基于能量活动曲线的肾脏超声图象的边界提取

与CT和MRI等医学图象相比，超声图象由于图象质量较差，相对难以分割，特别地，由于某些器官的边界不是很明显，尤其是肾脏的组织和组织之间的边界难以区分，因此，肾脏超声图象的边界提取对人们来说更富有挑战性。为了解决这一问题，本文提出了一种半自动的肾脏超声图象的边界提取方法。该算法基于能量活动曲线模型，并做了几点重要的改进，同时利用肾脏超声图象的统计模型，比较好地克服了肾脏复杂边界的影响，有效地提出了超声图象的肾脏边界。

Boundary Extraction Based on the Energy-Based Active Contour Model in Kidney Ultrasound Images

Compared with other medical images (e.g. CT and MRI), ultrasound images are particularly difficult to segment as the quality of the images is relatively low. In particular, organ boundaries are not always prominent. Moreover, boundary extraction in kidney ultrasound images is even more challenging as kidney's tissue tissue boundaries are relatively difficult to localize in ultrasound images. To handle this problem, this article describes a novel approach to the semi automatic boundary extraction of kidney ultrasound images. The algorithm developed in this article is based on the energy based active contour model and statistical models of kidney ultrasound images with several important modifications.It can successfully extract the contour, regardless of the heavy structural noise of kidney ultrasound images.