An Automatic Image Segmentation Model Integrating Fuzzy Clustering with Level Set Method

Abstract

Automatic segmentation for medical images is a fundamental task for scientific research and clinical application. Most reports focus on the active contour model or fuzzy clustering method independently, while integrating two methods properly may play an unexpected better results. A new method is proposed in this paper, which integrates fuzzy clustering with level set method through an additional term in our new energy functional. It is able to use the results of fuzzy clustering directly, which can control the level set evolution automatically. Such algorithm eliminates the manual operation and leads to more robust segmentation results. With the split Bregman method, the minimization of the energy functional is fast. The proposed algorithm was tested on some medical images. Experimental results show its effectiveness for medical image segmentation.