AIRCC's International Journal of Computer Science and Information Technology

Open Access Open Access  Restricted Access Subscription Access

A Modified Binary PSO Based Feature Selection for Automatic Lesion Detection in Mammograms


Affiliations
1 Department of Computer Applications, BPC College, Piravom, India
2 Department of Computer Science, Government College, Nedumangad, India
3 Department of Imageology, Regional Cancer Center, Thiruvananthapuram, India
 

This paper presents an effective feature selection method that can be applied to build a computer aided diagnosis system for breast cancer in order to discriminate between healthy, benign and malignant parenchyma. Determining the optimal feature set from a large set of original features is an important preprocessing step which removes irrelevant and redundant features and thus improves computational efficiency, classification accuracy and also simplifies the classifier structure. A modified binary particle swarm optimized feature selection method (MBPSO)has been proposed where k-Nearest Neighbour algorithm with leave-one-out cross validation serves as the fitness function. Digital mammograms obtained from Regional Cancer Centre, Thiruvananthapuram and the mammograms from web accessible mini-MIAS database has been used as the dataset for this experiment. Region of interests from the mammograms are automatically detected and segmented. A total of 117 shape, texture and histogram features are extracted from the ROIs. Significant features are selected using the proposed feature selection method.Classification is performed using feed forward artificial neural networks with back propagation learning. Receiver operating characteristics (ROC) and confusion matrix are used to evaluate the performance. Experimental results show that the modified binary PSO feature selection method not only obtains better classification accuracy but also simplifies the classification process as compared to full set of features. The performance of the modified BPSO is found to be at par with other widely used feature selection techniques.

Keywords

Binary Particle Swarm Optimization, Feed Forward Artificial Neural Networks, Feature Selection, K-Nearest Neighbour.
User
Notifications
Font Size

  • R Siegel, D. Naishadham and A.Jeimal(2013)“Cancer Statistics 2013”, CA: A Cancer Journal for Clinicians, Vol. 63, pp. 11-30.

  • (2012-2014) Statistics of Breast Cancer in India. “Trends of Breast Cancer in India” [online] Availablehttp://www.breastcancerindia.net/statistics/trends.html

  • (2013-14) World Cancer Research Fund International, “Cancer Facts and Figures” [online] Available http://www.wcrf.org/int/cancer-facts-and-figures

  • (2016) American Cancer Society, “Breast Cancer Signs and Symptoms” [online] Available https://www.cancer.org/cancer/breast-cancer/about/breast-cancer-signs-and-symptoms.html

  • K.Hu, X. Gao and F.Li (2011) “Detection of suspicious lesions by adaptive thresholding based on multi resolution analysis in mammograms”, IEEE Transactions on Instrumentation and Measurement, Vol. 60 (2), pp. 462-472.

  • K.U Sheba and S. Gladston Raj (2016) “Objective quality assessment of image enhancement methods in digital mammography-A comparative study”,Signal and Image Processing: An International Journal, Vol. 7(4), pp.1-13.

  • M.J.G Calas, B Gutfilen and W.C.A Pereira (2012) CAD and Mammography: Why use this tool?”, Radilogical Brasileira, Vol. 45 (1) , pp. 46-52.

  • J.Deeba and S.T Selvi(2014) “Computer-aided detection of breast cancer on mammograms: A Swarm Intelligence optimized wavelet neural network approach”, Journal of Biomedical Informatics, Vol. 49, pp.45-52.

  • El-Baz, G.M Beache, G Gimel’farb et.al., (2013)“ Computer-aided diagnosis system for lung cancer: challenges and methodologies”, International Journal of Biomedical Imaging, Vol 2013, Article T D 942353, 46 pages.doi:10,1155/2013/942353.

  • K.U Sheba and Gladston Raj S.,(2017) “Detection of lesions in mammograms using grey-level, texture and shape features”, Journal of Advanced Research in Dynamical and Control Systems, Vol. 9 Sp-16, pp. 919-936.

