首页 | 本学科首页   官方微博 | 高级检索  
     检索      

用于磁共振图像灰度校正的CLIC改进模型
引用本文:赵献策,谢海滨,郑慧,郭天,杨光.用于磁共振图像灰度校正的CLIC改进模型[J].波谱学杂志,2017,34(2):164-174.
作者姓名:赵献策  谢海滨  郑慧  郭天  杨光
作者单位:1. 华东师范大学物理系, 上海市磁共振重点实验室, 上海 200062; 2. 上海卡勒幅磁共振技术有限公司, 上海 201614
基金项目:国家高技术研究发展计划资助项目
摘    要:针对磁共振图像中存在的灰度不均匀问题,该文在灰度校正的连贯局部灰度聚类(coherent local intensityclustering,CLIC)模型的基础上,提出一种新的灰度校正算法.该算法通过引入图像边缘信息来更快寻找到组织边界,在CLIC模型中采用较大的高斯窗函数以保证偏场的光滑性,并结合分裂布雷格曼迭代来加速算法.将改进后的算法用于处理模拟和真实的磁共振图像,实验结果表明,使用该算法能够获得比使用CLIC模型更好的效果.

关 键 词:磁共振成像(MRI)  灰度不均匀  连贯局部灰度聚类(CLIC)  分裂布雷格曼迭代  
收稿时间:2016-04-20

Magnetic Resonance Image Intensity Inhomogeneity Correction Based on Coherent Local Intensity Clustering
ZHAO Xian-ce,XIE Hai-bin,ZHENG Hui,GUO Tian,YANG Guang.Magnetic Resonance Image Intensity Inhomogeneity Correction Based on Coherent Local Intensity Clustering[J].Chinese Journal of Magnetic Resonance,2017,34(2):164-174.
Authors:ZHAO Xian-ce  XIE Hai-bin  ZHENG Hui  GUO Tian  YANG Guang
Institution:1. Shanghai Key Laboratory of Magnetic Resonance, Department of Physics, East China Normal University, Shanghai 200062, China; 2. Shanghai Colorful Magnetic Resonance Technology Co. Ltd., Shanghai 201614, China
Abstract:We proposed a novel method for correcting intensity inhomogeneity in magnetic resonance images based on the coherent local intensity clustering (CLIC) model. The method used edge information to help identify tissue boundaries. A large Gaussian kernel was used to keep the bias field smooth. Split Bregman iteration was used to accelerate convergence. Phantom andin vivo images were used to evaluate the performance of the proposed method.
Keywords:magnetic resonance imaging(MRI)  intensity inhomogeneity  coherent local intensity clustering (CLIC)  split Bregman iteration
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《波谱学杂志》浏览原始摘要信息
点击此处可从《波谱学杂志》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号