single-jc.php

JACIII Vol.15 No.6 pp. 714-722
doi: 10.20965/jaciii.2011.p0714
(2011)

Paper:

Medical Image Diagnosis of Liver Cancer Using a Neural Network and Artificial Intelligence

Tadashi Kondo, Junji Ueno, and Shoichiro Takao

Graduate School of Health Sciences, The University of Tokushima, 3-18-15 Kuramoto-cho, Tokushima 770-8509, Japan

Received:
December 27, 2010
Accepted:
May 11, 2011
Published:
August 20, 2011
Keywords:
GMDH-type neural network, medical image diagnosis, artificial intelligence, CAD, PSS
Abstract

A revised Group Method of Data Handling (GMDH)-type neural network algorithm using artificial intelligence technology for medical image diagnosis is proposed and is applied to medical image diagnosis of liver cancer. In this algorithm, the knowledge base for medical image diagnosis is used in organizing the neural network architecture for medical image diagnosis. Furthermore, the revisedGMDH-type neural network algorithm has a feedback loop and can identify the characteristics of the medical images accurately using feedback loop calculations. The neural network architecture that optimally fit the complexity of the medical images, is automatically organized so as to minimize the prediction error criterion defined as Prediction Sum of Squares (PSS). It is shown that the revised GMDH-type neural network is accurate and a useful method for the medical image diagnosis of the liver cancer.

Cite this article as:
T. Kondo, J. Ueno, and S. Takao, “Medical Image Diagnosis of Liver Cancer Using a Neural Network and Artificial Intelligence,” J. Adv. Comput. Intell. Intell. Inform., Vol.15, No.6, pp. 714-722, 2011.
Data files:
References
  1. [1] T. Kondo and J. Ueno, “Medical image recognition of abdominal multi-organs by RBF GMDH-type neural network,” Int. J. of Innovative Computing, Information and Control, Vo.5, No.1, pp. 225-240, 2009.
  2. [2] T. Kondo and J. Ueno, “Multi-layered GMDH-type neural network self-selecting optimum neural network architecture and its application to 3-dimensional medical image recognition of blood vessels,” Int. J. of Innovative Computing, Information and Control, Vo.4, No.1, pp. 175-187, 2008.
  3. [3] C. Kondo, T. Kondo, and J. Ueno, “Three-dimensional medical image analysis of the heart by the revised GMFH-type neural network self-selecting optimum neural network architecture,” Artificial Life and Robotics, Vol.14, No.2, pp. 123-128, 2009.
  4. [4] T. Kondo and J. Ueno, “Logistic GMDH-type neural network and its application to identification of X-ray film characteristic curve,” J. of Advanced Computational Intelligence and Intelligent Informatics, Vol.11, No.3, pp. 312-318, 2007.
  5. [5] T. Kondo, “GMDH neural network algorithm using the heuristic self-organization method and its application to the pattern identification problem,” Proc. of the 37th SICE Annual Conf., pp. 1143-1148, 1998.
  6. [6] H. Tamura and T. Kondo, “Heuristics free group method of data handling algorithm of generating optimum partial polynomials with application to air pollution prediction,” Int. J. of System Sciences, Vol.11, No.9, pp. 1095-1111, 1980.
  7. [7] S. J. Farlow (Ed.), “Self-organizing methods in modeling, GMDHtype algorithm,” Marcel Dekker, Inc., New York, 1984.
  8. [8] A. G. Ivakhnenko, “Heuristic self-organization in problems of engineering cybernetics,” Automatica, Vol.6, No.2, pp. 207-219, 1970.
  9. [9] N. R. Draper and H. Smith, “Applied Regression Analysis,” John Wiley and Sons, New York, 1981.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, IE9,10,11, Opera.

Last updated on Jan. 18, 2019