Pulse coupled neural network (PCNN) is a new neural network that is widely used in image segmentation. Parameters play an important role on the performance of PCNN. However, parameters of PCNN are always obtained by trial and error, so that it's difficult to get satisfying effects which limits its application. In this paper, a novel image segmentation method based on spiral optimization and PCNN is proposed to set the parameters automatically. The new method can shorten the running time by spiral optimization which is a heuristic algorithm. Comparing with other methods, it shows higher segmentation performance which illustrates the effectiveness of the approach.