Ovarian Cancer Detection Method Using Proteomic Patterns, Independent Component Analysis, and Support Vector Machine

• Wesley B. Dominices de Araujo UEMA
• Lúcio F. A. Campos UEMA
• Aline S. Furtado FAMA

Abstract

It is proposed a CAD method to detect ovarian cancer, using Independent Component Analysis, the technique of Maximum Relevance and Minimum Redundancy, to reduce dimensionality and the computational cost, and Support Vector Machine, for classification of samples between presence or absence of cancer. The method was tested with a proteomic patterns set from SELDI-TOF database, and best performance was achieved with 10 features vector, resulting 98.80% of accuracy, with 95.65% of specificity and 100% of sensitivity.

References

Arieshanti, I., Purwananto, Y. and Tjandrasa, H. (2013) “Ovarian Cancer Identification using One-Pass Clustering and k-Nearest Neighbors”. TELKOMNIKA, Vol.11, No.4, December, pp. 797-802.

Bast, R. C., Feeney, M., Lazarus, H., Nadler, L. M., Colvin, R. B. and Knapp, R. C. (1981) “Reactivity of a monoclonal antibody with human ovarian carcinoma”. J. Clin. Invest, November.

Bushberg, J. T., Seibert, A. J., Leidholdt, E. M. and Boone, J. M. (2001) “The Essential Physics of Medical Imaging”, second ed., Lippincott Williams & Wilkins, Philadelphia, PA.

Campos, L. F. A., Barros, A. K. and Silva, A. C. (2007) “Independent Component Analysis and Neural Networks Applied for Classification of Malignant, Benign and Normal Tissue in Digital Mammography”, In: Special Issue - Methods of Information in Medicine, v. 46, p. 212-215.

Campos, L. F. A., Costa, D. D. and Barros, A. K. (2008) “Segmentation of breast cancer in Digital Mammograms using texture features and independent component analysis”. Proceedings of the BICS. Brain Inspired Cognitive Systems, Brazil.

Cerqueira, E. O., Andrade, J. C., Poppi, R. J. and Mello, C. (2001) “Determinação de constituintes químicos em madeira de eucalipto por pi-cg/em e calibração multivariada: comparação entre redes neurais artificiais e Máquinas de Vetor suporte”. Quim. Nova, v. 24, p. 864.

Christoyianni, I., Koutras, A., Kokkinakis, G. (2002) “Computer aided diagnosis of breast cancer in digitized mammograms”, In:Comp. Med. Imag. & Graph., 26:309-319.

Costa, D. D., Campos, L. F. A. and Barros, A. K. (2011) “Classification of breast tissue in mammograms using efficient coding”. In BioMedical Engineering OnLine. Disponível em: [link].

Ding, C. and Peng, H. (2003) “Minimum Redundancy Feature Selection from Microarray Gene Expression Data”, Proc. Second IEEE Computational Systems Bioinformatics Conf., p. 523-528, August.

Donald, D. (2006) “Bagged super wavelets reduction for boosted prostate cancer classification of seldi-tof mass spectral serum profiles”, Chemometrics and intelligent Laboratory Systems, vol 82, no. 1, p. 2-7, January.

INCa (2013). Instituto Nacional do Câncer [Online]. Disponível em: [link], acesso em 08/10/2013.

Hornik, K., Stinchombe, M. and White, H. (1989) “Multilayer feedforward networks are universal approximators”. Neural Netw, v. 2, p. 359-366, Marth.

Hyvärinen, A. and Oja, E. (1997) “A fast fixed-point algorithm for independent component analysis”, In: Neural Computation, 9(7):1483-1492.

Iannarilli, F. J. and Rubin, P. A. (2003) “Feature Selection for Multiclass Discrimination via Mixed-Integer Linear Programming”, IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 25, no. 6, pp. 779-783.

Jain, A. K., Duin, R. P. W. and Mao, J. (2000) “Statistical Pattern Recognition: A Review”, IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 1, pp. 4-37.

Kohavi, R. (1995) “A study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection”. In: International joint Conference on artificial intelligence, v. 14, p. 1137-1145.

Kwak, N. and Choi, C. H. (2002) “Input Feature Selection by Mutual Information Based on Parzen Window”, IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, no. 12, pp. 1667-1671.

Marchini, J. L., Heaton, C. and Ripley, B. D. (2004) “FastICA algorithms to perform ICA and Projection Pursuit”. Disponível em: [link].

Oncoguia (2012). “Exames de Imagem para o Diagnóstico do Câncer de Ovário”, [link].

Instituto do Câncer (2014). “Câncer de Ovário”. Disponível em: [link].

Peng, H., Long, F. and Ding, C. (2005) “Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy”. IEEE Transactions on Pattern Analisys and Machine Inteligence. Vol. 27, August.

Seldi–MS (2002) DATABASE. Disponível em: [link], Acesso em October, 2013.

Thakur, A., Mishra, V. and Jain, S. K. (2011) “Feed Forward Artificial Neural Network: Tool for Early Detection of Ovarian Cancer”. Scientia Pharmaceutica. Open Access. DOI: 10.3797/scipharm.1105-11.

Vapnik, V. N. (1998) “Statistical Learning Theory”. John Wiley and Sons.

Vigário, R. (1997) “Extraction of ocular artifacts form ecg using independent components analysis”, Eletroenceph. Clin. Neurophysiol., 103 (3) : 395-404.

Webb, A. (1999) “Statistical Pattern Recognition”. Arnold.

Whelean, O. P., Earll, M. E., Johansson, E., Toft, M. and Eriksson, L. (2006) “Detection of ovarian cancer using chemometric analysis of proteomic profiles”. Chemometrics and Intelligent Laboratory Systems 84, 82–87.

Wilkins, M. R., Sanchez, J. C., Gooley, A. A., Appel, R. D., Humphery-Smith, I, Hochstrasser, D. F. (1996) “Progress with proteome projects: why all proteins expressed by a genome should be identified and how to do it”. Biotechnol Genet Eng; 13:19-50.

Yang, S. Y. (2005) “Application of serum SELDI proteomic patterns in diagnosis of lung cancer”, BMC cancer, vol. 83, no. 5, September.

Yu, J. K. (2004) “An integrated approach to the detection of colorectal cancer utilizing proteomics and bioinformatics”, World J. Gastroenterol, vol. 21, no.10, pp. 3127-3131, October.