A PC-based simulated-liver tissue classification using artificial neural net classifier

Summary form only given, as follows. An algorithm and instrumentation for classifying liver tissue abnormalities have been developed. The instrumentation used is a 50 MHz microcomputer-based data acquisition and analysis system. The primary functions of the system are to digitize the backscattered ultrasound signal from a human liver tissue phantom; process these digitized data in the frequency domain; and apply pattern recognition algorithms to classify the abnormalities of simulated liver tissues. The pattern recognition algorithm is based on a three-layer backpropagation artificial neural network. The results show that the algorithm is working satisfactorily for classifying simulated normal liver tissue and three types of simulated abnormalities