Active contour driven by local divergence energies for ultrasound image segmentation

Abstract

In this study, a new local region-based active contour model in a variational level set formulation for ultrasound image segmentation is proposed. The energy function is formulated based on the local divergence with likelihood ratio. The proposed model can handle blurry boundaries and noise problems. In addition, the regularity of the level set function is intrinsically preserved by the level set regularisation term to ensure accurate computation. The authors only adopt a level set function to define the partition of image domain into two disjoined regions. Experimental results demonstrate desirable performance of the authors’ method for synthetic images with different level noise and ultrasound images with weak boundaries and noise.