Feedback GMDH-Type Neural Network Self-Sеlecting Optimum Neural Network Architecture and Its Application to 3-Dimensional Medical Image Recognition of the Lungs. Tadashi Kondo, Junji Ueno. IWIM, Prague, 2007.
Article (in pdf)
Abstract. The feedback Group Method of Data Handling (GMDH)-type neural network algorithm is proposed and is applied to 3-dimensional medical image recognition of the lungs, the pulmonary vessels and the bronchial trees. In this feedback GMDH-type neural network algorithm, the optimum neural network architecture is automatically selected from three types of neural network architectures such as the sigmoid function type neural network, the radial basis function (RBF) type neural network and the polynomial type neural network. Furthermore, the structural parameters such as the number of layers, the number of neurons in the hidden layers and the relevant input variables are automatically selected so as to minimize the prediction error criterion defined as Prediction Sum of Squares (PSS). The recognition results show that the feedback GMDH-type neural network algorithm is useful for the 3-dimensional medical image recognition of the lungs, the pulmonary vessels and the bronchial trees and is ideal for such practical complex problems since the optimum neural network architecture is automatically organized.
Keywords. GMDH, Neural network, Medical image recognition
References.
- Kondo T.: GMDH neural network algorithm using the heuristic self-organization method and its application to the pattern identification problem, Proc. of the 37th SICE Annual Conference, p.1143-1148, 1998.
- Kondo T.: Revised GMDH-type neural networks using prediction error criterions AIC and PSS, Proc. of SCIS & ISIS 2004, WP-6-4, p.1-6, 2004.
- Farlow S.J.ed.: Self-organizing methods in modeling, GMDH-type algorithm, Marcel Dekker, Inc., New York, 1984.
- Ivakhnenko A.G.: Heuristic self-organization in problems of engineering cybernetics, Automatica, Vo.6, No.2, p.207-219, 1970.
- Akaike H., A new look at the statistical model identification, IEEE Trans. Automatic Control, Vol.AC-19, No.6, p.716-723, 1974.
- Tamura H., Kondo T.: Heuristics free group method of data handling algorithm of generating optimum partial polynomials with application to air pollution prediction, Int. J. System Sci., Vol.11, No.9, p.1095-1111, 1980.
- Draper N.R , Smith H.: Applied Regression Analysis, John Wiley and Sons, New York, 1981.
