A computer-aided system for classifying computed tomographic (CT) lung images using artificial neural network

In this paper, computed tomographic (CT) images were investigated to develop a computer-aided system to discriminate different lung abnormalities. These were done by analyzing Data recorded for healthy subjects and patients suffering from lung asthma and emphysema diseases were considered. The techniques for utilized feature extraction included statistical, intensity, and morphological features as well as features derived from texture analysis, Fourier-based features and wavelet-based features. An artificial neural network (ANN) classifier was utilized and the results have shown that using wavelet domain features gives the highest rates to recognize lung abnormalities. Classification rate reaches about 98%.