独立成分分析在视觉运动核磁共振数据处理中的应用  

Application of independent component analysis in visuomotor functional magnetic resonance imaging data processing

作　　者：付令[1] 武杰[1] 

机构地区：[1]上海理工大学医疗器械与食品工程学院,上海200093

出　　处：《中国医学物理学杂志》2017年第7期676-680,共5页Chinese Journal of Medical Physics

基　　金：国家自然科学基金(61101174);上海理工大学微创励志创新基金(YS30809124)

摘　　要：目的:验证独立成分分析(ICA)方法在处理视觉运动核磁共振数据中的有效性。方法:将ICA方法应用于视觉运动任务态的功能磁共振的数据处理。选用Fast ICA算法,根据有效的筛选标准选择最佳的独立成分,并将独立成分与功能模板数据进行比较。结果:选用Fast ICA算法进行数据的ICA处理,并选取成分8与功能数据进行对比。结果显示成分8显示的脑部活跃区域与功能数据较为相符。结论:采用Fast ICA方法所分离出来的独立成分,能够比较准确地显示脑部与运动视觉相关的活跃区域,同时也验证了ICA方法在分离视觉信息处理的背侧通路的有效性。Objective To verify the effectiveness of independent component analysis（ICA） in visuomotor functional magnetic resonance imaging（f MRI） data processing. Methods ICA was applied in the visuomotor f MRI data processing. According to the effective screening criteria, the proper independent components were obtained with Fast ICA algorithm. The obtained independent components were compared with the function template data. Results Fast ICA algorithm was used for the ICA processing of data. Component 8 was selected to compare with the functional data, and the comparison showed that the brain activation areas revealed with component 8 were close to that obtained with functional data. Conclusion Components obtained with Fast ICA method clearly and accurately reveal the brain activation areas related to the visuomotor, which also verifys the effectiveness of ICA in the data processing for dorsal stream.

关 键 词：独立成分分析 视觉运动 功能磁共振成像 成分选取 

分 类 号：R445.2[医药卫生—影像医学与核医学]