Abstract
An adaptive medical image visualization system based on a hierarchical neural network structure and intelligent decision fusion is presented. The system consists of a feature generator utilizing both histogram and spatial information computed from a medical image, a wavelet transform, a competitive layer neural network, a bi-modal linear estimator and an radial basis functions (RBF) network as well as intelligent decision processes to integrate estimates from both estimators for different subclasses to compute the final display parameters. The large training image set is hierarchically organized for user interaction and re-mapping of the width/center values in the training data.