JACIII Vol.16 No.1 pp. 55-61
doi: 10.20965/jaciii.2012.p0055


New Method to Assist Discrimination of Liver Diseases by Spherical SOM with Mahalanobis Distance

Norie Kanzaki* and Akihiro Kanagawa**

*Graduate School of Systems Engineering, Okayama Prefectural University, 111 Kuboki, Soja, Okayama 719-1197, Japan

**Faculty of Computer Science & Systems Engineering, Okayama Prefectural University, 111 Kuboki, Soja, Okayama 719-1197, Japan

June 23, 2011
October 12, 2011
January 20, 2012
Mahalanobis distance, spherical SOM, liver disease, automated diagnosis

Spherical SOM, an improved version of a kind of neutral network SOM, has successfully been applied to data analysis in a variety of fields achieving effective results. However, distance measure of commercial spherical SOM is limited to the Euclidean distance and it is not suitable enough to the analysis of biased data such as blood test results. The Mahalanobis distance is said to be effective for the analysis of such medical data. Therefore it is expected that better results should be obtained if spherical SOM with Mahalanobis distance is applied to the analysis of medical data. In this paper, we take blood test items as multi-dimensional vectors and convert the input data into Mahalanobis distance with the aim of developing an automated diagnosis system by spherical SOM with Mahalanobis distance as pseudo input data. Conversion of the input data into Mahalanobis distance ensures correct evaluations of the biased data of blood test results at the same time allowing automated diagnosis based on doctors’ intuitions and experiences. We have grouped subjects of diagnosis whose features were not well discriminated by conventional Mahalanobis distance and have administered detailed discrimination by the group and obtained better discrimination rates. While in the conventional studies TP rates for the following five categories, no liverrelated problem, hepatoma (liver cancer), acute hepatitis, chronic hepatitis and liver cirrhosis, were 100%, 70%, 100%, 80% and 60% respectively, they were 96%, 80%, 71%, 86% and 91% respectively with the proposed method. Significant results were obtained overall except for acute hepatitis.

Cite this article as:
N. Kanzaki and A. Kanagawa, “New Method to Assist Discrimination of Liver Diseases by Spherical SOM with Mahalanobis Distance,” J. Adv. Comput. Intell. Intell. Inform., Vol.16, No.1, pp. 55-61, 2012.
Data files:
  1. [1] H. Tanaka, H. Ishibuchi, and T. Shigenaga, “Fuzzy Inference System Based on Rough Sets and Its Application to Medical Diagnosis, Intelligent Decision Support,” Handbook of Applications and Advances of the Rough Sets Theory (Theory and Decision Library Series D, System Theory, Knowledge Engineering, and Problem Solving), Part 1, Chapter 8, pp. 111-117, 1992.
  2. [2] Z. Zhang, A. Kanagawa, and H. Kawabata, “Associative Memory using Cellular Neural Networks and its Application to Medical Diagnosis,” Japan Society for Fussy Theory and Intelligent Informatics, Vol.16, No.4, pp. 341-348, 2004 (in Japanese).
  3. [3] G. Taguchi and J. Rajesh, “New Trends in Multivariate Diagnosis: Sankhya,” The Indian J. of Statistics, Vol.62, Seriees B, Pt.2, pp. 233-248, 2000.
  4. [4] H. Nakashima, K. Takada, H. Yano I. Takagi, M. Nakada, K. Wakatsuki, M. Yamauchi, and G. Toda, “Forecasting of Future Health from Medical Examination Results using Mahalanobis?Taguchi System,” 19th JCMI, pp. 952-953, 1999 (in Japanese).
  5. [5] M. Oyabu and U. Kiyohiro, “Development of Spherical SOM and its Property,” Proc. SCI 2002, 2002.
  6. [6] D. Nakatsuka and M. Oyabu, “Application of Spherical SOM in Clustering,” Proc. of Workshop on Self-Organizing Maps (WSO M’03), Japan, pp. 203-207, 2003.
  7. [7] K. Oguri, A. Iwata, T. Fukatsu, and K. Yamauchi, “A Diagnosis Support System of Chronic Liver Disease Using an Artificial Neural Network “NI-SYS”,” Bio Medical Engineering, Vol.32, No.2, pp. 106-111, 1994 (in Japanese).
  8. [8] P. Mahalanobis, “On the generalized distance in statistics,” Proc. Nat. Inst. Sciences India, Vol.2, pp. 49-55, 1936.
  9. [9] T. Kanetaka, “An application of Mahalanobis Distance to Diagnosis of Medical Examination,” Quality Engineering Forum, Vol.5, No.2, 1997 (in Japanese).
  10. [10] T. Kohonen, “Self-Organization and Associative Memory,” Springer Series in Information Sciences, Vol.8, 1984.
  11. [11] T. Kohonen, “Self-Organizing Maps,” Springer-Verlag Berlin Heidelberg, 1995.
  12. [12] H. Ritter, E. Oja, and S. Kaski, “Self-Organizing Maps on non-Euclidean Spaces, in Kohonen Maps,” pp. 95-110, Elsevier, New York, 1999.
  13. [13] K. Masuda, D. Nakatsuka, M. Okita, Y. Hukui, K. Hujimura, and H. Tokutaka, “Design of Spherical SOM by Matlab,” Technical Report of IEICE, Vol.104, No.139, pp. 73-77, 2004 (in Japanese).
  14. [14] SOM Japan:
  15. [15] N. Matsuda, H. Tokutaka, J. Laaksonen, F. Tajima, N. Miyatake, and H. Sato, “Spherical SOM and its Application to Fundus Image Analysis,” Biomedical Fussy System Association, Vol.11, No.1, pp. 29-34, 2009 (in Japanese).
  16. [16] H. Tokutaka, T. Kakihara, M. Kurata, K. Fujimura, E. Gonda, Y. Maniwa, M. Yamamoto, L. Shigang, and M. Ohkita, “Construction of the General Physical Condition Judgments System using Acceleration Plethysmogram Pulse-Wave Analysis results,” Biomedical Fussy System Association, Vol.11, No.1, pp. 49-56, 2009 (in Japanese).
  17. [17] H. Hirakawa, “Survival Rates and causes of Death in Various Liver Diseases,” Kanzo, Vol.22, No.6, pp. 848-858, 1981 (in Japanese).

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Dec. 02, 2020