A Multiphase Entropy-Based Level Set Algorithm for MR Breast Image Segmentation Using Lattice Boltzmann Model

摘要

Recently, with the development of high dimensional large-scale medical imaging devices, the need of fast and accurate segmentation methods is increasing. In this paper, we propose a new variational multiphase level set approach to medical image segmentation. We first design an entropy-based energy functional, from which we derive the multiphase level set equations and a new entropic external forces for the lattice Boltzmann D2Q9 model. The method is accurate and highly parallelizable. The local nature of the LBM allows it to be suitable for fast segmentation methods implemented using some parallel devices such as the graphics processing unit. Experimental results on MR breast images demonstrate the effectiveness of the proposed method.