ICA-R算法在静息态功能磁共振图像的应用研究

胡亚敏; 孙兵; 丁肇华; 常春起

中国临床医学影像杂志 ›› 2014, Vol. 25 ›› Issue (3) : 153-157.

论著

ICA-R算法在静息态功能磁共振图像的应用研究

胡亚敏1，孙兵1，丁肇华2，常春起1

作者信息 +

Application of ICA-R algorithm in resting state fMRI

HU Ya-min1, SUN Bing1, DING Zhao-hua2, CHANG Chun-qi1

Author information +

文章历史 +

摘要

目的：针对传统独立成分分析（ICA）方法在处理功能磁共振（fMRI）数据时存在计算量大、效率低等问题，提出基于ICA-R算法处理数据。方法：将脑默认网络的幅值信息作为源信号的部分先验知识，以参考信号的形式引入到传统ICA算法提取静息态fMRI（rsfMRI）数据的默认网络。结果：ICA-R算法能够有效提取符合大脑在静息状态时的自发活动特征的脑默认网络。结论：ICA-R算法克服了传统ICA算法以分离所有的源信号为目标造成的效率低等缺点，避免了传统ICA算法中需要后续处理的步骤，提高了算法效率，并且能够准确地提取脑脑默认网络。

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.

导出引用

胡亚敏;孙兵;丁肇华;常春起. ICA-R算法在静息态功能磁共振图像的应用研究[J]. 中国临床医学影像杂志. 2014, 25(3): 153-157

HU Ya-min;SUN Bing;DING Zhao-hua;CHANG Chun-qi. Application of ICA-R algorithm in resting state fMRI[J]. Journal of China Clinic Medical Imaging. 2014, 25(3): 153-157

中图分类号： Ｒ338.2 Ｒ445.2