三维肝脏CT图像中的血管分割

Vascular Segmentation in Three-dimensional CT Images of Livers

为了更好的了解血管生理形态,常需要从医学图像中分割出血管。采用传统的单阈值区域生长算法进行血管分割,如果选取的阈值太高可能导致血管末梢的丢失,而如果选取的阈值太低则可能会导致一些不属于血管的点被生长到血管区域中。因此,提出了一种基于Ordered Region Growing(ORG)算法的双阈值区域生长算法来克服这个缺点,实验证明这种算法能够获得较好的血管分割效果。

In order to understand the vascular physiology better, the blood vessels usually need to be segmented in medical images. When the traditional single-threshold region growth algorithm is used in vascular segmentation, on one hand, it may lead to loss of the peripheral blood vessels if the selected threshold is too high, on the other hand, it may cause some points which do not belong to the blood vessels to be added into the vessel region if the selected threshold is too low. Thus, a dual-threshold region growing algorithm based on ordered region growing （ORG） algorithm is proposed to overcome this drawback, the results show this algorithm can achieve good vascular segmentation.