutual learning (DML) framework to mine the relationship between diverse samples and created more discriminative image features through a new adaptive model fusion method. Experimental results on three public datasets demonstrate that the DCML model outperforms other state-of-the-art baselines. More importantly, DCML is easier to reproduce and relatively efficient, strengthening its high practicality. |
format |
Text |
author |
Zhang, Hongbin Liang, Weinan Li, Chuanxiu Xiong, Qipeng Shi, Haowei Hu, Lang Li, Guangli |
author_facet |
Zhang, Hongbin Liang, Weinan Li, Chuanxiu Xiong, Qipeng Shi, Haowei Hu, Lang Li, Guangli |
author_sort |
Zhang, Hongbin |
title |
DCML: Deep contrastive mutual learning for COVID-19 recognition |
title_short |
DCML: Deep contrastive mutual learning for COVID-19 recognition |
title_full |
DCML: Deep contrastive mutual learning for COVID-19 recognition |
title_fullStr |
DCML: Deep contrastive mutual learning for COVID-19 recognition |
title_full_unstemmed |
DCML: Deep contrastive mutual learning for COVID-19 recognition |
title_sort |
dcml: deep contrastive mutual learning for covid-19 recognition |
publisher |
Elsevier Ltd. |
publishDate |
2022 |
url |
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9058053/ https://doi.org/10.1016/j.bspc.2022.103770 |
genre |
DML |
genre_facet |
DML |
op_source |
Biomed Signal Process Control |
op_relation |
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9058053/ http://dx.doi.org/10.1016/j.bspc.2022.103770 |
op_rights |
© 2022 Elsevier Ltd. All rights reserved. Since January 2020 Elsevier has created a COVID-19 resource centre with free information in English and Mandarin on the novel coronavirus COVID-19. The COVID-19 resource centre is hosted on Elsevier Connect, the company's public news and information website. Elsevier hereby grants permission to make all its COVID-19-related research that is available on the COVID-19 resource centre - including this research content - immediately available in PubMed Central and other publicly funded repositories, such as the WHO COVID database with rights for unrestricted research re-use and analyses in any form or by any means with acknowledgement of the original source. These permissions are granted for free by Elsevier for as long as the COVID-19 resource centre remains active. |
op_doi |
https://doi.org/10.1016/j.bspc.2022.103770 |
container_title |
Biomedical Signal Processing and Control |
container_volume |
77 |
container_start_page |
103770 |
_version_ |
1766397587220332544 |