基于水平集方法的冠状动脉分割的分析-光学工程专业论文.docxVIP

摘 要 现今，冠心病因其高发病率、高致亡率等特征，业已成为威胁人类健康的常 见病。X 射线冠状动脉造影 (coronary angiography，CAG)和多层螺旋 CT(multislice computed tomography，MSCT)技术在诊断冠心病中扮演着关键角色。其中 MSCT 技术以其各向同性扫描、无创成像以及较高的时空分辨率等多项优势，被广泛应 用于冠状动脉类疾病的分析与诊断治疗中，并取得了很好的诊治效果。本文针对 冠心病诊断中冠状动脉信息难获取的问题，基于充分的文献整理及调研分析，提 出一种基于水平集方法的图像分割模型，旨在获取更高的分割精度。 水平集方法自引入到图像分割领域中以来，凭借其分割精度高、拓扑适应性 好等优势，应用范围愈发广泛。本文采用水平集方法中应用广泛的 Chan-Vese 模 型进行多层螺旋 CT 图像处理。针对该模型不能分割灰度不均匀的图像和对初始 轮廓的选取有依赖性的问题，研究了融合模糊聚类的改进图像分割模型，用模糊 聚类获得的聚类信息指导 Chan-Vese 模型的初始轮廓选取。首先，针对心脏 CT 数据进行模糊 C 均值聚类的预处理，提取聚类信息和隶属度矩阵；其次应用聚 类信息指导水平集方法初始轮廓的选取，用 Chan-Vese 模型进行冠状动脉的提取， 完成冠状动脉分割。之后应用医学图像三维重建算法，分别采用面绘制和体绘制 的方法对获取的二维冠状动脉信息进行三维重建，重建完整的三维冠状动脉，为 医生提供真实的感官效果，研究结果用于辅助诊断冠心病。 关键词：图像处理；冠状动脉血管分割；水平集方法；Chan-Vese 模型；模糊 C 均值聚类；三维重建 ABSTRACT Because of high incidence, high death rate and other characteristics, coronary artery disease has been a common disease which is a threat to human health these years. X-ray coronary angiography technology (CAG) and multislice computed tomography technology (MSCT) play a key role in the diagnosis of coronary artery disease. Because of its isotropic scanning, non-invasive imaging, high spatial and temporal resolution and other advantages, the multislice computed tomography technology is widely used in coronary artery disease analysis and diagnosis, and achieves good effect. In this article, in order to obtain higher accuracy of segmentation, basing on sufficient data compilation and research on desk, we use image segmentation model based on level set method to solve the difficulty of accessing coronary artery information. Taking into account the division of high precision and topology adaptability advantages, the level set method has obtained wide range of applications after it has been introduced into the field of image segmentation. Level set method is a kind of model-based segmentation methods in image segmentation in recent years. In this paper, we use Chan-Vese model for image processing as its high precision and topology and good adaptability. For the mode