Volume 5, Issue 6, November 2017, Page: 70-78
On Feature Selection Methods for Accurate Classification and Analysis of Emphysema CT Images
Musibau Adekunle Ibrahim, Department of Information and Communication Technology, Osun State University, Osogbo, Nigeria
Oladotun Ayotunde Ojo, Department of Physics, Osun State University, Osogbo, Nigeria
Peter Adefioye Oluwafisoye, Department of Physics, Osun State University, Osogbo, Nigeria
Received: Dec. 19, 2017;       Accepted: Jan. 2, 2018;       Published: Jan. 19, 2018
DOI: 10.11648/j.ijmi.20170506.12      View  1547      Downloads  61
Abstract
Feature selection techniques to search for the relevant features that would have the greatest influence on the predictive accuracy have been modified and applied in this paper. Selection search iteratively evaluates a subset of the feature, then modifies the subset and evaluates if the new subset is an improvement over the previous. The performances of the developed models are tested with some classifiers based on the feature variables selected by the proposed approach and the effects of some important parameters on the overall classification accuracy are analysed. Experimental results showed that the proposed approach consistently improved the classification accuracy. The improved classification accuracies on the multi-fractal datasets are statistically significant when compared with the previous methods applied in our previous publications. The use of the feature selection search tool reduces the classification model complexity and produces a robust system with greater efficiency, and excellent results. The research results also prove that the number of growing trees and the threshold values could affect the classification accuracy.
Keywords
Feature Selection, Multi-Fractal Descriptor, Classification Accuracy, Naïve Bayes, Bagged Decision Tree, Emphysema Patterns
To cite this article
Musibau Adekunle Ibrahim, Oladotun Ayotunde Ojo, Peter Adefioye Oluwafisoye, On Feature Selection Methods for Accurate Classification and Analysis of Emphysema CT Images, International Journal of Medical Imaging. Vol. 5, No. 6, 2017, pp. 70-78. doi: 10.11648/j.ijmi.20170506.12
Copyright
Copyright © 2017 Authors retain the copyright of this article.
This article is an open access article distributed under the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Reference
[1]
Y. Han, K. Park, & Y. K. Lee, “Confident wrapper-type semi-supervised feature selection using an ensemble classifier”. 2nd International Conference on Artificial Intelligence, Management Science and Electronic Commerce, AIMSEC – Proceedings.; pp. 4581–4586, 2011. doi:10.1109/AIMSEC.2011.6010202.
[2]
D. Wang, F. Nie, & H. Huang, “Feature Selection via Global Redundancy Minimization,” 2015; 4347 (c), pp. 1–14, 2015. doi:10.1109/TKDE.2015.2426703.
[3]
L. Sørensen, S. B. Shaker, and M. De. Bruijne, “Quantitative Analysis of Pulmonary Emphysema using Local Binary Patterns,” IEEE transactions on medical imaging. 29, 2, pp. 559–569, 2010.
[4]
Ibrahim, M. and Mukundan, R. “Multi-fractal Techniques for Emphysema Classification in Lung Tissue Images”. Proceeding of International Conference on Environment, Chemistry and Biology; pp. 115-119, 2014.
[5]
R. Duda, P. Hart, and D. Stork, “Pattern classification and scene analysis”. New York. 2011.
[6]
A. Papadopoulos, M. Plissiti, and D. Fotiadis, “Medical-image processing and analysis for CAD systems”. Journal of Applied Signal Processing. 2, 5, pp. 25–41, 2005.
[7]
M. Ibrahim & R. Mukundan, “Cascaded techniques for improving emphysema classification in computed tomography images,” Artificial Intelligence Research; 4 (2), pp. 112–118, 2015. doi:10.5430/air.v4n2p112.
[8]
M. Ibrahim, “Multifractal Techniques for Analysis and Classification of Emphysema Images (PhD thesis),” University of Canterbury, 2017, http://hdl.handle.net/10092/14383.
[9]
J. W. Xu, & K. Suzuki, “Max-AUC feature selection in computer-aided detection of polyps in CT colonography”. IEEE Journal of Biomedical and Health Informatics. 18 (2), pp. 585–593, 2014 doi:10.1109/JBHI.2013.2278023.
[10]
H. Zhang, “A Novel Bayes Model: Hidden Naive Bayes. IEEE Transactions on Knowledge and Data Engineering,” 21 (10), pp. 1361–1371; 2009.
