计算机应用与软件2017，Vol.34Issue(3)：165-169,5.DOI:10.3969/j.issn.1000-386x.2017.03.030
基于自适应区域增长的fMRI脑功能激活区检测
ACTIVE REGION DETECTION OF BRAIN FUNCTION BY FMRI BASED ON SELF-ADAPTIVE REGION GROWING
摘要
Abstract
Region growing has been utilized in the analysis of functional magnetic resonance imaging (fMRI) data for many years, while some influential factors, such as the noise problem, definition of the homogeneity criterion, restricting the application and development in brain function active region detection.In order to overcome these disadvantages, an adaptive region growing method (ARGM) is proposed to detect fMRI brain function active region, where PCA was firstly used to de-noise the fMRI data as a step of preprocessing.Then the region seed was automatically selected by the split-merge method combined with a prior template.Next, an improved homogeneity criterion defined by Canonical correlation coefficient and Pearson correlation coefficient were used to judge the region growing.Compared with the typical fMRI data analysis methods such as ICA and SPM and the classical region growing method, ARGM generates a more accurate and reliable result in task-related experiment.In addition, the resting-state experiment has also demonstrated the effectiveness and usefulness of the proposed method.To conclude, the proposed method is able to broaden the application of region growing in analyzing fMRI data.关键词
区域增长/裂分合并/皮尔森相关系数/典型相关系数/功能磁共振成像Key words
Region growing/Split-merge/Pearson correlation coefficient/Canonical correlation coefficient/Functional magnetic resonance imaging分类
信息技术与安全科学引用本文复制引用
李敏,曾卫明..基于自适应区域增长的fMRI脑功能激活区检测[J].计算机应用与软件,2017,34(3):165-169,5.基金项目
上海科委重点项目(14590501700). （14590501700）
