CT Image Segmentation by using a FHNN Algorithm Based on Genetic Approach

Traditional fuzzy Hopfield neural network (FHNN) is one of the excellent segmentation methods for CT image. Although FHNN has the capacity of searching values with high precision, it has obvious disadvantages, such as local minimum and slow convergence. In order to make up these shortcomings and find the right global minimum, a FHNN Algorithm based on genetic approach is proposed. Fine segmentation results have been obtained by the innovatory algorithm. Compared with corresponding segmentation results by means of the traditional FHNN method only, the experimental results of the innovative algorithm are better in CT image segmentation. The latter can segment the image more clearly, continuously, smoothly and has better capability in noise immunity. So the proposed approach possesses an important significance on computer aided diagnosis based on medical images segmentation.