计算机应用研究2017，Vol.34Issue(12)：3869-3872,3879,5.DOI:10.3969/j.issn.1001-3695.2017.12.079
基于灰度分布匹配的多模态脑部MR图像肿瘤分割算法
Tumor segmentation on multi-modality brain MR image based on grayscale distribution matching
摘要
Abstract
For the issue that the tumor segmentation on multi-modality brain magnetic resonance (MR) image,this paper proposed a tumor segmentation algorithm based on grayscale distribution matching.Firstly,it used the distribution of non-parametric model of image grayscale intensity to describe the normal region of the current image.Then,it calculated the global similarity between tumor image regions to find the sub-regions whose gray-level distribution was most consistent with the learning model.At the same time,it used a smooth operation to avoid the existence of the isolated region.Finally,it processed the FLAIR modal images to isolate the brain edema regions,and finally to obtain the accurate boundaries of brain tumor regions.Experiments are performed on multi-modality brain tumor image database:BraTS 2012,and the results show that the algorithm can accurately and completely separate the tumor region.关键词
脑肿瘤分割/多模态核磁共振图像/灰度分布匹配/平滑操作Key words
brain tumor segmentation/multi-modality magnetic resonance image/grayscale distribution matching/smoothing operations分类
信息技术与安全科学引用本文复制引用
侯发忠,邹北骥,刘召斌,周支元..基于灰度分布匹配的多模态脑部MR图像肿瘤分割算法[J].计算机应用研究,2017,34(12):3869-3872,3879,5.基金项目
国家自然科学基金资助项目(61173122) （61173122）
湖南省自然科学基金重点项目(12JJ2038) （12JJ2038）
湖南省博士研究生科研创新基金资助项目(CX2013B074) （CX2013B074）
湖南省教育厅科研项目(17C1156) （17C1156）
中南大学研究生自主探索创新项目(2015zzts2121) （2015zzts2121）
湖南医药学院教研项目(2013JG07) （2013JG07）
