A New Feature Extraction Approach Using Contourlet Transform and T-Test Statistics for Mammogram Classification

Abstract— In this study, a CAD system is recommended for the classification of mammographic images. The images are classified as normal-abnormaland benign-malignant. The proposed system consists of three basic steps: the feature extraction, determination of the distinguishing capabilities of the features and selection, and classification. The distinguishing capabilities of the features mean determining the best or optimal features. Thanks to this determination, mammograms could be put into classes with high accuracy. The determination process is carried out using thresholding and t-test statistics. Classification is performed repeatedly for all threshold values using support vector machine. Among the obtained results of the classification, the optimal feature set, which has the best classification performance, is selected. Finally, to evaluate the optimal feature set, classification carries out applying 5-fold cross-validation.

PDF

___

[1] M.D. Chin, K.K. Evans, J.M. Wolfe, J. Bowen, J.W. Tanaka, “Inversion effects in the expert classification of mammograms and faces”, Cognitive Research: Principles and Implications, vol. 3, 2018, pp. 31.
[2] Y. Wang, H. Shi, S. M, “A new approach to the detection of lesions in mammography using fuzzy clustering”, J. Int. Med. Res. vol. 39, no. 6, 2011, pp. 2256–2263.
[3] N.J. Massat, A. Dibden, D. Parmar, J. Cuzick, P.D. Sasieni, S.W. Duffy, “Impact of screening on breast cancer mortality: the UK program 20 years on”, Cancer Epidemiology and Prevention Biomarkers, vol. 25, no. 3, 2016, pp. 455-62.
[4] T. Onega, L.E. Goldman, R.L. Walker, D.L. Miglioretti, D.S. Buist, S. Taplin, B.M. Geller, D.A. Hill, R. Smith-Bindman, “Facility mammography volume in relation to breast cancer screening outcomes”, J. Med. Screen, vol. 23, 2016, pp. 31.
[5] M.M. Pawar, S.N. Talbar, “Genetic fuzzy system (GFS) based wavelet co-occurrence feature selection in mammogram classification for breast cancer diagnosis” Perspectives in Science, vol.8, 2016, pp. 247–250.
[6] L. Berlin, “Radiologic errors, past, present and future”, Diagnosis, vol. 1, no. 1, 2014, pp. 79–84.
[7] Y. Li, H. Chen, Y. Yang, L. Cheng, L. Cao, “A bilateral analysis scheme for false positive reduction in mammogram mass detection”, Computers in Biology and Medicine, vol. 57, 2015, pp. 84–95.
[8] N. Gedik, A. Atasoy, “Performance evaluation of the wave atom algorithm to classify mammographic images”, Turk. J. Elec. Eng. & Comp. Sci., vol.22, 2014, pp. 957–969.
[9] V. Chaurasia, S. Pal, “A novel approach for breast cancer detection using data mining techniques”, International Journal of Innovative Research in Computer and Communication Engineering, vol. 2, no. 1, 2014, pp. 1-17.
[10] L. Dora, S. Agrawal, R. Panda, A. Abraham, “Optimal breast cancer classification using Gauss–Newton representation based algorithm”, Expert Systems with Applications, vol. 85, 2017, pp. 134-145.
[11] N. Gedik, “Breast cancer diagnosis system via contourlet transform with sharp frequency localization and LS-SVM”, Journal of medical imaging and health informatics, vol. 5, 2015, pp. 1–9.
[12] W. Yang, L. Tianhui, “A Robust Feature Vector Based on Waveatom Transform for Mammographic Mass Detection,” ICVR 2018 Proceedings of the 4th International Conference on Virtual Reality, Hong Kong, pp.133-139, 24-26 February 2018.
[13] N. Gedik, “A new feature extraction method based on multi-resolution representations of mammograms”, Applied Soft Computing, vol. 44, no. 1, 2016, pp. 128-133.
[14] M.M. Jadoon, Q. Zhang, I.U. Haq, A. Jadoon, A. Basit, S. Butt, “Classification of mammograms for breast cancer detection based on curvelet transform and multi-layer perceptron”, Biomedical Research, vol. 28, no. 10, 2017, pp. 4311-4315.
[15] Y. Chen, Y. Zhang, H.M. Lu, X.Q. Chen, J.W. Li, S.H. Wang, “Wavelet energy entropy and linear regression classifier for detecting abnormal breasts”, Multimed Tools Appl., vol. 77, 2018, pp. 3813–3832.
[16] M.M. Eltoukhy, I. Faye, B.B. Samir, “A statistical based feature extraction method for breast cancer diagnosis in digital mammogram using multiresolution representation”, Computers in biology and medicine, vol. 42, no. 1, 2012, pp. 123–128.
[17] M.M. Eltoukhy, I. Faye, “An optimized feature selection method for breast cancer diagnosis in digital mammogram using multiresolution representation”, Applied Mathematics and Information Sciences, vol. 8, no. 6, 2014, pp. 2921-2928.
[18] D. Sehrawat, A. Sehrawat, D. Jaiswal, A. Sen, “Detection and classification of tumor in mammograms using discrete wavelet transform and support vector machine”, International Research Journal of Engineering and Technology (IRJET), vol. 4, no. 5, 2017, pp. 1328-1334.
[19] Y. Lu, M.N. Do, “A new contourlet transform wıth sharp frequency localızatıon”, IEEE 2006 International Conference on Image Processing, Atlanta, Georgıa, U.S.A., pp.1629-1632, 8-11 October 2006.
[20] V. Vapnik, “The Nature of Statistical Learning Theory”, Springer-Verlag New York, 1995.
[21] V. Vapnik, “Statistical Learning Theory”, New York: Wiley, 1998.
[22] V. Vapnik, E. Levin, Y.L. Cun, “Measuring the VC-dimension of a Learning Machine”, Neural Computation, 6(5), MIT Press, Cambridge, 1994.
[23] H. Liu, J. Li, L. Wong, “A comparative study on feature selection and classification methods using gene expression profiles and proteomic patterns”, Genome Inf., vol. 13, no. 1, 2002, pp. 51–60.
[24] http://peipa.essex.ac.uk/info/mias.html (20.11.2018)