针对冠状动脉造影图像中血管与背景的对比度低以及背景复杂等问题,提出了一种基于局部复杂度信息测度的冠脉血管分割方法。通过对造影图像过渡区特征的分析,构造了局部复杂度信息测度作为特征参数,提取造影图像的过渡区。根据提取的过渡区直方图确定一个最佳分割阈值,提取冠脉血管。实验结果表明,本文方法在小血管的提取、连通性和有效性方面优于文中其他的血管分割方法,并对辅助医疗诊断及心血管三维重建具有一定价值。
Aiming at the complex background of coronary angiograms and the weak contrast between the coronary arteries and the background,a new segmentation method based on local complexity information measurement is proposed.Firstly,the local complexity information measurement was proposed by analyzing the characteristics of the angiograms transition region.Then the transition region was extracted by local complexity information measurement.Finally,the threshold was obtained by transition region histogram and the coronary arteries were extracted.The experiments indicate that the proposed method has better performance on the small vessels extraction,effectiveness and connectivity.In addition,the method is valuable for diagnosis and 3-D reconstruction of coronary arteries.