Self-Supervised Deep Convolutional Neural Network for Chest X-Ray Classification

Chest radiography is a relatively cheap, widely available medical procedure that conveys key information for making diagnostic decisions. Chest X-rays are frequently used in the diagnosis of respiratory diseases such as pneumonia or COVID-19. In this paper, we propose a self-supervised deep neural n...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Matej Gazda, Jan Plavka, Jakub Gazda, Peter Drotar
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Self-supervised learning contrastive learning deep learning convolutional neural network chest X-ray COVID-19 Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/55228cfe99e54f56b099ecb78b7fa61b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:55228cfe99e54f56b099ecb78b7fa61b
record_format	dspace
spelling	oai:doaj.org-article:55228cfe99e54f56b099ecb78b7fa61b2021-11-18T00:01:00ZSelf-Supervised Deep Convolutional Neural Network for Chest X-Ray Classification2169-353610.1109/ACCESS.2021.3125324https://doaj.org/article/55228cfe99e54f56b099ecb78b7fa61b2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9600845/https://doaj.org/toc/2169-3536Chest radiography is a relatively cheap, widely available medical procedure that conveys key information for making diagnostic decisions. Chest X-rays are frequently used in the diagnosis of respiratory diseases such as pneumonia or COVID-19. In this paper, we propose a self-supervised deep neural network that is pretrained on an unlabeled chest X-ray dataset. Pretraining is achieved through the contrastive learning approach by comparing representations of differently augmented input images. The learned representations are transferred to downstream tasks – the classification of respiratory diseases. We evaluate the proposed approach on two tasks for pneumonia classification, one for COVID-19 recognition and one for discrimination of different pneumonia types. The results show that our approach yields competitive results without requiring large amounts of labeled training data.Matej GazdaJan PlavkaJakub GazdaPeter DrotarIEEEarticleSelf-supervised learningcontrastive learningdeep learningconvolutional neural networkchest X-rayCOVID-19Electrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 151972-151982 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Self-supervised learning contrastive learning deep learning convolutional neural network chest X-ray COVID-19 Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Self-supervised learning contrastive learning deep learning convolutional neural network chest X-ray COVID-19 Electrical engineering. Electronics. Nuclear engineering TK1-9971 Matej Gazda Jan Plavka Jakub Gazda Peter Drotar Self-Supervised Deep Convolutional Neural Network for Chest X-Ray Classification
description	Chest radiography is a relatively cheap, widely available medical procedure that conveys key information for making diagnostic decisions. Chest X-rays are frequently used in the diagnosis of respiratory diseases such as pneumonia or COVID-19. In this paper, we propose a self-supervised deep neural network that is pretrained on an unlabeled chest X-ray dataset. Pretraining is achieved through the contrastive learning approach by comparing representations of differently augmented input images. The learned representations are transferred to downstream tasks – the classification of respiratory diseases. We evaluate the proposed approach on two tasks for pneumonia classification, one for COVID-19 recognition and one for discrimination of different pneumonia types. The results show that our approach yields competitive results without requiring large amounts of labeled training data.
format	article
author	Matej Gazda Jan Plavka Jakub Gazda Peter Drotar
author_facet	Matej Gazda Jan Plavka Jakub Gazda Peter Drotar
author_sort	Matej Gazda
title	Self-Supervised Deep Convolutional Neural Network for Chest X-Ray Classification
title_short	Self-Supervised Deep Convolutional Neural Network for Chest X-Ray Classification
title_full	Self-Supervised Deep Convolutional Neural Network for Chest X-Ray Classification
title_fullStr	Self-Supervised Deep Convolutional Neural Network for Chest X-Ray Classification
title_full_unstemmed	Self-Supervised Deep Convolutional Neural Network for Chest X-Ray Classification
title_sort	self-supervised deep convolutional neural network for chest x-ray classification
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/55228cfe99e54f56b099ecb78b7fa61b
work_keys_str_mv	AT matejgazda selfsuperviseddeepconvolutionalneuralnetworkforchestxrayclassification AT janplavka selfsuperviseddeepconvolutionalneuralnetworkforchestxrayclassification AT jakubgazda selfsuperviseddeepconvolutionalneuralnetworkforchestxrayclassification AT peterdrotar selfsuperviseddeepconvolutionalneuralnetworkforchestxrayclassification
_version_	1718425225416146944

Self-Supervised Deep Convolutional Neural Network for Chest X-Ray Classification

Ejemplares similares