A variant of logistic transfer function in Infomax and a postprocessing procedure for independent component analysis applied to fMRI data

作者：Wu, Xia; Yao, Li^*; Long, Zhi-ying; Chen, Kewei

来源：Magnetic Resonance Imaging, 2007, 25(5): 703-711.

DOI：10.1016/j.mri.2006.09.038

• independent component analysis (ICA)
• functional magnetic resonance imaging (fMRI)
• consistently task-related (CTR) component
• transiently task-related (TTR) component
• time course
• functional localization

Independent component analysis with Infomax algorithm can separate functional magnetic resonance imaging (fMRI) data into independent spatial components (brain activation maps) and their associated time courses. In the current study, we propose a variant of the logistic transfer function in Informax, referred to as a-loistic Infomax, and a postprocessing procedure to combine a consistentl, task-related (CTR) component with transiently task-related (TTR) components for a better definition of brain functional localization. This a-logistic Infomax introduced parameter a into the standard logistic transfer function of conventional Infomax algorithm. For postprocessing method, we suggest the use of a stepwise linear regression of CTR and TTR components to fit reference function and then to sum up with different weights only those with significant contributions to the reference function in order to obtain a task component activation map. The effectiveness of both approaches on separating components and functional localization was evaluated with simulated and real fMRI data.

• 出版日期2007-6
• 单位北京师范大学; 认知神经科学与学习国家重点实验室