An evolutionary snake algorithm for the segmentation of nuclei in histopathological images

This paper addresses the problem of automatic segmentation of nuclei in histopathological images. A novel method, inspired from active contour models is proposed. An evolutionary based approach, which guarantees convergence to global minimum energies has been used to solve the combinatorial optimization problem of snakes. The computational complexity, often associated with evolutionary approaches, has been reduced by short cutting the natural evolution step by means of replacing standard mutation with an oriented stochastic mutation process. Results have shown the efficiency of this method both in terms of accuracy and fast computation.