模糊隶属度加权的KFCM脑MRI的组织分割方法

被引:23
作者
赵海峰 [1 ,2 ]
陈书海 [1 ]
机构
[1] 安徽大学计算机科学与技术学院
[2] 安徽省工业图像处理与分析重点实验室
关键词
基于核函数的模糊C均值聚类; 脑MRI; 图像分割; 核函数;
D O I
暂无
中图分类号
TP391.41 [];
学科分类号
摘要
医学图像受成像机制的影响不可避免地会引入噪声.为解决传统医学图像分割算法对噪声敏感的问题,提出一种模糊隶属度加权的KFCM分割方法.该方法在传统KFCM算法基础上引入局部空间信息,定义了局部隶属度函数,并结合传统KFCM算法得到的全局隶属度函数构造加权隶属度函数,为每个像素计算隶属度值;进一步地,结合邻域信息,使用迭代聚合方法为每个像素重新分配隶属度值.选取Simulated Brain Database数据集,对加入不同噪声的图像进行实验的结果表明,该方法在保证对噪声鲁棒的同时,能够提高分割精度.
引用
收藏
页码:2055 / 2062
页数:8
相关论文
共 12 条
[1]
基于模糊聚类算法的医学图像分割技术研究 [D]. 
张小峰 .
山东大学,
2014
[2]
A deep learning model integrating FCNNs and CRFs for brain tumor segmentation[J] Xiaomei Zhao;Yihong Wu;Guidong Song;Zhenye Li;Yazhuo Zhang;Yong Fan Medical Image Analysis 2018,
[3]
Deep Learning for Brain MRI Segmentation: State of the Art and Future Directions[J] Zeynettin Akkus;Alfiia Galimzianova;Assaf Hoogi;Daniel L. Rubin;Bradley J. Erickson Journal of Digital Imaging 2017,
[4]
A local fuzzy thresholding methodology for multiregion image segmentation[J] Santiago Aja-Fernández;Ariel Hernán Curiale;Gonzalo Vegas-Sánchez-Ferrero Knowledge-Based Systems 2015,
[5]
Segmentation of Brain Tissues from Magnetic Resonance Images Using Adaptively Regularized Kernel-Based Fuzzy C-Means Clustering[J] Ahmed Elazab;Changmiao Wang;Fucang Jia;Jianhuang Wu;Guanglin Li;Qingmao Hu Computational and Mathematical Methods in Medicine 2015,
[6]
Multiplicative intrinsic component optimization (MICO) for MRI bias field estimation and tissue segmentation[J] Chunming Li;John C. Gore;Christos Davatzikos Magnetic Resonance Imaging 2014,
[7]
A robust fuzzy local information C-Means clustering algorithm.[J] Krinidis Stelios;Chatzis Vassilios IEEE transactions on image processing : a publication of the IEEE Signal Processing Society 2010,
[8]
A review of methods for correction of intensity inhomogeneity in MRI.[J] Vovk Uros;Pernus Franjo;Likar Bostjan IEEE transactions on medical imaging 2007,
[9]
Fuzzy c-means clustering with spatial information for image segmentation[J] Keh-Shih Chuang;Hong-Long Tzeng;Sharon Chen;Jay Wu;Tzong-Jer Chen Computerized Medical Imaging and Graphics 2005,
[10]
A modified fuzzy C-means algorithm for bias field estimation and segmentation of MRI data.[J] Ahmed Mohamed N;Yamany Sameh M;Mohamed Nevin;Farag Aly A;Moriarty Thomas IEEE transactions on medical imaging 2002,