A FUZZY HOPFIELD NEURAL-NETWORK FOR MEDICAL IMAGE SEGMENTATION

In this paper, an unsupervised parallel segmentation approach using a fuzzy Hopfield neural network (FHNN) is proposed. The main purpose is to embed fuzzy clustering into neural networks so that on-line learnin g and parallel implementation for medical image segmentation are feasi ble. The idea is to cast a clustering problem as a minimization proble m where the criteria for the optimum segmentation is chosen as the min imization of the Euclidean distance between samples to class centers. In order to generate feasible results, a fuzzy c-means clustering stra tegy is included in the Hopfield neural network to eliminate the need of finding weighting factors in the energy function, which is formulat ed and based on a basic concept commonly used in pattern classificatio n, called the ''within-class scatter matrix'' principle, The suggested fuzzy c-means clustering strategy has also been proven to be converge nt and to allow the network to learn more effectively than the convent ional Hopfield neural network, The fuzzy Hopfield neural network based on the within-class scatter matrix shows the promising results in com parison with the hard c-means method.