  • B.I Shak and Anis(2016) “Variable selection using support vector regression and random forests: A comparative study”,Intelligent Data Analysis, Vol. 20 (1), pp. 83-104.

  • B. Xue, MZhang and W.N Browne(2012) “New fitness functions in binary particle swarm optimization for feature selection”, IEEE World Congress on Computational Intelligence (WCCI 2012),Brisbane, Australia.

  • A.Unler and A. Murat(2010) “A discrete particle swarm optimization method for feature selection in binary classification problems”, European Journal of Operational Research, Vol. 206, pp. 528-539.

  • V. Kothari, J. Anuradha, S. Shah and P.Mittal (2012) “A survey on particle swarm optimization in feature selection”, In: Krishna P.Y, Babu M.R, Ariwa E. (eds), Global Trends in Information systems and software applications, Vol. 270, pp. 192-201.

  • X. Wang, J. Yang, X. Teng, W. Xia and R. Jensen(2007)“ Feature selection based on rough sets and particle swarm optimization”, Pattern Recognition Letters, Vol. 28(4), pp. 459-471.

  • B.Xue, S. Nguyen and M. Zhang(2014) “Anew binary particle swarm optimization algorithm for feature selection”, In: Esparcia-Alca’zar A., Mora A.(eds). Applications of Evolutionary Computation. EvoAapplications 2014, Lecture Notes in Computer science, Vol. 8602. Springer Berlin, Heidelberg. pp 501-513.

  • B.Tran, B. Xue and M. Zhang (2014) “Overview of PSO for feature selection in classification”, In: Dick G et.al (eds). Simulated Evolution and Learning (SEAL 2014),Lecture Notes in Computer Science, Vol. 8886, Springer, Cham, pp. 605-617.

  • Z.Yong, G. Dunwei, H.Ying and Z. Wanqiu (2015) “Feature selection algorithm based on bare bones PSO”. Neurocomputing, Vol.148(6), pp. 150-157.

  • M.T Wong, X.He, W.C. Yeh, Z Ibrahim and Y.Y Chung (2014) “Feature selection and mass classification using PSO and SVM”, In: Loo C.K, Yap K.S, Wong K.W, Beng Jin A.T, Huang K (eds)., Neural information processing. ICONN 2014, Lecture Notes in Computer Science, Vol. 8836, Springer, Cham, pp. 439-446.

  • S. Sivakumar and C. Chandrasekhar (2014) “Modified PSO based feature selection for classification of lung CT images”, International Journal of Computer Science and Information Technologies, Vol. 5(2), pp. 2095-2098.

  • I. Zyout and I. Abdel-Qader(2011) “Classification of microcalcification clusters via PSO-KNN heuristic parameter selection and GLCM features”, International Journal of Computer Applications, Vol. 31(2), pp. 34-39.

  • M.T Wong, X.He and H Nguyen (2012) “Particle Swarm Optimization based feature selection in mammogram mass classification”, Computerized Health Care (ICCH 2012), International conference on, pp.152-157, Dec 2012.

  • J. Kennedy and R. Eberhart(1995) “Particle Swarm Optimization”, In:Proceedings of the 1995 IEEE international conference on neural networks,Perth, Australia, Vol. 4,pp. 1942-1948.

  • J. Kennedy and R. Eberhart (1997), “A discrete binary version of particle swarm algorithm”, In: Proceedings of the 1997 IEEE International Conference on Systems, Man and Cybernetics (SMC 97), Vol. 5, pp. 4104-4108.

  • Y.Shi and R. Eberhart(1998) “A Modified Particle Swarm Optimizer”, In: Proceedings of IEEE International Conference on Evolutionary Computation, World Congress on Computational Intelligence, Anchorage, Alaska.

  • B.Xue, M.Zhang and W.N Browne( 2012) “ New Fitness Functions in binary particle swarm optimization for feature selection, IEEE World Congress on Computational Intelligence (WCCI 2012),Brisbane, Australia.

