In-vivo ultrasound liver differentiation using artificial neural network

The authors present a pattern recognition algorithm and describe required instrumentation for in-vivo ultrasound human liver differentiation. A 50-MHz microprocessor-based data acquisition and analysis system is designed and constructed to capture, digitize and store the ultrasound backscattered signal. The algorithm is based on a multilayer perceptron neural network using the backpropagation training procedure. The network is implemented to differentiate between normal and abnormal liver. The acoustic attenuation coefficient is calculated using the log spectral difference technique over the frequency range from 1.5 to 4.5 MHz. The change of speed of sound with frequency (dispersion) is estimated over the 3 MHz bandwidth. The attenuation and velocity dispersion are used as differentiation features. The results show that out of 30 cases, the system differentiated correctly 27 and 28 using the attenuation and the velocity dispersion, respectively