Pattern analysis in neuroimaging

Beyond two-class categorization

Roman Filipovych, Ying Wang, Christos Davatzikos

Research output: Contribution to journalArticle

Abstract

One of the many advantages of multivariate pattern recognition approaches over conventional mass-univariate group analysis using voxel-wise statistical tests is their potential to provide highly sensitive and specific markers of diseases on an individual basis. However, a vast majority of imaging problems addressed by pattern recognition are viewed from the perspective of a two-class classification. In this article, we provide a summary of selected works that propose solutions to biomedical problems where the widely-accepted classification paradigm is not appropriate. These pattern recognition approaches address common challenges in many imaging studies: high heterogeneity of populations and continuous progression of diseases. We focus on diseases associated with aging and propose that clustering-based approaches may be more suitable for disentanglement of the underlying heterogeneity, while high-dimensional pattern regression methodology is appropriate for prediction of continuous and gradual clinical progression from magnetic resonance brain images.

Original languageEnglish (US)
Pages (from-to)173-178
Number of pages6
JournalInternational Journal of Imaging Systems and Technology
Volume21
Issue number2
DOIs
StatePublished - Jun 2011
Externally publishedYes

Fingerprint

Neuroimaging
Pattern recognition
Imaging techniques
Statistical tests
Magnetic resonance
Brain
Aging of materials

Keywords

  • aging
  • Alzheimer's disease
  • clustering
  • high-dimensional pattern analysis
  • MCI
  • MRI
  • pattern regression

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Pattern analysis in neuroimaging : Beyond two-class categorization. / Filipovych, Roman; Wang, Ying; Davatzikos, Christos.

In: International Journal of Imaging Systems and Technology, Vol. 21, No. 2, 06.2011, p. 173-178.

Research output: Contribution to journalArticle

Filipovych, Roman ; Wang, Ying ; Davatzikos, Christos. / Pattern analysis in neuroimaging : Beyond two-class categorization. In: International Journal of Imaging Systems and Technology. 2011 ; Vol. 21, No. 2. pp. 173-178.
@article{c7b653acb41245f48170bb5bc93146bc,
title = "Pattern analysis in neuroimaging: Beyond two-class categorization",
abstract = "One of the many advantages of multivariate pattern recognition approaches over conventional mass-univariate group analysis using voxel-wise statistical tests is their potential to provide highly sensitive and specific markers of diseases on an individual basis. However, a vast majority of imaging problems addressed by pattern recognition are viewed from the perspective of a two-class classification. In this article, we provide a summary of selected works that propose solutions to biomedical problems where the widely-accepted classification paradigm is not appropriate. These pattern recognition approaches address common challenges in many imaging studies: high heterogeneity of populations and continuous progression of diseases. We focus on diseases associated with aging and propose that clustering-based approaches may be more suitable for disentanglement of the underlying heterogeneity, while high-dimensional pattern regression methodology is appropriate for prediction of continuous and gradual clinical progression from magnetic resonance brain images.",
keywords = "aging, Alzheimer's disease, clustering, high-dimensional pattern analysis, MCI, MRI, pattern regression",
author = "Roman Filipovych and Ying Wang and Christos Davatzikos",
year = "2011",
month = "6",
doi = "10.1002/ima.20280",
language = "English (US)",
volume = "21",
pages = "173--178",
journal = "International Journal of Imaging Systems and Technology",
issn = "0899-9457",
publisher = "John Wiley and Sons Inc.",
number = "2",

}

TY - JOUR

T1 - Pattern analysis in neuroimaging

T2 - Beyond two-class categorization

AU - Filipovych, Roman

AU - Wang, Ying

AU - Davatzikos, Christos

PY - 2011/6

Y1 - 2011/6

N2 - One of the many advantages of multivariate pattern recognition approaches over conventional mass-univariate group analysis using voxel-wise statistical tests is their potential to provide highly sensitive and specific markers of diseases on an individual basis. However, a vast majority of imaging problems addressed by pattern recognition are viewed from the perspective of a two-class classification. In this article, we provide a summary of selected works that propose solutions to biomedical problems where the widely-accepted classification paradigm is not appropriate. These pattern recognition approaches address common challenges in many imaging studies: high heterogeneity of populations and continuous progression of diseases. We focus on diseases associated with aging and propose that clustering-based approaches may be more suitable for disentanglement of the underlying heterogeneity, while high-dimensional pattern regression methodology is appropriate for prediction of continuous and gradual clinical progression from magnetic resonance brain images.

AB - One of the many advantages of multivariate pattern recognition approaches over conventional mass-univariate group analysis using voxel-wise statistical tests is their potential to provide highly sensitive and specific markers of diseases on an individual basis. However, a vast majority of imaging problems addressed by pattern recognition are viewed from the perspective of a two-class classification. In this article, we provide a summary of selected works that propose solutions to biomedical problems where the widely-accepted classification paradigm is not appropriate. These pattern recognition approaches address common challenges in many imaging studies: high heterogeneity of populations and continuous progression of diseases. We focus on diseases associated with aging and propose that clustering-based approaches may be more suitable for disentanglement of the underlying heterogeneity, while high-dimensional pattern regression methodology is appropriate for prediction of continuous and gradual clinical progression from magnetic resonance brain images.

KW - aging

KW - Alzheimer's disease

KW - clustering

KW - high-dimensional pattern analysis

KW - MCI

KW - MRI

KW - pattern regression

UR - http://www.scopus.com/inward/record.url?scp=79955885579&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79955885579&partnerID=8YFLogxK

U2 - 10.1002/ima.20280

DO - 10.1002/ima.20280

M3 - Article

VL - 21

SP - 173

EP - 178

JO - International Journal of Imaging Systems and Technology

JF - International Journal of Imaging Systems and Technology

SN - 0899-9457

IS - 2

ER -