ISSN 1671-3710
CN 11-4766/R
主办:中国科学院心理研究所
出版:科学出版社

心理科学进展 ›› 2010, Vol. 18 ›› Issue (12): 1934-1941.

• • 上一篇    下一篇

利用脑成像多体素模式分析解码认知的神经表征:原理和应用

雷威;杨志;詹旻野;李红;翁旭初   

  1. (1西南大学心理学院, 重庆 400715) (2中国科学院心理学研究所脑高级功能实验室, 北京 100101)
  • 收稿日期:2010-09-15 修回日期:1900-01-01 出版日期:2010-12-15 发布日期:2010-12-15
  • 通讯作者: 李红

Decoding the Representation of Cognition: the Principles and Applications of MVPA

LEI Wei;YANG Zhi;ZHAN Min-Ye;LI Hong;WENG Xu-Chu   

  1. (1Southwest University, School of Psychology, Chongqing 400715, China)
    (2 Lab for Higher Brain Function, Institute of Psychology, Chinese Academy of Science, Beijing 100101, China)
  • Received:2010-09-15 Revised:1900-01-01 Online:2010-12-15 Published:2010-12-15
  • Contact: LI Hong

摘要: 多体素模式分析(multi-voxel pattern analysis, MVPA)是一种基于机器学习理论发展出来的新的功能磁共振数据分析技术。MVPA技术通过训练分类器, 对由不同认知状态引起的多体素信号模式进行分类。与传统的基于单个体素的分析方法相比, 该技术可更敏感地检测脑对认知状态的表征, 并使得从神经信号解码认知状态成为可能。文章介绍MVPA技术的基本原理、分析步骤以及可以用MVPA来解决的科学问题, 并对应用中可能面临的问题提供了参考建议。

关键词: 多体素模式分析, 表征, 功能磁共振成像, 分类

Abstract: Multi-voxel pattern analysis (MVPA), which is based on machine learning theories, has gained great popularity over the past years as a new approach for fMRI data analysis. By training a classifier, MVPA categorizes multi-voxel patterns tuned by different cognitive states. Compared to conventional voxel-wise methods, this new approach provide higher sensitivity for detecting cognitive representations in the brain. It opens up the possibility for “reading out” mental states of human beings from the non-invasive recordings of brain activities.This paper introduce the fundamental principles of MVPA and the basic realization procedures. Scientific questions that may be properly addressed with this new approach and potential problems in its applications are also discussed.

Key words: MVPA, representation, fMRI, classification