Cargando…
Automated Diagnosis of COVID-19 Using Deep Supervised Autoencoder With Multi-View Features From CT Images
Accurate and rapid diagnosis of coronavirus disease 2019 (COVID-19) from chest CT scans is of great importance and urgency during the worldwide outbreak. However, radiologists have to distinguish COVID-19 pneumonia from other pneumonia in a large number of CT scans, which is tedious and inefficient....
Formato: | Online Artículo Texto |
---|---|
Lenguaje: | English |
Publicado: |
IEEE
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9647725/ https://www.ncbi.nlm.nih.gov/pubmed/34351863 http://dx.doi.org/10.1109/TCBB.2021.3102584 |
_version_ | 1784827438053720064 |
---|---|
collection | PubMed |
description | Accurate and rapid diagnosis of coronavirus disease 2019 (COVID-19) from chest CT scans is of great importance and urgency during the worldwide outbreak. However, radiologists have to distinguish COVID-19 pneumonia from other pneumonia in a large number of CT scans, which is tedious and inefficient. Thus, it is urgently and clinically needed to develop an efficient and accurate diagnostic tool to help radiologists to fulfill the difficult task. In this study, we proposed a deep supervised autoencoder (DSAE) framework to automatically identify COVID-19 using multi-view features extracted from CT images. To fully explore features characterizing CT images from different frequency domains, DSAE was proposed to learn the latent representation by multi-task learning. The proposal was designed to both encode valuable information from different frequency features and construct a compact class structure for separability. To achieve this, we designed a multi-task loss function, which consists of a supervised loss and a reconstruction loss. Our proposed method was evaluated on a newly collected dataset of 787 subjects including COVID-19 pneumonia patients, other pneumonia patients, and normal subjects without abnormal CT findings. Extensive experimental results demonstrated that our proposed method achieved encouraging diagnostic performance and may have potential clinical application for the diagnosis of COVID-19. |
format | Online Article Text |
id | pubmed-9647725 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | IEEE |
record_format | MEDLINE/PubMed |
spelling | pubmed-96477252022-11-18 Automated Diagnosis of COVID-19 Using Deep Supervised Autoencoder With Multi-View Features From CT Images IEEE/ACM Trans Comput Biol Bioinform Article Accurate and rapid diagnosis of coronavirus disease 2019 (COVID-19) from chest CT scans is of great importance and urgency during the worldwide outbreak. However, radiologists have to distinguish COVID-19 pneumonia from other pneumonia in a large number of CT scans, which is tedious and inefficient. Thus, it is urgently and clinically needed to develop an efficient and accurate diagnostic tool to help radiologists to fulfill the difficult task. In this study, we proposed a deep supervised autoencoder (DSAE) framework to automatically identify COVID-19 using multi-view features extracted from CT images. To fully explore features characterizing CT images from different frequency domains, DSAE was proposed to learn the latent representation by multi-task learning. The proposal was designed to both encode valuable information from different frequency features and construct a compact class structure for separability. To achieve this, we designed a multi-task loss function, which consists of a supervised loss and a reconstruction loss. Our proposed method was evaluated on a newly collected dataset of 787 subjects including COVID-19 pneumonia patients, other pneumonia patients, and normal subjects without abnormal CT findings. Extensive experimental results demonstrated that our proposed method achieved encouraging diagnostic performance and may have potential clinical application for the diagnosis of COVID-19. IEEE 2021-08-05 /pmc/articles/PMC9647725/ /pubmed/34351863 http://dx.doi.org/10.1109/TCBB.2021.3102584 Text en This article is free to access and download, along with rights for full text and data mining, re-use and analysis. |
spellingShingle | Article Automated Diagnosis of COVID-19 Using Deep Supervised Autoencoder With Multi-View Features From CT Images |
title | Automated Diagnosis of COVID-19 Using Deep Supervised Autoencoder With Multi-View Features From CT Images |
title_full | Automated Diagnosis of COVID-19 Using Deep Supervised Autoencoder With Multi-View Features From CT Images |
title_fullStr | Automated Diagnosis of COVID-19 Using Deep Supervised Autoencoder With Multi-View Features From CT Images |
title_full_unstemmed | Automated Diagnosis of COVID-19 Using Deep Supervised Autoencoder With Multi-View Features From CT Images |
title_short | Automated Diagnosis of COVID-19 Using Deep Supervised Autoencoder With Multi-View Features From CT Images |
title_sort | automated diagnosis of covid-19 using deep supervised autoencoder with multi-view features from ct images |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9647725/ https://www.ncbi.nlm.nih.gov/pubmed/34351863 http://dx.doi.org/10.1109/TCBB.2021.3102584 |
work_keys_str_mv | AT automateddiagnosisofcovid19usingdeepsupervisedautoencoderwithmultiviewfeaturesfromctimages AT automateddiagnosisofcovid19usingdeepsupervisedautoencoderwithmultiviewfeaturesfromctimages AT automateddiagnosisofcovid19usingdeepsupervisedautoencoderwithmultiviewfeaturesfromctimages AT automateddiagnosisofcovid19usingdeepsupervisedautoencoderwithmultiviewfeaturesfromctimages AT automateddiagnosisofcovid19usingdeepsupervisedautoencoderwithmultiviewfeaturesfromctimages AT automateddiagnosisofcovid19usingdeepsupervisedautoencoderwithmultiviewfeaturesfromctimages AT automateddiagnosisofcovid19usingdeepsupervisedautoencoderwithmultiviewfeaturesfromctimages AT automateddiagnosisofcovid19usingdeepsupervisedautoencoderwithmultiviewfeaturesfromctimages AT automateddiagnosisofcovid19usingdeepsupervisedautoencoderwithmultiviewfeaturesfromctimages AT automateddiagnosisofcovid19usingdeepsupervisedautoencoderwithmultiviewfeaturesfromctimages |