Classification of Lung Nodules Based on Deep Residual Networks and Migration Learning.

Wu, P; Sun, X; Zhao, Z; Wang, H; Pan, S; Schuller, B

Classification of Lung Nodules Based on Deep Residual Networks and Migration Learning.

Wu, P Sun, X Zhao, Z Wang, H Pan, S

Schuller, B

Permalink

Publisher:: HINDAWI LTD
Publication Type:: Journal Article
Citation:: Computational intelligence and neuroscience, 2020, 2020, pp. 8975078
Issue Date:: 2020-01

Closed Access

	Filename	Description	Size
	Classification of Lung Nodules Based on Deep Residual Networks and Migration Learning.pdf	Published version	1.79 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Wu, P
dc.contributor.author	Sun, X
dc.contributor.author	Zhao, Z
dc.contributor.author	Wang, H
dc.contributor.author	Pan, S https://orcid.org/0000-0003-0794-527X
dc.contributor.author	Schuller, B
dc.date.accessioned	2020-11-08T19:04:28Z
dc.date.available	2020-02-12
dc.date.available	2020-11-08T19:04:28Z
dc.date.issued	2020-01
dc.identifier.citation	Computational intelligence and neuroscience, 2020, 2020, pp. 8975078
dc.identifier.issn	1687-5265
dc.identifier.issn	1687-5273
dc.identifier.uri	http://hdl.handle.net/10453/143851
dc.description.abstract	The classification process of lung nodule detection in a traditional computer-aided detection (CAD) system is complex, and the classification result is heavily dependent on the performance of each step in lung nodule detection, causing low classification accuracy and high false positive rate. In order to alleviate these issues, a lung nodule classification method based on a deep residual network is proposed. Abandoning traditional image processing methods and taking the 50-layer ResNet network structure as the initial model, the deep residual network is constructed by combining residual learning and migration learning. The proposed approach is verified by conducting experiments on the lung computed tomography (CT) images from the publicly available LIDC-IDRI database. An average accuracy of 98.23% and a false positive rate of 1.65% are obtained based on the ten-fold cross-validation method. Compared with the conventional support vector machine (SVM)-based CAD system, the accuracy of our method improved by 9.96% and the false positive rate decreased by 6.95%, while the accuracy improved by 1.75% and 2.42%, respectively, and the false positive rate decreased by 2.07% and 2.22%, respectively, in contrast to the VGG19 model and InceptionV3 convolutional neural networks. The experimental results demonstrate the effectiveness of our proposed method in lung nodule classification for CT images.
dc.format	Electronic-eCollection
dc.language	eng
dc.publisher	HINDAWI LTD
dc.relation.ispartof	Computational intelligence and neuroscience
dc.relation.isbasedon	10.1155/2020/8975078
dc.rights	info:eu-repo/semantics/restrictedAccess
dc.subject	1109 Neurosciences, 1702 Cognitive Sciences
dc.subject.classification	Neurology & Neurosurgery
dc.title	Classification of Lung Nodules Based on Deep Residual Networks and Migration Learning.
dc.type	Journal Article
utslib.citation.volume	2020
utslib.location.activity	United States
utslib.for	1109 Neurosciences
utslib.for	1702 Cognitive Sciences
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney
utslib.copyright.status	closed_access	*
dc.date.updated	2020-11-08T19:04:19Z
pubs.publication-status	Published
pubs.volume	2020

Abstract:

The classification process of lung nodule detection in a traditional computer-aided detection (CAD) system is complex, and the classification result is heavily dependent on the performance of each step in lung nodule detection, causing low classification accuracy and high false positive rate. In order to alleviate these issues, a lung nodule classification method based on a deep residual network is proposed. Abandoning traditional image processing methods and taking the 50-layer ResNet network structure as the initial model, the deep residual network is constructed by combining residual learning and migration learning. The proposed approach is verified by conducting experiments on the lung computed tomography (CT) images from the publicly available LIDC-IDRI database. An average accuracy of 98.23% and a false positive rate of 1.65% are obtained based on the ten-fold cross-validation method. Compared with the conventional support vector machine (SVM)-based CAD system, the accuracy of our method improved by 9.96% and the false positive rate decreased by 6.95%, while the accuracy improved by 1.75% and 2.42%, respectively, and the false positive rate decreased by 2.07% and 2.22%, respectively, in contrast to the VGG19 model and InceptionV3 convolutional neural networks. The experimental results demonstrate the effectiveness of our proposed method in lung nodule classification for CT images.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/143851