An automated algorithm for the computation of brain volume change from sequential MRIs using an iterative principal component analysis and its evaluation for the assessment of whole-brain atrophy rates in patients with probable Alzheimer's disease

Kewei Chen, Eric M. Reiman, Gene E Alexander, Daniel Bandy, Rosemary Renaut, William R. Crum, Nick C. Fox, Martin N. Rossor

Research output: Contribution to journalArticle

39 Citations (Scopus)

Abstract

This article introduces an automated method for the computation of changes in brain volume from sequential magnetic resonance images (MRIs) using an iterative principal component analysis (IPCA) and demonstrates its ability to characterize whole-brain atrophy rates in patients with Alzheimer's disease (AD). The IPCA considers the voxel intensity pairs from coregistered MRIs and identifies those pairs a sufficiently large distance away from the iteratively determined PCA major axis. Analyses of simulated and real MRI data support the underlying assumption of a linear relationship in paired voxel intensities, identify an outlier distance threshold that optimizes the trade-off between sensitivity and specificity in the detection of small volume changes while accounting for global intensity changes, and demonstrate an ability to detect changes as small as 0.04% of brain volume without confounding effects of between-scan shifts in voxel intensity. In eight patients with probable AD and eight age-matched normal control subjects, the IPCA was comparable to the established but partly manual digital subtraction (DS) method in characterizing annual rates of whole-brain atrophy: resulting rates were correlated (Spearman rank correlation = 0.94, P < 0.0005) and comparable in distinguishing probable AD from normal aging (IPCA-detected atrophy rates: 2.17 ± 0.52% per year in the patients vs. 0.41 ± 0.22% per year in the controls [Wilcoxon-Mann-Whitney test P = 7.8 × 10-4]; DS-detected atrophy rates: 3.51 ± 1.31% per year in the patients vs. 0.48 ± 0.29% per year in the controls [P = 7.8 × 10-4]). The IPCA could be used in tracking the progression of AD, evaluating the disease-modifying effects of putative treatments, and investigating the course of other normal and pathological changes in brain morphology.

Original languageEnglish (US)
Pages (from-to)134-143
Number of pages10
JournalNeuroImage
Volume22
Issue number1
DOIs
StatePublished - May 2004

Fingerprint

Principal Component Analysis
Atrophy
Alzheimer Disease
Magnetic Resonance Spectroscopy
Brain
Aptitude
Passive Cutaneous Anaphylaxis
Sensitivity and Specificity
Therapeutics

Keywords

  • Alzheimer's disease
  • Atrophy
  • Iterative principal component analysis
  • MRI

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Neurology

Cite this

An automated algorithm for the computation of brain volume change from sequential MRIs using an iterative principal component analysis and its evaluation for the assessment of whole-brain atrophy rates in patients with probable Alzheimer's disease. / Chen, Kewei; Reiman, Eric M.; Alexander, Gene E; Bandy, Daniel; Renaut, Rosemary; Crum, William R.; Fox, Nick C.; Rossor, Martin N.

In: NeuroImage, Vol. 22, No. 1, 05.2004, p. 134-143.

Research output: Contribution to journalArticle

@article{89d88aa5be8b444c97f04f6a96a79768,
title = "An automated algorithm for the computation of brain volume change from sequential MRIs using an iterative principal component analysis and its evaluation for the assessment of whole-brain atrophy rates in patients with probable Alzheimer's disease",
abstract = "This article introduces an automated method for the computation of changes in brain volume from sequential magnetic resonance images (MRIs) using an iterative principal component analysis (IPCA) and demonstrates its ability to characterize whole-brain atrophy rates in patients with Alzheimer's disease (AD). The IPCA considers the voxel intensity pairs from coregistered MRIs and identifies those pairs a sufficiently large distance away from the iteratively determined PCA major axis. Analyses of simulated and real MRI data support the underlying assumption of a linear relationship in paired voxel intensities, identify an outlier distance threshold that optimizes the trade-off between sensitivity and specificity in the detection of small volume changes while accounting for global intensity changes, and demonstrate an ability to detect changes as small as 0.04{\%} of brain volume without confounding effects of between-scan shifts in voxel intensity. In eight patients with probable AD and eight age-matched normal control subjects, the IPCA was comparable to the established but partly manual digital subtraction (DS) method in characterizing annual rates of whole-brain atrophy: resulting rates were correlated (Spearman rank correlation = 0.94, P < 0.0005) and comparable in distinguishing probable AD from normal aging (IPCA-detected atrophy rates: 2.17 ± 0.52{\%} per year in the patients vs. 0.41 ± 0.22{\%} per year in the controls [Wilcoxon-Mann-Whitney test P = 7.8 × 10-4]; DS-detected atrophy rates: 3.51 ± 1.31{\%} per year in the patients vs. 0.48 ± 0.29{\%} per year in the controls [P = 7.8 × 10-4]). The IPCA could be used in tracking the progression of AD, evaluating the disease-modifying effects of putative treatments, and investigating the course of other normal and pathological changes in brain morphology.",
keywords = "Alzheimer's disease, Atrophy, Iterative principal component analysis, MRI",
author = "Kewei Chen and Reiman, {Eric M.} and Alexander, {Gene E} and Daniel Bandy and Rosemary Renaut and Crum, {William R.} and Fox, {Nick C.} and Rossor, {Martin N.}",
year = "2004",
month = "5",
doi = "10.1016/j.neuroimage.2004.01.002",
language = "English (US)",
volume = "22",
pages = "134--143",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",
number = "1",

