Retrospective Research: Analysis of Liver ³¹P Magnetic Resonance Spectroscopy Combined with Support Vector Machine

Abstract:

Abstract. Support vector machine is in the statistical learning theory developed on the basis of a new kind of machine learning method, field in pattern recognition in a wide range of applications. Artificial intelligence technology has been widely used in medical field. Among them, the support vector machine (SVM) technology can mass of data for feature vector extraction. ³¹P(Phosphorus-31) magnetic resonance imaging in clinical spectrum analysis, facing mass data, can use the support vector machine (SVM) of ³¹P magnetic resonance spectroscopy data modeling, used in liver disease classification of common nodules, this experiment set up three research object: hepatocellular carcinoma (HCC), liver cirrhosis and normal liver tissue. Through the kernel function based on polynomial and RBF kernel function of support vector machine classifier carries on the comparison, and get three liver classification recognition rate. Experiments show that based on ³¹P magnetic resonance spectroscopy data of support vector machine (SVM) model can be classified to living liver diagnostic forecast, so as to improve the ³¹P magnetic resonance spectroscopy on HCC diagnosis accuracy rate.

• Periodical: Applied Mechanics and Materials (Volumes 220-223)
• Pages: 2936-2940
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.220-223.2936
• Online since: November 2012
• Authors: Qiang Liu, Shao Qing Wang, Dong Yue Yu, Guang Ju Liang
• Keywords: Hepatocellular Carcinoma (HCC), Magnetic Resonance Spectroscopy, Phosphorus, Support Vector Machine (SVM)

References

[1] Q. Liu, B. Wang, L.B.Wu: J. Med. Imaging, Vol.13(2003), p.11

[2] S. Leij-Halfwerk , J. Agteresch-Hendrik and E. Sijens-Paul: Hepatology. Vol.35 (2002), p.2

[3] AK Lim , N. Patel , G. Hamilton: Hepatology. Vol.5(2003), p.4

[4] V N Vapnik: Statistical Learning Theroy. New York: Wiley Interscience (1998).

[5] H.N. Qi: Computer engineering. Vol.30(2004) , p.10

[6] N. Cristianini, J. Shawe-Taylor, in:A N introduction to support vector machine and other kernel-based learning methods. Beijing: Pub. House of Elec. Industry (2004).

DOI: 10.1017/cbo9780511801389

[7] Y. Mao, X. Zhou, D. Pi D. J.: zhejiang university science. Vol.6B(2005), p.10

[8] S. S. Keerthi, C. J. Lin: Neural Computation. 15(2003).

[9] P.C. Li, S.H. Xu: Computer engineering and design. Vol.26(2005), p.2

[10] J. Han, M. Kamber: Data Mining: Concepts and Techniques. San Francisco: Morgan Kaufmann(2005), pp.363-366.

[11] M.F. Li, S.Y. Eun: Information Technology in Biomedicine. Vol.7(2003), p.3

[12] B. Scho., in: A.J. Smola.Learning with kernels. Combridge(2002), MA: MIT Press.