Computerized tumour boundary detection using a Hopfield neural network
Yan Zhu, Hong Yan · 2002
We present a new approach for detection of the brain tumour boundaries in medical images using a Hopfield network. The boundary detection problem is formulated as an optimization process that seeks the boundary points to minimize an energy functional based on the active contour model. A modified Hopfield network is constructed to solve the optimization problem. Taking advantage of the collective computational ability and energy convergence capability of the Hopfield network, results from the proposed method are comparable to those of standard snakes based algorithms, but with less computation time. Experiments on several magnetic resonance brain images show the effectiveness of our approach.