Feature Extraction Using Composite Individual Genetic Programming: An Application to Mass Classification

Abstract:

This paper proposes a novel method for breast cancer diagnosis using the features generated by genetic programming (GP). We developed a new individual combination pattern (Composite individual genetic programming) which regards several individual as one unity to generate more powerful features that can improve the discriminatory performance of a classifier and reducing the input feature dimensionality at the same time. The performance of the proposed method is demonstrated by extensive experiments on MIAS and DDSM mammographic image database.

• Periodical: Applied Mechanics and Materials (Volumes 198-199)
• Pages: 468-473
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.198-199.468
• Online since: September 2012
• Authors: Ying Hua Lv, Yu Ting Guo, Hui Sun, Ming Zhang, Jian Zhong Wang
• Keywords: Feature Extraction, Genetic Progamming, Mammogram, Mass

References

[1] Cancer Research UK. Breast cancer factsheet; February (2004).

[2] NationalCancer Institute ofCanada. Canadian cancer statistics 2006; (2006).

[3] Alfonso Rojas Domínguez, Asoke K, NandiToward breast cancer diagnosis based on automated segmentation ofmasses inmammograms, Pattern Recognition 42 (2009) , 1138-1148.

DOI: 10.1016/j.patcog.2008.08.006

[4] Encarnacao JL, Peitgen H-O, Sakas G, Englert G. Fractal geometry and computer graphics. Berlin: Springer-Verlag; (1992).

[5] Caldwell CB, Stapleton SJ, Holdsworth DW, Jong RA, WeiserWJ, Cooke G, et al. Characterization of mammographic parenchymal pattern by fractal dimension. Phys Med Biol, 1990; 35: 235-47.

DOI: 10.1088/0031-9155/35/2/004

[6] Bruce LM, Adhami RR. Classifying mammographic mass shapes using the wavelet transform modulus-maxima method. IEEE Trans Med Imag 1999; 18(12): 1170-7.

DOI: 10.1109/42.819326

[7] Homer MJ. Imaging features and management of characteristically benign and probably benign lesions. Radiol Clin N Am 1987; 25(5): 939-51.

DOI: 10.1016/s0033-8389(22)02273-4

[8] Homer MJ. Breast imaging: pitfalls, controversies and some practical thoughts. Radiol Clin N Am 1985; 23(3): 459-72.

[9] Mavroforakis M, Georgiou H, Dimitropoulos N, Cavouras D, Theodoridis S. Significance analysis of qualitative mammographic features, using linear classifiers, neural networks and support vector machines. Eur J Radiol 2005; 54: 80-9.

DOI: 10.1016/j.ejrad.2004.12.015

[10] Z.M. Huo, M.L. Giger, C.J. Vyborny, D.E. Wolverton, R.A. Schmidt,K. Doi, Automatedcomputerized classification of malignant and benign masses on digitized mammograms, Acad. Radiol. 5 (1998)155-168.

DOI: 10.1016/s1076-6332(98)80278-x

[11] N. Petrick, H.P. Chan, B. Sahiner, M.A. Helvie, Combined adaptiveenhancement and region-growing segmentation of breast masses on digitized mammograms, Med. Phys. 26 (1999) 1642–1654.

DOI: 10.1118/1.598658

[12] N.M. El-Faramawy, R.M. Rangayyan, J.E.L. Desautels, O.A. Alim, Shape factors for analysis of breast tumors in mammograms, 1996 Canadian Conference on Electrical and Computer Engineering, 1996, p.355–358.

DOI: 10.1109/ccece.1996.548110

[13] N. Petrick, H.P. Chan, B. Sahiner, M.A. Helvie, Combined adaptive enhancement and region-growing segmentation of breast masses on digitized mammograms, Med. Phys. 26 (1999) 1642–1654.

DOI: 10.1118/1.598658

[14] B. Sahiner, H.P. Chan, N. Petrick, D. Wei, M.A. Helvie, D.D. Adler M.M. Goodsitt, Classification of mass and normal breast tissue: a convolution neural network classifier with spatial domain and texture images, IEEE Trans. Med. Imaging 15 (5) (1996).

DOI: 10.1109/42.538937

[15] B. Sahiner, H.P. Chan, N. Petrick, M.A. Helvie, M.M. Goodsitt, Design of a high-sensitivity classifier based on a genetic algorithm: application to computer-aided diagnosis, Phys. Med. Biol. 43 (10)(1998) 2853–2871.

DOI: 10.1088/0031-9155/43/10/014

[16] F.F. Yin, M.L. Giger, K. Doi, C.J. Vyborny, R.A. Schmidt, Computerized detection of masses in digital mammograms: investigation of feature-analysis techniques, J. Digital Imaging 7(1994) 18–26.

DOI: 10.1007/bf03168475

[17] K. Bovis, S. Singh, J. Fieldsend, C. Pinder, Identification of masses in digital mammograms with MLP and RBF nets, in: Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks Com, 2000, p.342–347.

DOI: 10.1109/ijcnn.2000.857859

[18] B. Sahiner, N. Petrick, H.P. Chan, Computer-aided characterization of mammographic masses: accuracy of mass segmentation and its effects on characterization, IEEE Trans. Med. Imaging 20 (12)(2001) 1275–1284.

DOI: 10.1109/42.974922

[19] B. Sahiner, H.P. Chan, N. Petrick, M.A. Helvie, M.M. Goodsitt, Design of a high-sensitivity classifier based on a genetic algorithm: application to computer-aided diagnosis, Phys. Med. Biol. 43 (10)(1998) 2853–2871.

DOI: 10.1088/0031-9155/43/10/014

[20] J.R. Koza, Genetic Programming: On the Programming of Computers by Means of Natural Selection, MIT Press, Cambridge, (1992).

[21] Koza, John R. Genetic Programming . Cambridge, MA: MIT Press, (1992).

[22] J Suckling et al (1994): The Mammographic Image Analysis Society Digital Mammogram Database Exerpta Medica. International Congress Series 1069 pp.375-378.

[23] Alfonso Rojas Dom´ ınguez, Asoke K. Nandi, Detection of masses in mammograms via statistically based enhancement, multilevel-thresholding segmentation, and region selection, Computerized Medical Imaging and Graphics 32 (2008) 304–315.

DOI: 10.1016/j.compmedimag.2008.01.006

[24] Pasquale Delogu, Maria Evelina Fantacci, Parnian Kasae, Alessandra Retico, Characterization of mammographicmasses using a gradient-based segmentation algorithmand a neural classifier, Computers in Biology and Medicine 37 (2007) 1479 – 1491.

DOI: 10.1016/j.compbiomed.2007.01.009