一种基于蚁群算法的Snake模型与MRI分割

AN IMPROVED SNAKE MODEL BASED ON ANT COLONY ALGORITHM AND MRI SEGMENTATION

Snake模型以其收敛快速、精确度可达到亚像素等优点,被广泛地应用于医学图像分割,但该模型依赖于初始曲线的选取,易于收敛到局部最优且难以达到凹陷区域。为此提出一种基于蚁群算法的Snake模型,首先利用区域内灰度统计特征自动进行Snake初始化,然后在Snake演化过程中加入一向心力,使其能进入凹陷区域,最后用蚁群算法对演化结果进行优化,使其收敛到全局最优,获得最终的分割结果。实验结果表明,改进的模型在MR I分割中可以得到较好的分割结果。

Snake model has been widely applied in image segmentation, with the virtues of fast convergence and high accuracy attaining second-pixels. However,the model depends on an initial contour, converges easily to local optimum and is difficult to reach the concave regions. Here, Ant Colony Algorithm（ACA） has been introduced into Snake model. First, gray statistical characteristics are used to automatically initiate Snake. Then, a centripetal energy is added to Snake model in evolving process so as to move into the concave regions. Finally, ACA optimizes the result and make it converge to the whole optimum. The experiment results demonstrate that this algorithm can segment MR images effectively.