Multivariate examination of brain abnormality using both structural and functional MRI

Yong Fan, Hengyi Rao, Hallam Hurt, Joan Giannetta, Marc Korczykowski, David Shera, Brian B. Avants, James C. Gee, Jiongjiong Wang, Dinggang Shen

Research output: Contribution to journalArticle

66 Citations (Scopus)

Abstract

A multivariate classification approach has been presented to examine the brain abnormalities, i.e., due to prenatal cocaine exposure, using both structural and functional brain images. First, a regional statistical feature extraction scheme was adopted to capture discriminative features from voxel-wise morphometric and functional representations of brain images, in order to reduce the dimensionality of the features used for classification, as well as to achieve the robustness to registration error and inter-subject variations. Then, this feature extraction method was used in conjunction with a hybrid feature selection method and a nonlinear support vector machine for the classification of brain abnormalities. This brain classification approach has been applied to detecting the brain abnormality associated with prenatal cocaine exposure in adolescents. A promising classification performance was achieved on a data set of 49 subjects (24 normal and 25 prenatally cocaine-exposed teenagers), with a leave-one-out cross-validation. Experimental results demonstrated the efficacy of our method, as well as the importance of incorporating both structural and functional images for brain classification. Moreover, spatial patterns of group difference derived from the constructed classifier were mostly consistent with the results of the conventional statistical analysis method. Therefore, the proposed approach provided not only a multivariate classification method for detecting brain abnormalities, but also an alternative way for group analysis of multimodality images.

Original languageEnglish
Pages (from-to)1189-1199
Number of pages11
JournalNeuroImage
Volume36
Issue number4
DOIs
Publication statusPublished - 2007 Jul 15
Externally publishedYes

Fingerprint

Magnetic Resonance Imaging
Brain
Cocaine

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Neurology

Cite this

Multivariate examination of brain abnormality using both structural and functional MRI. / Fan, Yong; Rao, Hengyi; Hurt, Hallam; Giannetta, Joan; Korczykowski, Marc; Shera, David; Avants, Brian B.; Gee, James C.; Wang, Jiongjiong; Shen, Dinggang.

In: NeuroImage, Vol. 36, No. 4, 15.07.2007, p. 1189-1199.

Research output: Contribution to journalArticle

Fan, Y, Rao, H, Hurt, H, Giannetta, J, Korczykowski, M, Shera, D, Avants, BB, Gee, JC, Wang, J & Shen, D 2007, 'Multivariate examination of brain abnormality using both structural and functional MRI', NeuroImage, vol. 36, no. 4, pp. 1189-1199. https://doi.org/10.1016/j.neuroimage.2007.04.009
Fan Y, Rao H, Hurt H, Giannetta J, Korczykowski M, Shera D et al. Multivariate examination of brain abnormality using both structural and functional MRI. NeuroImage. 2007 Jul 15;36(4):1189-1199. https://doi.org/10.1016/j.neuroimage.2007.04.009
Fan, Yong ; Rao, Hengyi ; Hurt, Hallam ; Giannetta, Joan ; Korczykowski, Marc ; Shera, David ; Avants, Brian B. ; Gee, James C. ; Wang, Jiongjiong ; Shen, Dinggang. / Multivariate examination of brain abnormality using both structural and functional MRI. In: NeuroImage. 2007 ; Vol. 36, No. 4. pp. 1189-1199.
@article{857af8f5f3a14731b7b9c031f6ea34c7,
title = "Multivariate examination of brain abnormality using both structural and functional MRI",
abstract = "A multivariate classification approach has been presented to examine the brain abnormalities, i.e., due to prenatal cocaine exposure, using both structural and functional brain images. First, a regional statistical feature extraction scheme was adopted to capture discriminative features from voxel-wise morphometric and functional representations of brain images, in order to reduce the dimensionality of the features used for classification, as well as to achieve the robustness to registration error and inter-subject variations. Then, this feature extraction method was used in conjunction with a hybrid feature selection method and a nonlinear support vector machine for the classification of brain abnormalities. This brain classification approach has been applied to detecting the brain abnormality associated with prenatal cocaine exposure in adolescents. A promising classification performance was achieved on a data set of 49 subjects (24 normal and 25 prenatally cocaine-exposed teenagers), with a leave-one-out cross-validation. Experimental results demonstrated the efficacy of our method, as well as the importance of incorporating both structural and functional images for brain classification. Moreover, spatial patterns of group difference derived from the constructed classifier were mostly consistent with the results of the conventional statistical analysis method. Therefore, the proposed approach provided not only a multivariate classification method for detecting brain abnormalities, but also an alternative way for group analysis of multimodality images.",
author = "Yong Fan and Hengyi Rao and Hallam Hurt and Joan Giannetta and Marc Korczykowski and David Shera and Avants, {Brian B.} and Gee, {James C.} and Jiongjiong Wang and Dinggang Shen",
year = "2007",
month = "7",
day = "15",
doi = "10.1016/j.neuroimage.2007.04.009",
language = "English",
volume = "36",
pages = "1189--1199",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",
number = "4",

