Application of ICA-R algorithm in resting state fMRI
HU Ya-min1, SUN Bing1, DING Zhao-hua2, CHANG Chun-qi1
1. School of Electronics and Information Engineering, Soochow University, Suzhou Jiangsu 215006, China;2. Vanderbult University Institute of Imaging Science, Tennessee 37232-2310, USA
Abstract：Objective: In order to facilitate the functional magnetic resonance imaging(fMRI) data processing using classical independent component analysis(ICA) method, ICA with reference(ICA-R) algorithm is proposed to reduce the computational load and to increase calculating efficiency. Methods: The signal amplitude information of the default network is introduced to ICA-R algorithm as a reference signal to investigate the orientation of activation in the resting state fMRI data. Results: Experiments with synthetic signals and real fMRI data demonstrate the efficacy and accuracy of the proposed algorithm. Conclusion: ICA-R algorithm could overcome the weakness of inefficiency of classical ICA method.
2014, Vol. 25 
