基于LUT的快速3D气道树骨架线提取

发布时间：2018-03-28 17:17

  本文选题：计算机辅助诊断　切入点：气管树　出处：《哈尔滨工业大学学报》2017年05期

【摘要】：为提高肺部支气管骨架线的提取效率,提出并使用一种基于look-up-table(LUT)的腐蚀细化算法.分析建立腐蚀模型,并根据该模型优化建立了LUT,以该LUT为依据通过索引查找对原始数据进行快速腐蚀细化,对得到的腐蚀结果进行剪枝处理以得到最终的骨架线.实验结果表明:提取过程中LUT的应用从根本上降低了腐蚀细化中判断的复杂度,将复杂的简单点判断问题转化为LUT中的查询问题,从而极大地优化了腐蚀细化中关键的腐蚀过程.相比传统方法,基于LUT的腐蚀细化算法显著提高了骨架线的提取速度,较传统细化法提速近22.95倍.
[Abstract]:In order to improve the extraction efficiency of lung bronchus skeleton, a corrosion thinning algorithm based on look-up-tableLUT-based was proposed and established. According to the model, the LUTs are optimized. According to the LUT, the original data can be quickly corroded and refined by index lookup. The experimental results show that the application of LUT in the extraction process can fundamentally reduce the complexity of judgment in corrosion refinement. The complex simple point judgment problem is transformed into a query problem in LUT, which greatly optimizes the critical corrosion process in corrosion thinning. Compared with the traditional method, the LUT based corrosion thinning algorithm improves the extraction speed of skeleton line significantly. The speed of the method is 22.95 times faster than that of the traditional refinement method.
【作者单位】： 上海交通大学生物医学工程学院;
【基金】：国家自然科学基金(61271318)
【分类号】：R56;R734.2;TP301.6
，

本文编号：1677282