Medical image recognition by using logistic GMDH-type neural networks

In this study, the logistic GMDH-type neural networks are applied to the medical image recognition. This neural network algorithm is based on the conventional GMDH-type neural networks that can automatically organize neural network architecture by using the heuristic self-organization method. In the logistic GMDH-type neural networks, a lot of complex nonlinear combinations of the input variables fitting the complexity of the nonlinear system are generated and only useful combinations of the input variables are selected for organizing the neural network architecture. Therefore, the neural networks organized by the logistic GMDH-type neural networks have good generalization ability even if the characteristic of the nonlinear system is very complex. In this study, the logistic GMDH-type neural networks are applied to the medical image recognition and it is shown that the logistic GMDH-type neural networks are accurate and useful method for the medical image recognition.

[1]  N. Draper,et al.  Applied Regression Analysis , 1966 .

[2]  A. Ivakhnenko.  Heuristic self-organization in problems of engineering cybernetics , 1970 .

[3]  H. Akaike.  A new look at the statistical model identification , 1974 .

[4]  Tadashi Kondo,et al.  GMDH neural network algorithm using the heuristic self-organization method and its application to the pattern identification problem , 1998, Proceedings of the 37th SICE Annual Conference. International Session Papers.

[5]  Jacek M. Zurada,et al.  GMDH-type neural networks and their application to the medical image recognition of the lungs , 1999, SICE '99. Proceedings of the 38th SICE Annual Conference. International Session Papers (IEEE Cat. No.99TH8456).

[6]  Jacek M. Zurada,et al.  Logistic GMDH-type neural networks and their application to the identification of the X-ray film characteristic curve , 1999, IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028).