基于融合的冠状动脉血管分割方法

Segmentation method of coronary arteries based on fusion algorithm

针对现有冠脉血管分割方法对于小血管和低对比度血管分割效果差的问题,提出了一种基于融合的冠状动脉血管分割方法。首先分别采用形态学的头帽法和高斯滤波法对同一幅血管图像进行增强,得到两幅增强图像;然后采用基于局部熵的过渡区提取的分割方法提取血管,得到两幅含有冠脉血管的图像;最后将两幅图像通过区域连通性的分析进行融合,分割出最终的血管。实验结果表明,新算法在小血管的提取、连通性和有效性方面取得了更好的效果。另外,该方法对辅助医疗诊断具有一定价值。

Aiming at the complex background of coronary angiograms,weak contrast between the coronary arteries and the back-ground,a new segmentation method based on fusion algorithm is proposed.Firstly,the original coronary angiogram is enhanced respectively by using the top-hat method and the Gaussian filter method,then two enhanced images are obtained.Secondly,two extracted coronary arteries images are obtained by using the local entropy threshold method from two enhanced images.Two images of the extracted coronary arteries are fused at last.The experiments indicate that the proposed method outperforms the other methods mentioned in the paper about the small vessels extraction,connectivity and effectiveness.In addition,the method is indeed valuable for diagnosis.