数据采集与处理2016，Vol.31Issue(5)：911-918,8.DOI:10.16337/j.1004-9037.2016.05.007
基于Hessian矩阵的冠脉造影图像分割与骨架提取
Coronary Angiography Image Segmentation and Skeleton Extraction Based on Hessian Matrix
摘要
Abstract
Due to incompletely extracted coronary vessels and discontinuous skeleton caused by image blurring and low contrast of coronary angiogram,a multi-scale coronary segmentation and skeleton ex-traction method is proposed based on the Hessian matrix.Vessel radius to be estimated also lays the foundation of three-dimensional reconstruction of coronary structure.By using the relations between Hessian matrix eigenvalues and line items,a novel vesselness measure is constructed and obtain a segmen-ted result enhancing and thresholding coronary are segmented.The normal direction of the coronary vessels is de-termined by the Hessian matrix,and an initial set of coronary skeleton pixels is obtained by extreme points through solving the normal direction.Therefore,Euclidean skeleton of coronary vessels are extracted.The experiment re-sult indicates that the algorithm is concise and effective.Also it can extract more tiny branches comparing with the existing algorithms.It can get a completed coronary skeleton and estimate radius accurately.关键词
冠脉造影图像/Hessian矩阵/对数变换/中轴转换/欧氏骨架Key words
coronary angiography image/Hessian matrix/logarithmic transformation/medial axis trans-form/Euclidean skeleton分类
信息技术与安全科学引用本文复制引用
秦红星,黄晓雪..基于Hessian矩阵的冠脉造影图像分割与骨架提取[J].数据采集与处理,2016,31(5):911-918,8.基金项目
国家自然科学基金青年科学基金(61100113)资助项目 （61100113）
国家教育部留学归国基金教外司留([2012]940)资助项目 （[2012]940）
重庆自然科学基金重点项目(cstc2013jjB40003) （cstc2013jjB40003）
重庆市首批青年骨干教师项目(渝教人[2011]31)资助项目 （渝教人[2011]31）
重庆市基础与前沿研究计划(cstc2013jcyjA400062)资助项目 （cstc2013jcyjA400062）
重庆邮电大学学科引进人才基金(A2010-12)资助项目 （A2010-12）
重庆市研究生科研创新(CYS14142)资助项目。 （CYS14142）
