Morphological classification of brains via high-dimensional shape transformations and machine learning methods

Zhiqiang Lao, Dinggang Shen, Zhong Xue, Bilge Karacali, Susan M. Resnick, Christos Davatzikos

Research output: Contribution to journalArticle

Abstract

A high-dimensional shape transformation posed in a mass-preserving framework is used as a morphological signature of a brain image. Population differences with complex spatial patterns are then determined by applying a nonlinear support vector machine (SVM) pattern classification method to the morphological signatures. Significant reduction of the dimensionality of the morphological signatures is achieved via wavelet decomposition and feature reduction methods. Applying the method to MR images with simulated atrophy shows that the method can correctly detect subtle and spatially complex atrophy, even when the simulated atrophy represents only a 5% variation from the original image. Applying this method to actual MR images shows that brains can be correctly determined to be male or female with a successful classification rate of 97%, using the leave-one-out method. This proposed method also shows a high classification rate for old adults' age classification, even under difficult test scenarios. The main characteristic of the proposed methodology is that, by applying multivariate pattern classification methods, it can detect subtle and spatially complex patterns of morphological group differences which are often not detectable by voxel-based morphometric methods, because these methods analyze morphological measurements voxel-by-voxel and do not consider the entirety of the data simultaneously.

Original languageEnglish (US)
Pages (from-to)46-57
Number of pages12
JournalNeuroImage
Volume21
Issue number1
DOIs
StatePublished - Jan 2004
Externally publishedYes

Fingerprint

Brain
Atrophy
Machine Learning
Population

Keywords

  • High-dimensional shape transformations
  • Machine learning methods
  • Morphological classification

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Neurology

Cite this

Morphological classification of brains via high-dimensional shape transformations and machine learning methods. / Lao, Zhiqiang; Shen, Dinggang; Xue, Zhong; Karacali, Bilge; Resnick, Susan M.; Davatzikos, Christos.

In: NeuroImage, Vol. 21, No. 1, 01.2004, p. 46-57.

Research output: Contribution to journalArticle

Lao, Zhiqiang ; Shen, Dinggang ; Xue, Zhong ; Karacali, Bilge ; Resnick, Susan M. ; Davatzikos, Christos. / Morphological classification of brains via high-dimensional shape transformations and machine learning methods. In: NeuroImage. 2004 ; Vol. 21, No. 1. pp. 46-57.
@article{accf84719c2c4099bef99f9a8faa5627,
title = "Morphological classification of brains via high-dimensional shape transformations and machine learning methods",
abstract = "A high-dimensional shape transformation posed in a mass-preserving framework is used as a morphological signature of a brain image. Population differences with complex spatial patterns are then determined by applying a nonlinear support vector machine (SVM) pattern classification method to the morphological signatures. Significant reduction of the dimensionality of the morphological signatures is achieved via wavelet decomposition and feature reduction methods. Applying the method to MR images with simulated atrophy shows that the method can correctly detect subtle and spatially complex atrophy, even when the simulated atrophy represents only a 5{\%} variation from the original image. Applying this method to actual MR images shows that brains can be correctly determined to be male or female with a successful classification rate of 97{\%}, using the leave-one-out method. This proposed method also shows a high classification rate for old adults' age classification, even under difficult test scenarios. The main characteristic of the proposed methodology is that, by applying multivariate pattern classification methods, it can detect subtle and spatially complex patterns of morphological group differences which are often not detectable by voxel-based morphometric methods, because these methods analyze morphological measurements voxel-by-voxel and do not consider the entirety of the data simultaneously.",
keywords = "High-dimensional shape transformations, Machine learning methods, Morphological classification",
author = "Zhiqiang Lao and Dinggang Shen and Zhong Xue and Bilge Karacali and Resnick, {Susan M.} and Christos Davatzikos",
year = "2004",
month = "1",
doi = "10.1016/j.neuroimage.2003.09.027",
language = "English (US)",
volume = "21",
pages = "46--57",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",
number = "1",

}

TY - JOUR

T1 - Morphological classification of brains via high-dimensional shape transformations and machine learning methods

AU - Lao, Zhiqiang

AU - Shen, Dinggang

AU - Xue, Zhong

AU - Karacali, Bilge

AU - Resnick, Susan M.

AU - Davatzikos, Christos

PY - 2004/1

Y1 - 2004/1

N2 - A high-dimensional shape transformation posed in a mass-preserving framework is used as a morphological signature of a brain image. Population differences with complex spatial patterns are then determined by applying a nonlinear support vector machine (SVM) pattern classification method to the morphological signatures. Significant reduction of the dimensionality of the morphological signatures is achieved via wavelet decomposition and feature reduction methods. Applying the method to MR images with simulated atrophy shows that the method can correctly detect subtle and spatially complex atrophy, even when the simulated atrophy represents only a 5% variation from the original image. Applying this method to actual MR images shows that brains can be correctly determined to be male or female with a successful classification rate of 97%, using the leave-one-out method. This proposed method also shows a high classification rate for old adults' age classification, even under difficult test scenarios. The main characteristic of the proposed methodology is that, by applying multivariate pattern classification methods, it can detect subtle and spatially complex patterns of morphological group differences which are often not detectable by voxel-based morphometric methods, because these methods analyze morphological measurements voxel-by-voxel and do not consider the entirety of the data simultaneously.

AB - A high-dimensional shape transformation posed in a mass-preserving framework is used as a morphological signature of a brain image. Population differences with complex spatial patterns are then determined by applying a nonlinear support vector machine (SVM) pattern classification method to the morphological signatures. Significant reduction of the dimensionality of the morphological signatures is achieved via wavelet decomposition and feature reduction methods. Applying the method to MR images with simulated atrophy shows that the method can correctly detect subtle and spatially complex atrophy, even when the simulated atrophy represents only a 5% variation from the original image. Applying this method to actual MR images shows that brains can be correctly determined to be male or female with a successful classification rate of 97%, using the leave-one-out method. This proposed method also shows a high classification rate for old adults' age classification, even under difficult test scenarios. The main characteristic of the proposed methodology is that, by applying multivariate pattern classification methods, it can detect subtle and spatially complex patterns of morphological group differences which are often not detectable by voxel-based morphometric methods, because these methods analyze morphological measurements voxel-by-voxel and do not consider the entirety of the data simultaneously.

KW - High-dimensional shape transformations

KW - Machine learning methods

KW - Morphological classification

UR - http://www.scopus.com/inward/record.url?scp=1642574430&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1642574430&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2003.09.027

DO - 10.1016/j.neuroimage.2003.09.027

M3 - Article

C2 - 14741641

AN - SCOPUS:1642574430

VL - 21

SP - 46

EP - 57

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

IS - 1

ER -