(3.90.187.11)
Users online: 10214     
Ijournet
Email id
 

Indian Journal of Public Health Research & Development
Year : 2018, Volume : 9, Issue : 10
First page : ( 1126) Last page : ( 1132)
Print ISSN : 0976-0245. Online ISSN : 0976-5506.
Article DOI : 10.5958/0976-5506.2018.01290.1

SVM based lung cancer classification using texture and fractal features from PET/CT images

Punithavathy K.1,*, Poobal Sumathi2, Ramya M. M.3

1Hindustan Institute of Technology and Science, Chennai

2KCG College of Technology, Karapakkam, Chennai

3Hindustan Institute of Technology and Science, Chennai, India

*Corresponding Author: Punithavathy K. Hindustan Institute of Technology and Science, Chennai, 603103, India Email: punitha1994@gmail.com

Online published on 1 November, 2018.

Abstract

Early lung cancer detection is extremely challenging as symptoms are not exposed till advanced stage. This study is aimed at developing a computer aided diagnosis (CAD) system with image processing techniques and support vector machine (SVM) in lung cancer classification from positron emission tomography/computed tomography (PET/CT) images. The developed CAD system utilized fuzzy enhancement for contrast improvement. Texture and fractal features were used for training the SVM. This study utilized 82 PET/CT images and 10-fold cross validation to analyze the performance of the classifiers. Experimental study showed that SVM classifier with radial basis function (RBF) kernel of width, σ = 1 outperformed the other SVM models. It produced maximum accuracy of 98.13% using texture and fractal features from PET/CT images. The RBF kernel is effective in handling sparse, non-linear, multi-dimensional data to transform it into linearly separable.

Top

Keywords

Lung cancer, PET/CT, feature extraction, computer aided diagnosis, support vector machine.

Top

  
║ Site map ║ Privacy Policy ║ Copyright ║ Terms & Conditions ║ Page Rank Tool
733,144,939 visitor(s) since 30th May, 2005.
All rights reserved. Site designed and maintained by DIVA ENTERPRISES PVT. LTD..
Note: Please use Internet Explorer (6.0 or above). Some functionalities may not work in other browsers.