Automated detection of lung nodules using HOG technique with chest X-ray images

U. Raghavendra, Anjan Gudigar, Tejaswi N. Rao, Hamido Fujita, U. Rajendra Acharya

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Lung disease is a growing disease and hence needs lot of attention. It is difficult to delineate the boundary of the lung when it is imaged through X-ray due to poor resolution. Hence, computer aided diagnosis (CAD) is preferred as it assists the radiologists in efficient diagnosis. In this work, a novel supervised classification technique is proposed using histogram of oriented gradient (HOG) and neighborhood preserving embedding (NPE). Our method is evaluated using 2000 chest X-ray images and can efficiently classify normal and abnormal classes with a promising performance of 97.95% accuracy, using support vector machine (SVM) classifier.

Original languageEnglish
Title of host publicationNew Trends in Intelligent Software Methodologies, Tools and Techniques - Proceedings of the 17th International Conference, SoMeT 2018
EditorsEnrique Herrera-Viedma, Hamido Fujita
PublisherIOS Press
Pages1018-1026
Number of pages9
ISBN (Electronic)9781614998990
DOIs
Publication statusPublished - 01-01-2018
Event17th International Conference on New Trends in Intelligent Software Methodology Tools and Techniques, SoMeT 2018 - Granada, Spain
Duration: 26-09-201828-09-2018

Publication series

NameFrontiers in Artificial Intelligence and Applications
Volume303
ISSN (Print)0922-6389

Conference

Conference17th International Conference on New Trends in Intelligent Software Methodology Tools and Techniques, SoMeT 2018
CountrySpain
CityGranada
Period26-09-1828-09-18

Fingerprint

Computer aided diagnosis
X rays
Pulmonary diseases
Support vector machines
Classifiers

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this

Raghavendra, U., Gudigar, A., Rao, T. N., Fujita, H., & Acharya, U. R. (2018). Automated detection of lung nodules using HOG technique with chest X-ray images. In E. Herrera-Viedma, & H. Fujita (Eds.), New Trends in Intelligent Software Methodologies, Tools and Techniques - Proceedings of the 17th International Conference, SoMeT 2018 (pp. 1018-1026). (Frontiers in Artificial Intelligence and Applications; Vol. 303). IOS Press. https://doi.org/10.3233/978-1-61499-900-3-1018
Raghavendra, U. ; Gudigar, Anjan ; Rao, Tejaswi N. ; Fujita, Hamido ; Acharya, U. Rajendra. / Automated detection of lung nodules using HOG technique with chest X-ray images. New Trends in Intelligent Software Methodologies, Tools and Techniques - Proceedings of the 17th International Conference, SoMeT 2018. editor / Enrique Herrera-Viedma ; Hamido Fujita. IOS Press, 2018. pp. 1018-1026 (Frontiers in Artificial Intelligence and Applications).
@inproceedings{6a8e5c7589ef421c8dfac7f8502d34d8,
title = "Automated detection of lung nodules using HOG technique with chest X-ray images",
abstract = "Lung disease is a growing disease and hence needs lot of attention. It is difficult to delineate the boundary of the lung when it is imaged through X-ray due to poor resolution. Hence, computer aided diagnosis (CAD) is preferred as it assists the radiologists in efficient diagnosis. In this work, a novel supervised classification technique is proposed using histogram of oriented gradient (HOG) and neighborhood preserving embedding (NPE). Our method is evaluated using 2000 chest X-ray images and can efficiently classify normal and abnormal classes with a promising performance of 97.95{\%} accuracy, using support vector machine (SVM) classifier.",
author = "U. Raghavendra and Anjan Gudigar and Rao, {Tejaswi N.} and Hamido Fujita and Acharya, {U. Rajendra}",
year = "2018",
month = "1",
day = "1",
doi = "10.3233/978-1-61499-900-3-1018",
language = "English",
series = "Frontiers in Artificial Intelligence and Applications",
publisher = "IOS Press",
pages = "1018--1026",
editor = "Enrique Herrera-Viedma and Hamido Fujita",
booktitle = "New Trends in Intelligent Software Methodologies, Tools and Techniques - Proceedings of the 17th International Conference, SoMeT 2018",
address = "Netherlands",

