Analysis of regional cerebral blood flow data to discriminate among Alzheimer's disease, frontotemporal dementia, and elderly controls

A multi-block barycentric discriminant analysis (MUBADA) methodology

Hervé Abdi, Lynne J. Williams, Derek Beaton, Mette T. Posamentier, Thomas S. Harris, Anjali Krishnan, Michael D. Devous

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

We present a generalization of mean-centered partial least squares correlation called multiblock barycentric discriminant analysis (MUBADA) that integrates multiple regions of interest (ROIs) to analyze functional brain images of cerebral blood flow or metabolism obtained with SPECT or PET. To illustrate MUBADA we analyzed data from 104 participants comprising Alzheimer's disease (AD) patients, frontotemporal dementia (FTD) patients, and elderly normal controls. Brain images were analyzed via 28 ROIs (59,845 voxels) selected for clinical relevance. This is a discriminant analysis (DA) question with several blocks (one per ROI) and with more variables than observations, a configuration that precludes using DA. MUBADA revealed two factors explaining 74% and 26% of the total variance: Factor 1 isolated FTD, and Factor 2 isolated AD. A random effects model correctly classified 64% (chance = 33%) of "new" participants (p < 0.0001). MUBADA identified ROIs that best discriminated groups: ROIs separating FTD were bilateral inferior, middle frontal, left inferior, and middle temporal gyri, while ROIs separating AD were bilateral thalamus, inferior parietal gyrus, inferior temporal gyrus, left precuneus, middle frontal, and middle temporal gyri. MUBADA classified participants at levels comparable to standard methods (i.e., SVM, PCA-LDA, and PLS-DA) but provided information (e.g., discriminative ROIs and voxels) not easily accessible to these methods.

Original languageEnglish (US)
JournalJournal of Alzheimer's Disease
Volume31
Issue numberSUPPL. 3
DOIs
StatePublished - 2012

Fingerprint

Cerebrovascular Circulation
Frontotemporal Dementia
Regional Blood Flow
Discriminant Analysis
Alzheimer Disease
Temporal Lobe
Parietal Lobe
Passive Cutaneous Anaphylaxis
Public Opinion
Brain
Single-Photon Emission-Computed Tomography
Least-Squares Analysis
Thalamus

Keywords

  • BADA
  • dementia
  • discriminant analysis
  • MUBADA
  • multiblock analysis
  • neuroimaging
  • partial least squares correlation
  • PET
  • PLS methods
  • SPECT

ASJC Scopus subject areas

  • Psychiatry and Mental health
  • Geriatrics and Gerontology
  • Clinical Psychology

Cite this

Analysis of regional cerebral blood flow data to discriminate among Alzheimer's disease, frontotemporal dementia, and elderly controls : A multi-block barycentric discriminant analysis (MUBADA) methodology. / Abdi, Hervé; Williams, Lynne J.; Beaton, Derek; Posamentier, Mette T.; Harris, Thomas S.; Krishnan, Anjali; Devous, Michael D.

In: Journal of Alzheimer's Disease, Vol. 31, No. SUPPL. 3, 2012.

Research output: Contribution to journalArticle

Abdi, Hervé ; Williams, Lynne J. ; Beaton, Derek ; Posamentier, Mette T. ; Harris, Thomas S. ; Krishnan, Anjali ; Devous, Michael D. / Analysis of regional cerebral blood flow data to discriminate among Alzheimer's disease, frontotemporal dementia, and elderly controls : A multi-block barycentric discriminant analysis (MUBADA) methodology. In: Journal of Alzheimer's Disease. 2012 ; Vol. 31, No. SUPPL. 3.
@article{bd317221b73741d19cfd929f277178f1,
title = "Analysis of regional cerebral blood flow data to discriminate among Alzheimer's disease, frontotemporal dementia, and elderly controls: A multi-block barycentric discriminant analysis (MUBADA) methodology",
abstract = "We present a generalization of mean-centered partial least squares correlation called multiblock barycentric discriminant analysis (MUBADA) that integrates multiple regions of interest (ROIs) to analyze functional brain images of cerebral blood flow or metabolism obtained with SPECT or PET. To illustrate MUBADA we analyzed data from 104 participants comprising Alzheimer's disease (AD) patients, frontotemporal dementia (FTD) patients, and elderly normal controls. Brain images were analyzed via 28 ROIs (59,845 voxels) selected for clinical relevance. This is a discriminant analysis (DA) question with several blocks (one per ROI) and with more variables than observations, a configuration that precludes using DA. MUBADA revealed two factors explaining 74{\%} and 26{\%} of the total variance: Factor 1 isolated FTD, and Factor 2 isolated AD. A random effects model correctly classified 64{\%} (chance = 33{\%}) of {"}new{"} participants (p < 0.0001). MUBADA identified ROIs that best discriminated groups: ROIs separating FTD were bilateral inferior, middle frontal, left inferior, and middle temporal gyri, while ROIs separating AD were bilateral thalamus, inferior parietal gyrus, inferior temporal gyrus, left precuneus, middle frontal, and middle temporal gyri. MUBADA classified participants at levels comparable to standard methods (i.e., SVM, PCA-LDA, and PLS-DA) but provided information (e.g., discriminative ROIs and voxels) not easily accessible to these methods.",
keywords = "BADA, dementia, discriminant analysis, MUBADA, multiblock analysis, neuroimaging, partial least squares correlation, PET, PLS methods, SPECT",
author = "Herv{\'e} Abdi and Williams, {Lynne J.} and Derek Beaton and Posamentier, {Mette T.} and Harris, {Thomas S.} and Anjali Krishnan and Devous, {Michael D.}",
year = "2012",
doi = "10.3233/JAD-2012-112111",
language = "English (US)",
volume = "31",
journal = "Journal of Alzheimer's Disease",
issn = "1387-2877",
publisher = "IOS Press",
number = "SUPPL. 3",