[11]
Q. Liu, S. Shi, H. Zhu, & J. Xiao, “A Mutual Information-Based Hybrid Feature Selection Method for Software Cost Estimation Using Feature Clustering”. 2014 IEEE 38th Annual Computer Software and Applications Conference. pp. 27–32, 2014; doi:10.1109/COMPSAC.2014.99.
[12]
J. A. Mangai, J Nayak, and V. S. Kumar, “A Novel Approach for Classifying Medical Images Using Data Mining Techniques”. International Journal of Computer Science and Electronics Engineering (IJCSEE). 2013; 1, 2.
[13]
R. Bhuvaneswari, & K. Kalaiselvi, “Naive Bayesian Classification Approach in Healthcare Applications”. International Journal of Computer Science. 3 (1), pp. 106–112, 2012.
[14]
H. Zhang, H. and J. Su, “Naive Bayes for optimal ranking. Journal of Experimental & Theoretical Artificial Intelligence”. 20, 2, pp. 79–93; 2008.
[15]
L. M. Wang, X. L. Li, C. H. Cao, and S. M. Yuan,. “Combining decision tree and Naive Bayes for classification. Knowledge-Based Systems”, 19, 7, pp. 511–515; 2006.
[16]
R. Kohavi, and H. John, “Artihficial Intelligence Wrappers for feature subset selection”. Data Mining and Visualization Silicon Graphics. 97, 273–324; 2011.
[17]
P. Domingos, “On the Optimality of the Simple Bayesian Classifier under Zero-One Loss”. 29, pp. 103–130; 1997.
[18]
A. L. Bluma, and P. Langley, “Artificial Intelligence Selection of relevant features and examples in machine”. pp. 245–271, 1997.
[19]
Y. Liu, J. Guo, & J. Lee. “Halftone Image Classification Using LMS Algorithm and Naive Bayes”. IEEE Transactions on Image Processing. 20 (10), pp. 2837–2847, 2011. doi:10.1109/TIP.2011.2136354.
[20]
J. Demšar, G. Leban, and B. Zupan, “Freeviz-an intelligent visualization approach for class-labeled multidimensional data sets”. Proceedings of IDAMAP. 1, pp. 13–18; 2005.
[21]
C. Supriyanto, N. Yusof & B. Nurhadiono, “Two-Level F eature S election for Naive B ayes with Kernel Density,” Estimation in Question Classification based on B loom’s Cognitive Levels. pp. 1–5; 2013.
[22]
L. T. D. Ladha, “Feature Selection Methods and Algorithms”. International Journal of Computer Science and Engineering. 3 (5), pp. 1787–1797; 2011.
[23]
V. Ruiz and S. Nasuto, “Biomedical-image classification methods and techniques”. Costaridou, L. (ed.), 2005.
[24]
H. A. Zhang, “A Novel Bayes Model: Hidden Naive Bayes”. IEEE Transactions on Knowledge and Data Engineering. 21, 10, pp. 1361–1371; 2009.
[25]
K. Mikolajczyk, & C. Schmid, “Performance evaluation of local descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence,” 27 (10), 1615–30; 2005. doi:10.1109/TPAMI.2005.188.
[26]
G. Zhao & P. Matti,”Local Binary Patterns with an Application to Facial Expressions”. Pattern Analysis and Machine Intelligence, IEEE Transactions on. 2007; 29 (6), pp. 915–928.
[27]
S. Marsland, “Machine Learning: An Algorithm Perspective”. (2nd ed.). USA: CRC Press, 2014.
[28]
M. Kallergi, “Evaluation strategies for medical-image analysis and processing methodologies”. International Journal of Image Analysis and Processing Methodologies; 2, 5, pp. 75–91.
[29]
T. Randen, and J. H. Husoy, “Filtering for texture classification”: a comparative study. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1999; 21, 4, pp. 291–310; 2005.
[30]
R. Mukundan and A. Hemsley, “A. Tissue Image Classification Using Multi-Fractal Spectra”. International Journal of Multimedia Data Engineering and Management. 1, 2, pp. 62–75; 2010.
[31]
A. Hemsley, and R. Mukundan, “Multifractal Measures for Tissue Image Classification and Retrieval”. 11th IEEE International Symposium on Multimedia. pp. 618–623; 2009.
Browse journals by subject