基于改进活动轮廓模型的超声图像分割

Ultrasound Image Segmentation Based on Improved Active Contour Model

活动轮廓模型被广泛应用于医学图像分割之中,文中提出了一种改进的快速活动轮廓分割法。原算法在优化过程中容易缩成一点,其初始轮廓必须给定在图像边缘附近,改进的快速活动轮廓算法给出了不同于原算法的内部能量函数,并增加一自适应的约束力,扩大了算法捕捉图像特征的范围。实验结果表明:该算法快,能在更大的范围内捕捉图像特征,是一种有效的分割超声图像的算法。

Active contour model is widely used in medical image segmentation, an improved parametric active contour model is proposed. The original model is easy to be a dot in the optimize process and the initial contour must be set near the edge of the image. The improved fast active contour method by introducing an internal energy function different from before and an automatic external force is added to the target function. The experiment results demonstrate that this algorithm is characterized by its rapidity and capacity which can capture the image feature in a wider region, and is an effective algorithm for segmenting the ultrasound image.