}

TY - JOUR

T1 - Analysis of regional cerebral blood flow data to discriminate among Alzheimer's disease, frontotemporal dementia, and elderly controls

T2 - A multi-block barycentric discriminant analysis (MUBADA) methodology

AU - Abdi, Hervé

AU - Williams, Lynne J.

AU - Beaton, Derek

AU - Posamentier, Mette T.

AU - Harris, Thomas S.

AU - Krishnan, Anjali

AU - Devous, Michael D.

PY - 2012

Y1 - 2012

N2 - We present a generalization of mean-centered partial least squares correlation called multiblock barycentric discriminant analysis (MUBADA) that integrates multiple regions of interest (ROIs) to analyze functional brain images of cerebral blood flow or metabolism obtained with SPECT or PET. To illustrate MUBADA we analyzed data from 104 participants comprising Alzheimer's disease (AD) patients, frontotemporal dementia (FTD) patients, and elderly normal controls. Brain images were analyzed via 28 ROIs (59,845 voxels) selected for clinical relevance. This is a discriminant analysis (DA) question with several blocks (one per ROI) and with more variables than observations, a configuration that precludes using DA. MUBADA revealed two factors explaining 74% and 26% of the total variance: Factor 1 isolated FTD, and Factor 2 isolated AD. A random effects model correctly classified 64% (chance = 33%) of "new" participants (p < 0.0001). MUBADA identified ROIs that best discriminated groups: ROIs separating FTD were bilateral inferior, middle frontal, left inferior, and middle temporal gyri, while ROIs separating AD were bilateral thalamus, inferior parietal gyrus, inferior temporal gyrus, left precuneus, middle frontal, and middle temporal gyri. MUBADA classified participants at levels comparable to standard methods (i.e., SVM, PCA-LDA, and PLS-DA) but provided information (e.g., discriminative ROIs and voxels) not easily accessible to these methods.

AB - We present a generalization of mean-centered partial least squares correlation called multiblock barycentric discriminant analysis (MUBADA) that integrates multiple regions of interest (ROIs) to analyze functional brain images of cerebral blood flow or metabolism obtained with SPECT or PET. To illustrate MUBADA we analyzed data from 104 participants comprising Alzheimer's disease (AD) patients, frontotemporal dementia (FTD) patients, and elderly normal controls. Brain images were analyzed via 28 ROIs (59,845 voxels) selected for clinical relevance. This is a discriminant analysis (DA) question with several blocks (one per ROI) and with more variables than observations, a configuration that precludes using DA. MUBADA revealed two factors explaining 74% and 26% of the total variance: Factor 1 isolated FTD, and Factor 2 isolated AD. A random effects model correctly classified 64% (chance = 33%) of "new" participants (p < 0.0001). MUBADA identified ROIs that best discriminated groups: ROIs separating FTD were bilateral inferior, middle frontal, left inferior, and middle temporal gyri, while ROIs separating AD were bilateral thalamus, inferior parietal gyrus, inferior temporal gyrus, left precuneus, middle frontal, and middle temporal gyri. MUBADA classified participants at levels comparable to standard methods (i.e., SVM, PCA-LDA, and PLS-DA) but provided information (e.g., discriminative ROIs and voxels) not easily accessible to these methods.

KW - BADA

KW - dementia

KW - discriminant analysis

KW - MUBADA

KW - multiblock analysis

KW - neuroimaging

KW - partial least squares correlation

KW - PET

KW - PLS methods

KW - SPECT

UR - http://www.scopus.com/inward/record.url?scp=84866885744&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866885744&partnerID=8YFLogxK

U2 - 10.3233/JAD-2012-112111

DO - 10.3233/JAD-2012-112111

M3 - Article

VL - 31

JO - Journal of Alzheimer's Disease

JF - Journal of Alzheimer's Disease

SN - 1387-2877

IS - SUPPL. 3

ER -