小血管医学图像的增强与实时提取

利用一种新的非线性各向异性反应扩散血管图像增强方法,对小血管图像增强后,再采用快速推进算法及融合区域信息的速度函数对小血管自动提取.该方法能够有效地增强血管的一致性取向结构及血管与背景之间的边界,并能很好地滤除噪声.借助高效的快速推进方法求解曲线进化方程,为提高算法的实时性,在数值求解中同时采用多初始化策略.实验结果表明,利用该方法可以实时地提取6~7级肺部小血管分枝.

Enhancement and Real Time Extraction Algorithm for Thin Vessel Images

A new approach named anisotropic reaction diffusion to vessels images enhancement is proposed and then an efficient approach to thin vessels extraction based on the curve evolution is adopted. The proposed approach facilitates enhancing the directional structure of vessels and strengthening the edge while noise is removed in this way. The curve evolution can not only drive the curve propagation in the low contrast and thin vessel branches without the earlier boundary leaking, but also guarantee the curve marching monotonically, and the curve evolution equation can be solved with fast marching algorithm. Simultaneously, the multi-initial scheme is adopted for improving real time implementation. The experiments show that thin pulmonary vessels at six to seven level can be extracted fast and accurately.