  • S.Zhang, X.Li, M.Zong, X. Zhu and R.Wang (2017) “Efficient KNN classification with different numbers of nearest neighbors”, IEEE Transactions on Neural Networks and Learning systems, Vol. 99, pp.1-12.

  • A.Vehtari, A.Gelman andJ.Gabry (2017) “Practicalbayesian model evaluation using leave-one-out cross validation and WAIC”, Statistics and Computing, Vol. 27(5),pp.1413-1432.

  • J Suckling et.al (1994). The mammographic Image Analysis Society Digital Mammogram database. Exerpta Medica. International Congress Series 1069, pp. 375-378.

  • K.U Sheba and S. Gladston Raj (2017) “Detection of Lesions in Mammograms using grey-level, texture and shape features”, Journal of Advanced Research in Dynamical and Control Systems, Vol.(16)-Special Issue, pp. 919-936.

  • K.U Sheba and S. Gladston Raj (2017) “Adaptive fuzzy logic based bi-histogram equalization for contrast enhancement of mammograms”, In: Proceedings of IEEE International Conference on Intelligent Computing, Instrumentation and Control Technologies, Kannur, Kerala.(to be published)

  • M.J Homer (2004) “Breast Imaging, Standard of care and the expert”,Radiologic Clinics of North America, Vol. 42(5), pp. 963-974.

  • P.Tahmasebi and A.Hezarkhani (2011) “Application of a modular feed forward neural network for grade estimation”, Natural Resources Research, Vol. 20(1), pp. 25-32.

  • Z.M Hera and D.F Gillies (2015) “ A review of feature selection and feature extraction methods applied on micro array data”, Advances on Bioinformatics, Vol. 2015, Article ID 198363, 13 pages. doi 10.1155/2015/198363

  • I. Guyon, J. Weston, S.Barnhill and V.Vapnik, (2002) “Gene selection for cancer classification using support vector machines”, Mach.Learn, Vol. 46(1-3), pp. 389-422.

  • T.Hayes, S.Usami et.al, (2015) “Using classification and regression Trees (CART) and random forest to analyze attrition: Results from two simulations”, Psychology Aging, Vol. 30(4), pp. 911-929.


Abstract Views: 280

PDF Views: 133




  • A Modified Binary PSO Based Feature Selection for Automatic Lesion Detection in Mammograms

Abstract Views: 280  |  PDF Views: 133

Authors

K. U. Sheba
Department of Computer Applications, BPC College, Piravom, India
S. Gladston Raj
Department of Computer Science, Government College, Nedumangad, India
D. Ramachandran
Department of Imageology, Regional Cancer Center, Thiruvananthapuram, India

Abstract


This paper presents an effective feature selection method that can be applied to build a computer aided diagnosis system for breast cancer in order to discriminate between healthy, benign and malignant parenchyma. Determining the optimal feature set from a large set of original features is an important preprocessing step which removes irrelevant and redundant features and thus improves computational efficiency, classification accuracy and also simplifies the classifier structure. A modified binary particle swarm optimized feature selection method (MBPSO)has been proposed where k-Nearest Neighbour algorithm with leave-one-out cross validation serves as the fitness function. Digital mammograms obtained from Regional Cancer Centre, Thiruvananthapuram and the mammograms from web accessible mini-MIAS database has been used as the dataset for this experiment. Region of interests from the mammograms are automatically detected and segmented. A total of 117 shape, texture and histogram features are extracted from the ROIs. Significant features are selected using the proposed feature selection method.Classification is performed using feed forward artificial neural networks with back propagation learning. Receiver operating characteristics (ROC) and confusion matrix are used to evaluate the performance. Experimental results show that the modified binary PSO feature selection method not only obtains better classification accuracy but also simplifies the classification process as compared to full set of features. The performance of the modified BPSO is found to be at par with other widely used feature selection techniques.

Keywords


Binary Particle Swarm Optimization, Feed Forward Artificial Neural Networks, Feature Selection, K-Nearest Neighbour.

References