Diagnosis of brain abnormality using both structural and functional MR images.

Yong Fan, Hengyi Rao, Joan Giannetta, Hallam Hurt, Jiongjiong Wang, Christos Davatzikos, Dinggang Shen

Research output: Contribution to journalArticle

Abstract

A number of neurological diseases are associated with structural and functional alterations in the brain. This paper presents a method of using both structural and functional MR images for brain disease diagnosis, by machine learning and high-dimensional template warping. First, a high-dimensional template warping technique is used to compute morphological and functional representations for each individual brain in a template space, within a mass preserving framework. Then, statistical regional features are extracted to reduce the dimensionality of morphological and functional representations, as well as to achieve the robustness to registration errors and inter-subject variations. Finally, the most discriminative regional features are selected by a hybrid feature selection method for brain classification, using a nonlinear support vector machine. The proposed method has been applied to classifying the brain images of prenatally cocaine-exposed young adults from those of socioeconomically matched controls, resulting in 91.8% correct classification rate using a leave-one-out cross-validation. Comparison results show the effectiveness of our method and also the importance of simultaneously using both structural and functional images for brain classification.

Original languageEnglish
Pages (from-to)1044-1047
Number of pages4
JournalConference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference
Publication statusPublished - 2006 Dec 1
Externally publishedYes

Fingerprint

Brain
Brain Diseases
Cocaine
Young Adult
Support vector machines
Learning systems
Feature extraction

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Biomedical Engineering
  • Health Informatics

Cite this

@article{3052a108af2949ef992d0375830923f7,
title = "Diagnosis of brain abnormality using both structural and functional MR images.",
abstract = "A number of neurological diseases are associated with structural and functional alterations in the brain. This paper presents a method of using both structural and functional MR images for brain disease diagnosis, by machine learning and high-dimensional template warping. First, a high-dimensional template warping technique is used to compute morphological and functional representations for each individual brain in a template space, within a mass preserving framework. Then, statistical regional features are extracted to reduce the dimensionality of morphological and functional representations, as well as to achieve the robustness to registration errors and inter-subject variations. Finally, the most discriminative regional features are selected by a hybrid feature selection method for brain classification, using a nonlinear support vector machine. The proposed method has been applied to classifying the brain images of prenatally cocaine-exposed young adults from those of socioeconomically matched controls, resulting in 91.8{\%} correct classification rate using a leave-one-out cross-validation. Comparison results show the effectiveness of our method and also the importance of simultaneously using both structural and functional images for brain classification.",
author = "Yong Fan and Hengyi Rao and Joan Giannetta and Hallam Hurt and Jiongjiong Wang and Christos Davatzikos and Dinggang Shen",
year = "2006",
month = "12",
day = "1",
language = "English",
pages = "1044--1047",
journal = "The BMJ",
issn = "0730-6512",
publisher = "Kluwer Academic Publishers",

}

TY - JOUR

T1 - Diagnosis of brain abnormality using both structural and functional MR images.

AU - Fan, Yong

AU - Rao, Hengyi

AU - Giannetta, Joan

AU - Hurt, Hallam

AU - Wang, Jiongjiong

AU - Davatzikos, Christos

AU - Shen, Dinggang

PY - 2006/12/1

Y1 - 2006/12/1

N2 - A number of neurological diseases are associated with structural and functional alterations in the brain. This paper presents a method of using both structural and functional MR images for brain disease diagnosis, by machine learning and high-dimensional template warping. First, a high-dimensional template warping technique is used to compute morphological and functional representations for each individual brain in a template space, within a mass preserving framework. Then, statistical regional features are extracted to reduce the dimensionality of morphological and functional representations, as well as to achieve the robustness to registration errors and inter-subject variations. Finally, the most discriminative regional features are selected by a hybrid feature selection method for brain classification, using a nonlinear support vector machine. The proposed method has been applied to classifying the brain images of prenatally cocaine-exposed young adults from those of socioeconomically matched controls, resulting in 91.8% correct classification rate using a leave-one-out cross-validation. Comparison results show the effectiveness of our method and also the importance of simultaneously using both structural and functional images for brain classification.

AB - A number of neurological diseases are associated with structural and functional alterations in the brain. This paper presents a method of using both structural and functional MR images for brain disease diagnosis, by machine learning and high-dimensional template warping. First, a high-dimensional template warping technique is used to compute morphological and functional representations for each individual brain in a template space, within a mass preserving framework. Then, statistical regional features are extracted to reduce the dimensionality of morphological and functional representations, as well as to achieve the robustness to registration errors and inter-subject variations. Finally, the most discriminative regional features are selected by a hybrid feature selection method for brain classification, using a nonlinear support vector machine. The proposed method has been applied to classifying the brain images of prenatally cocaine-exposed young adults from those of socioeconomically matched controls, resulting in 91.8% correct classification rate using a leave-one-out cross-validation. Comparison results show the effectiveness of our method and also the importance of simultaneously using both structural and functional images for brain classification.

UR - http://www.scopus.com/inward/record.url?scp=84903861278&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903861278&partnerID=8YFLogxK

M3 - Article

C2 - 17946017

SP - 1044

EP - 1047

JO - The BMJ

JF - The BMJ

SN - 0730-6512

ER -