保边滤波和改进FCM的疑似肺结节分割方法  

Suspected lung nodule segmentation method of edge-preserving smoothing and improved FCM

作　　者：香世杰[1] 李彬[1] 田联房[1] 王立非[2] 陈萍[3] 

机构地区：[1]华南理工大学自动化科学与工程学院,广州510640 [2]广州中医药大学祈福医院影像中心,广州511495 [3]广州医学院第一附属医院核医学科,广州510120

出　　处：《计算机工程与应用》2010年第32期202-204,208,共4页Computer Engineering and Applications

基　　金：中国博士后基金(No.20090450866);广东省自然科学基金(No.8451064101000631);广东省教育厅产学研结合项目(No.2009B090300057);教育部博士点基金资助项目(No.200805610018);广州市番禺区科技攻关项目(No.2009-Z-108-1);华南理工大学中央高校基本科研业务费(No.2009ZM0077)~~

摘　　要：提出一种基于保边滤波和改进FCM算法的疑似肺结节自动分割方法。首先,分离出边缘光滑的肺实质并通过非线性各向异性扩散滤波增强肺区疑似病灶,然后运用改进的模糊C-均值聚类算法分割出不同大小的疑似肺结节。实验结果证明,该方法能够自动、准确地完成疑似肺结节分割,比用传统的FCM算法取得更佳效果,并具有良好的鲁棒性和效率。A new automatic segmentation method of suspected lung nodules of edge-preserving smoothing and improved FCM algorithm is proposed.Firstly,the pulmonary parenchyma with smooth edge is separated from the original CT scans and the suspected lesions in the lung area are used by nonlinear anisotropic diffusion filtering for enhancement.Secondly,an improved Fuzzy C-Means（FCM） clustering algorithm is applied to the segmentation of the suspected lung nodules in different sizes.Experiment results indicate that the presented segmentation method of suspected lung nodules can be completed correctly and automatically,which achieves better performance than the conventional FCM algorithm and is much robust and efficient.

关 键 词：计算机辅助检测 肺结节 非线性各向异性扩散 模糊C-均值 医学图像 

分 类 号：R391.4[医药卫生—基础医学] R319