}

TY - JOUR

T1 - An automated algorithm for the computation of brain volume change from sequential MRIs using an iterative principal component analysis and its evaluation for the assessment of whole-brain atrophy rates in patients with probable Alzheimer's disease

AU - Chen, Kewei

AU - Reiman, Eric M.

AU - Alexander, Gene E

AU - Bandy, Daniel

AU - Renaut, Rosemary

AU - Crum, William R.

AU - Fox, Nick C.

AU - Rossor, Martin N.

PY - 2004/5

Y1 - 2004/5

N2 - This article introduces an automated method for the computation of changes in brain volume from sequential magnetic resonance images (MRIs) using an iterative principal component analysis (IPCA) and demonstrates its ability to characterize whole-brain atrophy rates in patients with Alzheimer's disease (AD). The IPCA considers the voxel intensity pairs from coregistered MRIs and identifies those pairs a sufficiently large distance away from the iteratively determined PCA major axis. Analyses of simulated and real MRI data support the underlying assumption of a linear relationship in paired voxel intensities, identify an outlier distance threshold that optimizes the trade-off between sensitivity and specificity in the detection of small volume changes while accounting for global intensity changes, and demonstrate an ability to detect changes as small as 0.04% of brain volume without confounding effects of between-scan shifts in voxel intensity. In eight patients with probable AD and eight age-matched normal control subjects, the IPCA was comparable to the established but partly manual digital subtraction (DS) method in characterizing annual rates of whole-brain atrophy: resulting rates were correlated (Spearman rank correlation = 0.94, P < 0.0005) and comparable in distinguishing probable AD from normal aging (IPCA-detected atrophy rates: 2.17 ± 0.52% per year in the patients vs. 0.41 ± 0.22% per year in the controls [Wilcoxon-Mann-Whitney test P = 7.8 × 10-4]; DS-detected atrophy rates: 3.51 ± 1.31% per year in the patients vs. 0.48 ± 0.29% per year in the controls [P = 7.8 × 10-4]). The IPCA could be used in tracking the progression of AD, evaluating the disease-modifying effects of putative treatments, and investigating the course of other normal and pathological changes in brain morphology.

AB - This article introduces an automated method for the computation of changes in brain volume from sequential magnetic resonance images (MRIs) using an iterative principal component analysis (IPCA) and demonstrates its ability to characterize whole-brain atrophy rates in patients with Alzheimer's disease (AD). The IPCA considers the voxel intensity pairs from coregistered MRIs and identifies those pairs a sufficiently large distance away from the iteratively determined PCA major axis. Analyses of simulated and real MRI data support the underlying assumption of a linear relationship in paired voxel intensities, identify an outlier distance threshold that optimizes the trade-off between sensitivity and specificity in the detection of small volume changes while accounting for global intensity changes, and demonstrate an ability to detect changes as small as 0.04% of brain volume without confounding effects of between-scan shifts in voxel intensity. In eight patients with probable AD and eight age-matched normal control subjects, the IPCA was comparable to the established but partly manual digital subtraction (DS) method in characterizing annual rates of whole-brain atrophy: resulting rates were correlated (Spearman rank correlation = 0.94, P < 0.0005) and comparable in distinguishing probable AD from normal aging (IPCA-detected atrophy rates: 2.17 ± 0.52% per year in the patients vs. 0.41 ± 0.22% per year in the controls [Wilcoxon-Mann-Whitney test P = 7.8 × 10-4]; DS-detected atrophy rates: 3.51 ± 1.31% per year in the patients vs. 0.48 ± 0.29% per year in the controls [P = 7.8 × 10-4]). The IPCA could be used in tracking the progression of AD, evaluating the disease-modifying effects of putative treatments, and investigating the course of other normal and pathological changes in brain morphology.

KW - Alzheimer's disease

KW - Atrophy

KW - Iterative principal component analysis

KW - MRI

UR - http://www.scopus.com/inward/record.url?scp=1942456809&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1942456809&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2004.01.002

DO - 10.1016/j.neuroimage.2004.01.002

M3 - Article

C2 - 15110003

AN - SCOPUS:1942456809

VL - 22

SP - 134

EP - 143

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

IS - 1

ER -