Active contours under topology control - Genus preserving level sets
Active contours under topology control - Genus preserving level sets
复制标题
DOI：
10.1007/s11263-007-0102-8
复制
发表时间：
2008-08-01
影响因子：
19.5
通讯作者：
Segonne, Florent
中科院分区：
文献类型：
--
作者：
Segonne, Florent
我们提出了一个新的框架，施加拓扑控制的水平集演化。水平集方法提供了一些优于参数活动轮廓的优点，特别是自动拓扑变化。在一些应用中，在目标拓扑的一些先验知识可用的情况下，拓扑改变可能是不期望的。这通常是生物医学图像分割中的情况，其中目标形状的拓扑由解剖学知识规定。然而，拓扑约束的演化往往会产生拓扑障碍，导致大的几何不一致。我们引入了一个拓扑控制的水平集框架，大大简化了这个问题。与现有的工作不同，我们的方法允许连接的组件合并，分裂或消失在一些特定的条件下，确保初始活动轮廓（即其数量的手柄）的属被保存。我们证明了我们的方法在广泛的数值实验的强度，并说明其性能的皮层表面和血管的分割。
We present a novel framework to exert topology control over a level set evolution. Level set methods offer several advantages over parametric active contours, in particular automated topological changes. In some applications, where some a priori knowledge of the target topology is available, topological changes may not be desirable. This is typically the case in biomedical image segmentation, where the topology of the target shape is prescribed by anatomical knowledge. However, topologically constrained evolutions often generate topological barriers that lead to large geometric inconsistencies. We introduce a topologically controlled level set framework that greatly alleviates this problem. Unlike existing work, our method allows connected components to merge, split or vanish under some specific conditions that ensure that the genus of the initial active contour (i.e. its number of handles) is preserved. We demonstrate the strength of our method on a wide range of numerical experiments and illustrate its performance on the segmentation of cortical surfaces and blood vessels.