Medical Image Diagnosis of Liver Cancer by Revised GMDH-type Neural Network Using Feedback Loop Calculation

摘要

Revised Group Method of Data Handling (GMDH)-type neural network algorithm using feedback loop calculation is applied to the medical image diagnosis of liver cancer. in this revised GMDH-type neural network algorithm, the complexity of the neural network architectures is increased gradually through the feedback loop calculation and the optimum neural network architecture is organized so as to fit the complexity of the medical images using the prediction error criterion defined as Akaike's Information Criterion (AIC) or Prediction Sum of Squares (PSS). in this study, two kinds of GMDH-type neural networks which can recognize the liver regions and the liver cancer regions, are organized and the recognition results are compared with the conventional sigmoid function neural network trained using the back propagation method.