一种使用膨胀气球模型的Snakes多目标分割方法  

A multi-object segmentation algorithm for snakes using inflating balloon model

作　　者：吕红宇[1] 马竞峰[2] 包尚联[1] 

机构地区：[1]北京大学医学物理和工程北京市重点实验室,北京100871 [2]浙江大学计算机科学与技术学院,浙江杭州310027

出　　处：《中国医学影像技术》2006年第3期458-460,共3页Chinese Journal of Medical Imaging Technology

基　　金：国家自然科学基金(10275003);北京市共建项目(SYS100010401);教育部重点项目(104237)资助。

摘　　要：目的为实现一种有效的基于Snakes的多目标医学图像分割算法。方法通过模拟气球在含多个物体的封闭空间内的膨胀,来实现Snake曲线的拓扑形变。算法使用一个燃烧区域滞后跟踪Snake曲线运动来给出其演化停止条件,然后忽略停止条件并继续演化Snake曲线,就能完成燃烧而得到一个连通区域。提取出已燃烧区域的轮廓可给出与各分割目标对应的子Snake。结果所提出的算法能够正确分割出医学图像中多目标对象的轮廓。结论此基于模型的分割算法原理明确且易于实现,具有较好的实用性。Objective To develop an effective scheme for using Snakes or parametric active contours to identify the multiobjects in medical image. Methods The approach simulates the balloon inflating in a close space containing multi-objects to realize the topological change of the snake. A burning area is utilized to trace the snake curve while the fire front keeps a small distance to the snake contour. Its function is to give the stopping criteria for the snake. Then omitting the stopping criteria, it can form a connected region by evolving the snake and continuing burning. The contours extracted from the burned region represent the child snake of each object respectively. Results The proposed methods can outline the boundaries of the multi-objects of medical image correctly. Conclusion The principle of the approach is explicit because its techniques are model based. The algorithm can be implemented easily and is effective for practical applications.

关 键 词：图像分割 蛇模型 多目标 拓扑形变 区域增长 

分 类 号：R445.1[医药卫生—影像医学与核医学] R312[医药卫生—诊断学]