UMLF-COVID: an unsupervised meta-learning model specifically designed to identify X-ray images of COVID-19 patients

Abstract Background With the rapid spread of COVID-19 worldwide, quick screening for possible COVID-19 patients has become the focus of international researchers. Recently, many deep learning-based Computed Tomography (CT) image/X-ray image fast screening models for potential COVID-19 patients have...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Rui Miao, Xin Dong, Sheng-Li Xie, Yong Liang, Sio-Long Lo
Formato:	article
Lenguaje:	EN
Publicado:	BMC 2021
Materias:	COVID-19 X-ray CNN UMLF-COVID Medical technology R855-855.5
Acceso en línea:	https://doaj.org/article/6a8b4cc1b1f3420184ce1bd214e1a1ed
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6a8b4cc1b1f3420184ce1bd214e1a1ed
record_format	dspace
spelling	oai:doaj.org-article:6a8b4cc1b1f3420184ce1bd214e1a1ed2021-11-28T12:30:32ZUMLF-COVID: an unsupervised meta-learning model specifically designed to identify X-ray images of COVID-19 patients10.1186/s12880-021-00704-21471-2342https://doaj.org/article/6a8b4cc1b1f3420184ce1bd214e1a1ed2021-11-01T00:00:00Zhttps://doi.org/10.1186/s12880-021-00704-2https://doaj.org/toc/1471-2342Abstract Background With the rapid spread of COVID-19 worldwide, quick screening for possible COVID-19 patients has become the focus of international researchers. Recently, many deep learning-based Computed Tomography (CT) image/X-ray image fast screening models for potential COVID-19 patients have been proposed. However, the existing models still have two main problems. First, most of the existing supervised models are based on pre-trained model parameters. The pre-training model needs to be constructed on a dataset with features similar to those in COVID-19 X-ray images, which limits the construction and use of the model. Second, the number of categories based on the X-ray dataset of COVID-19 and other pneumonia patients is usually imbalanced. In addition, the quality is difficult to distinguish, leading to non-ideal results with the existing model in the multi-class classification COVID-19 recognition task. Moreover, no researchers have proposed a COVID-19 X-ray image learning model based on unsupervised meta-learning. Methods This paper first constructed an unsupervised meta-learning model for fast screening of COVID-19 patients (UMLF-COVID). This model does not require a pre-trained model, which solves the limitation problem of model construction, and the proposed unsupervised meta-learning framework solves the problem of sample imbalance and sample quality. Results The UMLF-COVID model is tested on two real datasets, each of which builds a three-category and four-category model. And the experimental results show that the accuracy of the UMLF-COVID model is 3–10% higher than that of the existing models. Conclusion In summary, we believe that the UMLF-COVID model is a good complement to COVID-19 X-ray fast screening models.Rui MiaoXin DongSheng-Li XieYong LiangSio-Long LoBMCarticleCOVID-19X-rayCNNUMLF-COVIDMedical technologyR855-855.5ENBMC Medical Imaging, Vol 21, Iss 1, Pp 1-16 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	COVID-19 X-ray CNN UMLF-COVID Medical technology R855-855.5
spellingShingle	COVID-19 X-ray CNN UMLF-COVID Medical technology R855-855.5 Rui Miao Xin Dong Sheng-Li Xie Yong Liang Sio-Long Lo UMLF-COVID: an unsupervised meta-learning model specifically designed to identify X-ray images of COVID-19 patients
description	Abstract Background With the rapid spread of COVID-19 worldwide, quick screening for possible COVID-19 patients has become the focus of international researchers. Recently, many deep learning-based Computed Tomography (CT) image/X-ray image fast screening models for potential COVID-19 patients have been proposed. However, the existing models still have two main problems. First, most of the existing supervised models are based on pre-trained model parameters. The pre-training model needs to be constructed on a dataset with features similar to those in COVID-19 X-ray images, which limits the construction and use of the model. Second, the number of categories based on the X-ray dataset of COVID-19 and other pneumonia patients is usually imbalanced. In addition, the quality is difficult to distinguish, leading to non-ideal results with the existing model in the multi-class classification COVID-19 recognition task. Moreover, no researchers have proposed a COVID-19 X-ray image learning model based on unsupervised meta-learning. Methods This paper first constructed an unsupervised meta-learning model for fast screening of COVID-19 patients (UMLF-COVID). This model does not require a pre-trained model, which solves the limitation problem of model construction, and the proposed unsupervised meta-learning framework solves the problem of sample imbalance and sample quality. Results The UMLF-COVID model is tested on two real datasets, each of which builds a three-category and four-category model. And the experimental results show that the accuracy of the UMLF-COVID model is 3–10% higher than that of the existing models. Conclusion In summary, we believe that the UMLF-COVID model is a good complement to COVID-19 X-ray fast screening models.
format	article
author	Rui Miao Xin Dong Sheng-Li Xie Yong Liang Sio-Long Lo
author_facet	Rui Miao Xin Dong Sheng-Li Xie Yong Liang Sio-Long Lo
author_sort	Rui Miao
title	UMLF-COVID: an unsupervised meta-learning model specifically designed to identify X-ray images of COVID-19 patients
title_short	UMLF-COVID: an unsupervised meta-learning model specifically designed to identify X-ray images of COVID-19 patients
title_full	UMLF-COVID: an unsupervised meta-learning model specifically designed to identify X-ray images of COVID-19 patients
title_fullStr	UMLF-COVID: an unsupervised meta-learning model specifically designed to identify X-ray images of COVID-19 patients
title_full_unstemmed	UMLF-COVID: an unsupervised meta-learning model specifically designed to identify X-ray images of COVID-19 patients
title_sort	umlf-covid: an unsupervised meta-learning model specifically designed to identify x-ray images of covid-19 patients
publisher	BMC
publishDate	2021
url	https://doaj.org/article/6a8b4cc1b1f3420184ce1bd214e1a1ed
work_keys_str_mv	AT ruimiao umlfcovidanunsupervisedmetalearningmodelspecificallydesignedtoidentifyxrayimagesofcovid19patients AT xindong umlfcovidanunsupervisedmetalearningmodelspecificallydesignedtoidentifyxrayimagesofcovid19patients AT shenglixie umlfcovidanunsupervisedmetalearningmodelspecificallydesignedtoidentifyxrayimagesofcovid19patients AT yongliang umlfcovidanunsupervisedmetalearningmodelspecificallydesignedtoidentifyxrayimagesofcovid19patients AT siolonglo umlfcovidanunsupervisedmetalearningmodelspecificallydesignedtoidentifyxrayimagesofcovid19patients
_version_	1718407960094310400

UMLF-COVID: an unsupervised meta-learning model specifically designed to identify X-ray images of COVID-19 patients

Ejemplares similares