光学相干断层成像技术（OCT）现已发展成为国内外较热门的冠状动脉内影像技术，其中冠脉 OCT 图像的斑块区域分割对易损斑块的识别和研究有着重大意义。本文提出了一种基于 K-means 聚类与改进随机游走的新算法，实现了对冠脉钙化、纤维化斑块和脂质池的半自动化分割。本文主要创新点为改进了随机游走算法的权函数，将图像中像素间的边与种子点之间的距离加入到了权函数定义中，增加了弱边界的权值，防止了过分割现象的发生。本文基于以上方法对 9 名冠状动脉粥样硬化患者的 OCT 图像进行了斑块区域分割。通过对比医生手动分割结果，证明了本文方法具有良好的精度和鲁棒性，以期本文方法可对冠心病的临床诊断起到一定的辅助作用
References
[1]
1. 杜伟. OCT 技术诊断冠脉易损斑块破裂的临床效果分析. 当代医学, 2017, 23(3): 112-113.
[2]
2. 严金川, 梁仪, 陈小节, 等. OCT 技术诊断冠脉易损斑块破裂1例. 临床心血管病杂志, 2015(8): 915-917.
4. Wang Z, Hiroyuki K, Hiram G B, et al. Semiautomatic segmentation and quantification of calcified plaques in intracoronary optical coherence tomography images. J Biomed Opt, 2010, 15(6): 061711.
[5]
5. Athanasiou L S, Bourantas C, Rigas G, et al. Methodology for fully automated segmentation and plaque characterization in intracoronary optical coherence tomography images. J Biomed Opt, 2014, 19(2): 026009.
[6]
6. Prakash A, Hewko M D, Sowa M, et al. Detection of atherosclerotic plaque from optical coherence tomography images using texture-based segmentation. Sovremennye Tehnologii, 2015, 7(1): 21-28.
[7]
7. Prakash A, Hewko M, Sowa M, et al. Texture based segmentation method to detect atherosclerotic plaque from optical tomography images//Optical Coherence Tomography and Coherence Techniques VI, 2013, 8802: 448-453.
[8]
8. Celi S, Berti S. In-vivo segmentation and quantification of coronary lesions by optical coherence tomography images for a lesion type definition and stenosis grading. Med Image Anal, 2014, 18(7): 1157-1168.
[9]
9. Athanasiou L S, Bourantas C, Rigas G, et al. Fully automated calcium detection using opticalcoherence tomography//International Conference of the IEEE Engineering in Medicine & Biology Society, Osaka, Japan: 2013: 1430-1433.
11. Rezaei Z, Selamat A, Taki A, et al. Automatic plaque segmentation based on hybird fuzzy clustering and k nearest neighborhood using virtual histology instravascularulsrasound images. Applied Soft Computting, 2017, 53: 380-395.
[12]
12. Sarkar J P, Saha I, Maulik U. Rough possibilistic type-2 fuzzy C-Means clustering for MR brain image segmentation. Appl Soft Comput, 2016, 46: 527-536.