}

TY - JOUR

T1 - Multivariate examination of brain abnormality using both structural and functional MRI

AU - Fan, Yong

AU - Rao, Hengyi

AU - Hurt, Hallam

AU - Giannetta, Joan

AU - Korczykowski, Marc

AU - Shera, David

AU - Avants, Brian B.

AU - Gee, James C.

AU - Wang, Jiongjiong

AU - Shen, Dinggang

PY - 2007/7/15

Y1 - 2007/7/15

N2 - A multivariate classification approach has been presented to examine the brain abnormalities, i.e., due to prenatal cocaine exposure, using both structural and functional brain images. First, a regional statistical feature extraction scheme was adopted to capture discriminative features from voxel-wise morphometric and functional representations of brain images, in order to reduce the dimensionality of the features used for classification, as well as to achieve the robustness to registration error and inter-subject variations. Then, this feature extraction method was used in conjunction with a hybrid feature selection method and a nonlinear support vector machine for the classification of brain abnormalities. This brain classification approach has been applied to detecting the brain abnormality associated with prenatal cocaine exposure in adolescents. A promising classification performance was achieved on a data set of 49 subjects (24 normal and 25 prenatally cocaine-exposed teenagers), with a leave-one-out cross-validation. Experimental results demonstrated the efficacy of our method, as well as the importance of incorporating both structural and functional images for brain classification. Moreover, spatial patterns of group difference derived from the constructed classifier were mostly consistent with the results of the conventional statistical analysis method. Therefore, the proposed approach provided not only a multivariate classification method for detecting brain abnormalities, but also an alternative way for group analysis of multimodality images.

AB - A multivariate classification approach has been presented to examine the brain abnormalities, i.e., due to prenatal cocaine exposure, using both structural and functional brain images. First, a regional statistical feature extraction scheme was adopted to capture discriminative features from voxel-wise morphometric and functional representations of brain images, in order to reduce the dimensionality of the features used for classification, as well as to achieve the robustness to registration error and inter-subject variations. Then, this feature extraction method was used in conjunction with a hybrid feature selection method and a nonlinear support vector machine for the classification of brain abnormalities. This brain classification approach has been applied to detecting the brain abnormality associated with prenatal cocaine exposure in adolescents. A promising classification performance was achieved on a data set of 49 subjects (24 normal and 25 prenatally cocaine-exposed teenagers), with a leave-one-out cross-validation. Experimental results demonstrated the efficacy of our method, as well as the importance of incorporating both structural and functional images for brain classification. Moreover, spatial patterns of group difference derived from the constructed classifier were mostly consistent with the results of the conventional statistical analysis method. Therefore, the proposed approach provided not only a multivariate classification method for detecting brain abnormalities, but also an alternative way for group analysis of multimodality images.

UR - http://www.scopus.com/inward/record.url?scp=34347251908&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34347251908&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2007.04.009

DO - 10.1016/j.neuroimage.2007.04.009

M3 - Article

C2 - 17512218

AN - SCOPUS:34347251908

VL - 36

SP - 1189

EP - 1199

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

IS - 4

ER -