Abstract
A revised Group Method of Data Handling (GMDH)-type neural network algorithm for medical image diagnosis is proposed and is applied to medical image diagnosis of liver cancer that is called hepatocellular carcinoma (HCC). In this algorithm, the knowledge base for medical image diagnosis are used for organizing the neural network architecture for medical image diagnosis and the revised GMDH-type neural network algorithm can identify the characteristics of the medical images accurately. The optimum neural network architecture fitting the complexity of the medical images is automatically organized so as to minimize the prediction error criterion defined as Prediction Sum of Squares (PSS) and it is shown that the revised GMDH-type neural network can be easily applied to the medical image diagnosis.
