Staff View: Lung disease classification using GLCM and deep features from different deep learning architectures with principal component analysis

Lung disease classification using GLCM and deep features from different deep learning architectures with principal component analysis

Lung disease classification is an important stage in implementing a Computer Aided Diagnosis (CADx) system. CADx systems can aid doctors as a second rater to increase diagnostic accuracy for medical applications. It has also potential to reduce waiting time and increasing patient throughput when hos...

Full description

Saved in:

Bibliographic Details
Main Authors:	Than, Joel Chia Ming, Mohd. Noor, Norliza, Mohd. Rijal, Omar, M. Kassim, Rosminah, Yunus, Ashari
Format:	Article
Language:	English
Published:	Penerbit UTHM 2018
Subjects:	T Technology (General)
Online Access:	http://eprints.utm.my/id/eprint/86488/1/JoelThan2018_LungDiseaseClassificationusingGLCMandDeep.pdf http://eprints.utm.my/id/eprint/86488/ https://publisher.uthm.edu.my/ojs/index.php/ijie/article/view/3476
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.utm.86488
record_format	eprints
spelling	my.utm.864882020-09-30T08:41:05Z http://eprints.utm.my/id/eprint/86488/ Lung disease classification using GLCM and deep features from different deep learning architectures with principal component analysis Than, Joel Chia Ming Mohd. Noor, Norliza Mohd. Rijal, Omar M. Kassim, Rosminah Yunus, Ashari T Technology (General) Lung disease classification is an important stage in implementing a Computer Aided Diagnosis (CADx) system. CADx systems can aid doctors as a second rater to increase diagnostic accuracy for medical applications. It has also potential to reduce waiting time and increasing patient throughput when hospitals high workload. Conventional lung classification systems utilize textural features. However textural features may not be enough to describe properties of an image. Deep features are an emerging source of features that can combat the weaknesses of textural features. The goal of this study is to propose a lung disease classification framework using deep features from five different deep networks and comparing its results with the conventional Gray-level Co-occurrence Matrix (GLCM). This study used a dataset of 81 diseased and 15 normal patients with five levels of High Resolution Computed Tomography (HRCT) slices. A comparison of five different deep learning networks namely, Alexnet, VGG16, VGG19, Res50 and Res101, with textural features from Gray-level Co-occurrence Matrix (GLCM) was performed. This study used a K-fold validation protocol with K = 2, 3, 5 and 10. This study also compared using five classifiers; Decision Tree, Support Vector Machine, Linear Discriminant Analysis, Regression and k-nearest neighbor (k-NN) classifiers. The usage of PCA increased the classification accuracy from 92.01% to 97.40% when using k-NN classifier. This was achieved with only using 14 features instead of the initial 1000 features. Using SVM classifier, a maximum accuracy of 100% was achieved when using all five of the deep learning features. Thus deep features show a promising application for classifying diseased and normal lungs. Penerbit UTHM 2018 Article PeerReviewed application/pdf en http://eprints.utm.my/id/eprint/86488/1/JoelThan2018_LungDiseaseClassificationusingGLCMandDeep.pdf Than, Joel Chia Ming and Mohd. Noor, Norliza and Mohd. Rijal, Omar and M. Kassim, Rosminah and Yunus, Ashari (2018) Lung disease classification using GLCM and deep features from different deep learning architectures with principal component analysis. International Journal of Integrated Engineering, 10 (7). pp. 76-89. ISSN 2229-838X https://publisher.uthm.edu.my/ojs/index.php/ijie/article/view/3476
institution	Universiti Teknologi Malaysia
building	UTM Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	Universiti Teknologi Malaysia
content_source	UTM Institutional Repository
url_provider	http://eprints.utm.my/
language	English
topic	T Technology (General)
spellingShingle	T Technology (General) Than, Joel Chia Ming Mohd. Noor, Norliza Mohd. Rijal, Omar M. Kassim, Rosminah Yunus, Ashari Lung disease classification using GLCM and deep features from different deep learning architectures with principal component analysis
description	Lung disease classification is an important stage in implementing a Computer Aided Diagnosis (CADx) system. CADx systems can aid doctors as a second rater to increase diagnostic accuracy for medical applications. It has also potential to reduce waiting time and increasing patient throughput when hospitals high workload. Conventional lung classification systems utilize textural features. However textural features may not be enough to describe properties of an image. Deep features are an emerging source of features that can combat the weaknesses of textural features. The goal of this study is to propose a lung disease classification framework using deep features from five different deep networks and comparing its results with the conventional Gray-level Co-occurrence Matrix (GLCM). This study used a dataset of 81 diseased and 15 normal patients with five levels of High Resolution Computed Tomography (HRCT) slices. A comparison of five different deep learning networks namely, Alexnet, VGG16, VGG19, Res50 and Res101, with textural features from Gray-level Co-occurrence Matrix (GLCM) was performed. This study used a K-fold validation protocol with K = 2, 3, 5 and 10. This study also compared using five classifiers; Decision Tree, Support Vector Machine, Linear Discriminant Analysis, Regression and k-nearest neighbor (k-NN) classifiers. The usage of PCA increased the classification accuracy from 92.01% to 97.40% when using k-NN classifier. This was achieved with only using 14 features instead of the initial 1000 features. Using SVM classifier, a maximum accuracy of 100% was achieved when using all five of the deep learning features. Thus deep features show a promising application for classifying diseased and normal lungs.
format	Article
author	Than, Joel Chia Ming Mohd. Noor, Norliza Mohd. Rijal, Omar M. Kassim, Rosminah Yunus, Ashari
author_facet	Than, Joel Chia Ming Mohd. Noor, Norliza Mohd. Rijal, Omar M. Kassim, Rosminah Yunus, Ashari
author_sort	Than, Joel Chia Ming
title	Lung disease classification using GLCM and deep features from different deep learning architectures with principal component analysis
title_short	Lung disease classification using GLCM and deep features from different deep learning architectures with principal component analysis
title_full	Lung disease classification using GLCM and deep features from different deep learning architectures with principal component analysis
title_fullStr	Lung disease classification using GLCM and deep features from different deep learning architectures with principal component analysis
title_full_unstemmed	Lung disease classification using GLCM and deep features from different deep learning architectures with principal component analysis
title_sort	lung disease classification using glcm and deep features from different deep learning architectures with principal component analysis
publisher	Penerbit UTHM
publishDate	2018
url	http://eprints.utm.my/id/eprint/86488/1/JoelThan2018_LungDiseaseClassificationusingGLCMandDeep.pdf http://eprints.utm.my/id/eprint/86488/ https://publisher.uthm.edu.my/ojs/index.php/ijie/article/view/3476
_version_	1680321053961748480
score	13.211869

Lung disease classification using GLCM and deep features from different deep learning architectures with principal component analysis

Similar Items