Contextual-based Hopfield neural network for medical image edge detection

Detection and outlining of boundaries of organs and tumors in computed tomography (CT) and magnetic resonance imaging (MRI) images are prerequisite in medical applications. A special design Hopfield neural network called the contextual Hopfield neural network (CHNN) is presented for finding the edges of CT and MRI images. Different from the conventional 2-D Hopfield neural networks, the CHNN maps the 2-D Hopfield network at the original image plane. With the direct mapping, the network is capable of incorporating pixels' contextual information into an edge-detecting procedure. As a result, the effect of tiny details and noise will be effectively removed by the CHNN. Furthermore, the problem of satisfying strong constraints can be alleviated and results in a fast converge. Our experimental results show that the CHNN can obtain more appropriate, more continued edge points than Laplacian-based, Marr-Hildreth's, Canny's, wavelet-based, and CHEFNN methods. (c) 2006 Society of Photo-Optical Instrumentation Engineers.