Medical image recognition by using logistic GMDH-type neural networks

Author

Kondo, Tadashi ; Pandya, Abhijit S.

Author_Institution

Sch. of Med. Sci., Tokushima Univ., Japan

fYear

2001

fDate

2001

Firstpage

259

Lastpage

264

Abstract

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

Keywords

generalisation (artificial intelligence); heuristic programming; identification; image recognition; medical image processing; self-organising feature maps; complex nonlinear combinations; heuristic self-organization method; logistic GMDH-type neural networks; medical image recognition; neural network architecture; nonlinear system complexity; Biomedical imaging; Image recognition; Input variables; Logistics; Neural networks; Neurons; Nonlinear systems; Organizing; Polynomials; Wool;

fLanguage

English

Publisher

ieee

Conference_Titel

SICE 2001. Proceedings of the 40th SICE Annual Conference. International Session Papers

Conference_Location

Nagoya

Print_ISBN

0-7803-7306-5

Type

conf

DOI

10.1109/SICE.2001.977843

Filename

977843