作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程

• 开发研究与工程应用 • 上一篇    下一篇

基于凸优化的脑图像数据盲信号分离算法

冯宝1,秦传波2   

  1. (1.桂林航天工业学院自动化系,广西 桂林 541004; 2.华南理工大学自动化科学与工程学院,广州 510640)
  • 收稿日期:2014-08-21 出版日期:2015-08-15 发布日期:2015-08-15
  • 作者简介:冯宝(1986-),男,博士,主研方向:模式识别,脑信号分析;秦传波,博士。
  • 基金资助:
    中央高校基本科研业务费专项基金资助项目(2014ZB0031);广西高校科学技术研究基金资助重点项目(KY2015ZB143);广西高校机器人与焊接技术重点实验室建设基金资助项目;桂林航空工业学院博士启动基金资助项目。

Blind Signal Separation Algorithm of Brain Image Data Based on Convex Optimization

FENG Bao  1,QIN Chuanbo  2   

  1. (1.Department of Automation,Guilin University of Aerospace Technology,Guilin 541004,China; 2.School of Automation Science and Engineering,South China University of Technology,Guangzhou 510640,China)
  • Received:2014-08-21 Online:2015-08-15 Published:2015-08-15

摘要: 在实际脑图像分析中,独立成分分析方法的独立性假设很难完全满足。为此,结合脑图像数据的特点,以凸优化为基础,提出利用源分量稀疏性和非负性的脑图像盲信号分离算法。相比于独立性假设,稀疏性和非负性数学假设更符合fMRI数据的自然特性。将源分量的估计过程 转化为寻找由观测数据构成的凸集合端点的过程。实验结果证明,由该算法选择出的激活体素与实验任务更相关,更容易进行生理解释。

关键词: 盲信号分离, 功能核磁共振成像, 独立成分分析, 凸优化, 体素选择, 脑激活区定位

Abstract: Independent Component Analysis(ICA) is widely used in function Magnetic Resonance Imaging(fMRI) data analysis.However,recent studies show that the independence assumption for ICA based method is sometime violated in practice.In order to overcome this problem,combined with the characteristics of fMRI data,this paper proposes a new blind separation method,which exploits sparsity and non-negativity of sources,for brain image data.Compared with independence assumption,sparsity and non-negativity assumptions are considered more realistic to fMRI data.Based on non-negativity and sparsity assumptions,the new method estimates the source components by finding the extreme points of the observed fMRI data constructed convex set.Numerical results show that voxels selected by the proposed method are more related to task function and easily interpretable.

Key words: Blind Signal Separation(BSS), function Magnetic Resonance Imaging(fMRI), Independent Component Analysis(ICA), convex optimization, voxel selection, brain activation region localization

中图分类号: