Relating one-year cognitive change in mild cognitive impairment to baseline MRI features

Simon Duchesne, Anna Caroli, Cristina Geroldi, D. Louis Collins, Giovanni B. Frisoni

Research output: Contribution to journalArticle

58 Citations (Scopus)

Abstract

Background: We propose a completely automated methodology to investigate the relationship between magnetic resonance image (MRI) features and changes in cognitive estimates, applied to the study of Mini-Mental State Examination (MMSE) changes in mild cognitive impairment (MCI). Subjects: A reference group composed of 75 patients with clinically probable Alzheimer's Disease (AD) and 75 age-matched controls; and a study group composed of 49 MCI, 20 having progressed to clinically probable AD and 29 having remained stable after a 48 month follow-up. Methods: We created a pathology-specific reference space using principal component analysis of MRI-based features (intensity, local volume changes) within the medial temporal lobe of T1-weighted baseline images for the reference group. We projected similar data from the study group and identified a restricted set of image features highly correlated with one-year change in MMSE, using a bootstrap sampling estimation. We used robust linear regression models to predict one-year MMSE changes from baseline MRI, baseline MMSE, age, gender, and years of education. Results: All experiments were performed using a leave-one-out paradigm. We found multiple image-based features highly correlated with one-year MMSE changes (|r| > 0.425). The model for all N = 49 MCI subjects had a correlation of r = 0.31 between actual and predicted one-year MMSE change values. A second model only for MCI subjects with MMSE loss larger than 1 U had a pairwise correlation r = 0.80 with an adjusted coefficient of determination r2 = 0.61. Findings: Our automated MRI-based technique revealed a strong relationship between baseline MRI features and one-year cognitive changes in a sub-group of MCI subjects. This technique should be generalized to other aspects of cognitive evaluation and to a wider scope of dementias.

Original languageEnglish
Pages (from-to)1363-1370
Number of pages8
JournalNeuroImage
Volume47
Issue number4
DOIs
Publication statusPublished - Oct 1 2009

Fingerprint

Magnetic Resonance Spectroscopy
Linear Models
Alzheimer Disease
Temporal Lobe
Principal Component Analysis
Dementia
Cognitive Dysfunction
Pathology
Education

Keywords

  • High-dimensional analysis
  • Mild cognitive impairment
  • Mini-Mental Score Examination
  • MRI
  • Regression

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Neurology

Cite this

Relating one-year cognitive change in mild cognitive impairment to baseline MRI features. / Duchesne, Simon; Caroli, Anna; Geroldi, Cristina; Collins, D. Louis; Frisoni, Giovanni B.

In: NeuroImage, Vol. 47, No. 4, 01.10.2009, p. 1363-1370.

Research output: Contribution to journalArticle

@article{8096dac4fd7b492e9ac9301a017f3426,
title = "Relating one-year cognitive change in mild cognitive impairment to baseline MRI features",
abstract = "Background: We propose a completely automated methodology to investigate the relationship between magnetic resonance image (MRI) features and changes in cognitive estimates, applied to the study of Mini-Mental State Examination (MMSE) changes in mild cognitive impairment (MCI). Subjects: A reference group composed of 75 patients with clinically probable Alzheimer's Disease (AD) and 75 age-matched controls; and a study group composed of 49 MCI, 20 having progressed to clinically probable AD and 29 having remained stable after a 48 month follow-up. Methods: We created a pathology-specific reference space using principal component analysis of MRI-based features (intensity, local volume changes) within the medial temporal lobe of T1-weighted baseline images for the reference group. We projected similar data from the study group and identified a restricted set of image features highly correlated with one-year change in MMSE, using a bootstrap sampling estimation. We used robust linear regression models to predict one-year MMSE changes from baseline MRI, baseline MMSE, age, gender, and years of education. Results: All experiments were performed using a leave-one-out paradigm. We found multiple image-based features highly correlated with one-year MMSE changes (|r| > 0.425). The model for all N = 49 MCI subjects had a correlation of r = 0.31 between actual and predicted one-year MMSE change values. A second model only for MCI subjects with MMSE loss larger than 1 U had a pairwise correlation r = 0.80 with an adjusted coefficient of determination r2 = 0.61. Findings: Our automated MRI-based technique revealed a strong relationship between baseline MRI features and one-year cognitive changes in a sub-group of MCI subjects. This technique should be generalized to other aspects of cognitive evaluation and to a wider scope of dementias.",
keywords = "High-dimensional analysis, Mild cognitive impairment, Mini-Mental Score Examination, MRI, Regression",
author = "Simon Duchesne and Anna Caroli and Cristina Geroldi and Collins, {D. Louis} and Frisoni, {Giovanni B.}",
year = "2009",
month = "10",
day = "1",
doi = "10.1016/j.neuroimage.2009.04.023",
language = "English",
volume = "47",
pages = "1363--1370",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",
number = "4",

}

TY - JOUR

T1 - Relating one-year cognitive change in mild cognitive impairment to baseline MRI features

AU - Duchesne, Simon

AU - Caroli, Anna

AU - Geroldi, Cristina

AU - Collins, D. Louis

AU - Frisoni, Giovanni B.

PY - 2009/10/1

Y1 - 2009/10/1

N2 - Background: We propose a completely automated methodology to investigate the relationship between magnetic resonance image (MRI) features and changes in cognitive estimates, applied to the study of Mini-Mental State Examination (MMSE) changes in mild cognitive impairment (MCI). Subjects: A reference group composed of 75 patients with clinically probable Alzheimer's Disease (AD) and 75 age-matched controls; and a study group composed of 49 MCI, 20 having progressed to clinically probable AD and 29 having remained stable after a 48 month follow-up. Methods: We created a pathology-specific reference space using principal component analysis of MRI-based features (intensity, local volume changes) within the medial temporal lobe of T1-weighted baseline images for the reference group. We projected similar data from the study group and identified a restricted set of image features highly correlated with one-year change in MMSE, using a bootstrap sampling estimation. We used robust linear regression models to predict one-year MMSE changes from baseline MRI, baseline MMSE, age, gender, and years of education. Results: All experiments were performed using a leave-one-out paradigm. We found multiple image-based features highly correlated with one-year MMSE changes (|r| > 0.425). The model for all N = 49 MCI subjects had a correlation of r = 0.31 between actual and predicted one-year MMSE change values. A second model only for MCI subjects with MMSE loss larger than 1 U had a pairwise correlation r = 0.80 with an adjusted coefficient of determination r2 = 0.61. Findings: Our automated MRI-based technique revealed a strong relationship between baseline MRI features and one-year cognitive changes in a sub-group of MCI subjects. This technique should be generalized to other aspects of cognitive evaluation and to a wider scope of dementias.

AB - Background: We propose a completely automated methodology to investigate the relationship between magnetic resonance image (MRI) features and changes in cognitive estimates, applied to the study of Mini-Mental State Examination (MMSE) changes in mild cognitive impairment (MCI). Subjects: A reference group composed of 75 patients with clinically probable Alzheimer's Disease (AD) and 75 age-matched controls; and a study group composed of 49 MCI, 20 having progressed to clinically probable AD and 29 having remained stable after a 48 month follow-up. Methods: We created a pathology-specific reference space using principal component analysis of MRI-based features (intensity, local volume changes) within the medial temporal lobe of T1-weighted baseline images for the reference group. We projected similar data from the study group and identified a restricted set of image features highly correlated with one-year change in MMSE, using a bootstrap sampling estimation. We used robust linear regression models to predict one-year MMSE changes from baseline MRI, baseline MMSE, age, gender, and years of education. Results: All experiments were performed using a leave-one-out paradigm. We found multiple image-based features highly correlated with one-year MMSE changes (|r| > 0.425). The model for all N = 49 MCI subjects had a correlation of r = 0.31 between actual and predicted one-year MMSE change values. A second model only for MCI subjects with MMSE loss larger than 1 U had a pairwise correlation r = 0.80 with an adjusted coefficient of determination r2 = 0.61. Findings: Our automated MRI-based technique revealed a strong relationship between baseline MRI features and one-year cognitive changes in a sub-group of MCI subjects. This technique should be generalized to other aspects of cognitive evaluation and to a wider scope of dementias.

KW - High-dimensional analysis

KW - Mild cognitive impairment

KW - Mini-Mental Score Examination

KW - MRI

KW - Regression

UR - http://www.scopus.com/inward/record.url?scp=67651020812&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67651020812&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2009.04.023

DO - 10.1016/j.neuroimage.2009.04.023

M3 - Article

C2 - 19371783

AN - SCOPUS:67651020812

VL - 47

SP - 1363

EP - 1370

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

IS - 4

ER -