}

Raghavendra, U, Gudigar, A, Rao, TN, Fujita, H & Acharya, UR 2018, Automated detection of lung nodules using HOG technique with chest X-ray images. in E Herrera-Viedma & H Fujita (eds), New Trends in Intelligent Software Methodologies, Tools and Techniques - Proceedings of the 17th International Conference, SoMeT 2018. Frontiers in Artificial Intelligence and Applications, vol. 303, IOS Press, pp. 1018-1026, 17th International Conference on New Trends in Intelligent Software Methodology Tools and Techniques, SoMeT 2018, Granada, Spain, 26-09-18. https://doi.org/10.3233/978-1-61499-900-3-1018

Automated detection of lung nodules using HOG technique with chest X-ray images. / Raghavendra, U.; Gudigar, Anjan; Rao, Tejaswi N.; Fujita, Hamido; Acharya, U. Rajendra.

New Trends in Intelligent Software Methodologies, Tools and Techniques - Proceedings of the 17th International Conference, SoMeT 2018. ed. / Enrique Herrera-Viedma; Hamido Fujita. IOS Press, 2018. p. 1018-1026 (Frontiers in Artificial Intelligence and Applications; Vol. 303).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Automated detection of lung nodules using HOG technique with chest X-ray images

AU - Raghavendra, U.

AU - Gudigar, Anjan

AU - Rao, Tejaswi N.

AU - Fujita, Hamido

AU - Acharya, U. Rajendra

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Lung disease is a growing disease and hence needs lot of attention. It is difficult to delineate the boundary of the lung when it is imaged through X-ray due to poor resolution. Hence, computer aided diagnosis (CAD) is preferred as it assists the radiologists in efficient diagnosis. In this work, a novel supervised classification technique is proposed using histogram of oriented gradient (HOG) and neighborhood preserving embedding (NPE). Our method is evaluated using 2000 chest X-ray images and can efficiently classify normal and abnormal classes with a promising performance of 97.95% accuracy, using support vector machine (SVM) classifier.

AB - Lung disease is a growing disease and hence needs lot of attention. It is difficult to delineate the boundary of the lung when it is imaged through X-ray due to poor resolution. Hence, computer aided diagnosis (CAD) is preferred as it assists the radiologists in efficient diagnosis. In this work, a novel supervised classification technique is proposed using histogram of oriented gradient (HOG) and neighborhood preserving embedding (NPE). Our method is evaluated using 2000 chest X-ray images and can efficiently classify normal and abnormal classes with a promising performance of 97.95% accuracy, using support vector machine (SVM) classifier.

UR - http://www.scopus.com/inward/record.url?scp=85063391315&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063391315&partnerID=8YFLogxK

U2 - 10.3233/978-1-61499-900-3-1018

DO - 10.3233/978-1-61499-900-3-1018

M3 - Conference contribution

T3 - Frontiers in Artificial Intelligence and Applications

SP - 1018

EP - 1026

BT - New Trends in Intelligent Software Methodologies, Tools and Techniques - Proceedings of the 17th International Conference, SoMeT 2018

A2 - Herrera-Viedma, Enrique

A2 - Fujita, Hamido

PB - IOS Press

ER -

Raghavendra U, Gudigar A, Rao TN, Fujita H, Acharya UR. Automated detection of lung nodules using HOG technique with chest X-ray images. In Herrera-Viedma E, Fujita H, editors, New Trends in Intelligent Software Methodologies, Tools and Techniques - Proceedings of the 17th International Conference, SoMeT 2018. IOS Press. 2018. p. 1018-1026. (Frontiers in Artificial Intelligence and Applications). https://doi.org/10.3233/978-1-61499-900-3-1018