0 276

Cited 4 times in

Multivariate detrending of fMRI signal drifts for real-time multiclass pattern classification

Authors
 Dongha Lee  ;  Changwon Jang  ;  Hae-Jeong Park 
Citation
 NEUROIMAGE, Vol.108 : 203-213, 2015 
Journal Title
 NEUROIMAGE 
ISSN
 1053-8119 
Issue Date
2015
MeSH
Adult ; Artifacts* ; Brain/anatomy & histology ; Brain/physiology* ; Brain Mapping/methods* ; Humans ; Magnetic Resonance Imaging/methods* ; Male ; Multivariate Analysis ; Support Vector Machine* ; Young Adult
Keywords
Multi-voxel fMRI classification ; Multi-voxel pattern analysis (MVPA) ; Real-time fMRI ; Support vector machine (SVM) ; Voxel-wise detrending
Abstract
Signal drift in functional magnetic resonance imaging (fMRI) is an unavoidable artifact that limits classification performance in multi-voxel pattern analysis of fMRI. As conventional methods to reduce signal drift, global demeaning or proportional scaling disregards regional variations of drift, whereas voxel-wise univariate detrending is too sensitive to noisy fluctuations. To overcome these drawbacks, we propose a multivariate real-time detrending method for multiclass classification that involves spatial demeaning at each scan and the recursive detrending of drifts in the classifier outputs driven by a multiclass linear support vector machine. Experiments using binary and multiclass data showed that the linear trend estimation of the classifier output drift for each class (a weighted sum of drifts in the class-specific voxels) was more robust against voxel-wise artifacts that lead to inconsistent spatial patterns and the effect of online processing than voxel-wise detrending. The classification performance of the proposed method was significantly better, especially for multiclass data, than that of voxel-wise linear detrending, global demeaning, and classifier output detrending without demeaning. We concluded that the multivariate approach using classifier output detrending of fMRI signals with spatial demeaning preserves spatial patterns, is less sensitive than conventional methods to sample size, and increases classification performance, which is a useful feature for real-time fMRI classification.
Full Text
http://www.sciencedirect.com/science/article/pii/S1053811914010672
DOI
10.1016/j.neuroimage.2014.12.062
Appears in Collections:
1. College of Medicine (의과대학) > BioMedical Science Institute (의생명과학부) > 1. Journal Papers
1. College of Medicine (의과대학) > Dept. of Nuclear Medicine (핵의학교실) > 1. Journal Papers
Yonsei Authors
Park, Hae Jeong(박해정) ORCID logo https://orcid.org/0000-0002-4633-0756
Lee, Dong Ha(이동하)
URI
https://ir.ymlib.yonsei.ac.kr/handle/22282913/139432
사서에게 알리기
  feedback

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse