论文部分内容阅读
为辅助医生临床诊断,提出了一种冠状动脉血管树的提取方法。提取方法包含基于形态学的冠状动脉路径线提取;基于圆模板的冠状动脉段的区域划分;基于动态规划方法的冠状动脉树边缘提取。该方法可以在无人工干预的情况下自动获取完整、单连通和单像素的冠脉树边缘。实验结果表明,与已有的获取冠状动脉树边缘方法相比较,该方法有很好的准确性。
To assist clinicians in clinical diagnosis, a method of extracting coronary blood vessel tree was proposed. Extraction methods include morphological extraction of coronary artery pathways; segmentation of coronary artery segments based on circular templates; and extraction of coronary artery tree edges based on dynamic programming. This method automatically obtains complete, single-connected and single-pixel coronary tree edges without human intervention. The experimental results show that this method has a good accuracy compared with the existing method of obtaining the edge of the coronary artery tree.