Abstract

Although some computer-assisted diagnostic systems have been reported recently, they have not been so much spread in clinical field yet. The principles of fuzzy or neural network are so complicated to the general clinicians and they do not have the skills or techniques, which are necessary to develop the computer-assisted diagnostic system. The authors herein propose the new method, which automatically optimize the system only by setting the simple inferences. Because the method can be utilized with an ordinary application on a standard personal computer, even the users who cannot make programs can develop the system. The method applies the adaptive neuro-fuzzy inference system (ANFIS), which is combined with fuzzy and neural network. In this method, membership functions, which are set temporally at first, can be optimized automatically by back propagation procedure of neural network. Consequently, the performance of the diagnostic system can be improved. The authors describes the outline of the method with the preliminary applied case to the ultrasonographic dignosis.