Amnestic MCI future clinical status prediction using baseline MRI features

Simon Duchesne, Christian Bocti, Kathy De Sousa, Giovanni B. Frisoni, Howard Chertkow, D. Louis Collins

Research output: Contribution to journalArticle

24 Citations (Scopus)

Abstract

Amnestic mild cognitive impairment (aMCI) individuals are known to be at risk for progression to clinically probable Alzheimer's disease (AD). The objective of this work is to measure the accuracy of an automated classification technique based on clinical-quality, single time-point structural magnetic resonance imaging (MRI) scans for the retrospective prediction of future clinical status in aMCI. Thirty-one aMCI research subjects were followed with annual clinical reassessment after baseline MRI. Twenty subjects progressed to probable AD within an average 2.2 (1.4) years [mean age 76.6 (4.7) years, MMSE 27.1 (2.3)], while 11 remained non-demented on average 5.6 (2.6) years after baseline [mean age 73.3 (7.2) years, MMSE 28.2 (1.8)]. Leave-one-out classification was performed within a multidimensional MRI feature space built from intensity and local volume estimate data of a reference group of 75 probable AD and 75 age-matched control subjects. Prediction using aMCI data reached 81% accuracy, 70% sensitivity and 100% specificity. This automated and objective method has potential in helping predict future clinical status in aMCI.

Original languageEnglish
Pages (from-to)1606-1617
Number of pages12
JournalNeurobiology of Aging
Volume31
Issue number9
DOIs
Publication statusPublished - Sep 2010

Fingerprint

Magnetic Resonance Imaging
Alzheimer Disease
Research Subjects
Cognitive Dysfunction
Sensitivity and Specificity

Keywords

  • Automated computer classification
  • Early detection
  • Magnetic resonance imaging
  • Mild cognitive impairment

ASJC Scopus subject areas

  • Clinical Neurology
  • Neuroscience(all)
  • Ageing
  • Developmental Biology
  • Geriatrics and Gerontology

Cite this

Amnestic MCI future clinical status prediction using baseline MRI features. / Duchesne, Simon; Bocti, Christian; De Sousa, Kathy; Frisoni, Giovanni B.; Chertkow, Howard; Collins, D. Louis.

In: Neurobiology of Aging, Vol. 31, No. 9, 09.2010, p. 1606-1617.

Research output: Contribution to journalArticle

Duchesne, Simon ; Bocti, Christian ; De Sousa, Kathy ; Frisoni, Giovanni B. ; Chertkow, Howard ; Collins, D. Louis. / Amnestic MCI future clinical status prediction using baseline MRI features. In: Neurobiology of Aging. 2010 ; Vol. 31, No. 9. pp. 1606-1617.
@article{13492b4907d64d2db589a281257fd09b,
title = "Amnestic MCI future clinical status prediction using baseline MRI features",
abstract = "Amnestic mild cognitive impairment (aMCI) individuals are known to be at risk for progression to clinically probable Alzheimer's disease (AD). The objective of this work is to measure the accuracy of an automated classification technique based on clinical-quality, single time-point structural magnetic resonance imaging (MRI) scans for the retrospective prediction of future clinical status in aMCI. Thirty-one aMCI research subjects were followed with annual clinical reassessment after baseline MRI. Twenty subjects progressed to probable AD within an average 2.2 (1.4) years [mean age 76.6 (4.7) years, MMSE 27.1 (2.3)], while 11 remained non-demented on average 5.6 (2.6) years after baseline [mean age 73.3 (7.2) years, MMSE 28.2 (1.8)]. Leave-one-out classification was performed within a multidimensional MRI feature space built from intensity and local volume estimate data of a reference group of 75 probable AD and 75 age-matched control subjects. Prediction using aMCI data reached 81{\%} accuracy, 70{\%} sensitivity and 100{\%} specificity. This automated and objective method has potential in helping predict future clinical status in aMCI.",
keywords = "Automated computer classification, Early detection, Magnetic resonance imaging, Mild cognitive impairment",
author = "Simon Duchesne and Christian Bocti and {De Sousa}, Kathy and Frisoni, {Giovanni B.} and Howard Chertkow and Collins, {D. Louis}",
year = "2010",
month = "9",
doi = "10.1016/j.neurobiolaging.2008.09.003",
language = "English",
volume = "31",
pages = "1606--1617",
journal = "Neurobiology of Aging",
issn = "0197-4580",
publisher = "Elsevier Inc.",
number = "9",

}

TY - JOUR

T1 - Amnestic MCI future clinical status prediction using baseline MRI features

AU - Duchesne, Simon

AU - Bocti, Christian

AU - De Sousa, Kathy

AU - Frisoni, Giovanni B.

AU - Chertkow, Howard

AU - Collins, D. Louis

PY - 2010/9

Y1 - 2010/9

N2 - Amnestic mild cognitive impairment (aMCI) individuals are known to be at risk for progression to clinically probable Alzheimer's disease (AD). The objective of this work is to measure the accuracy of an automated classification technique based on clinical-quality, single time-point structural magnetic resonance imaging (MRI) scans for the retrospective prediction of future clinical status in aMCI. Thirty-one aMCI research subjects were followed with annual clinical reassessment after baseline MRI. Twenty subjects progressed to probable AD within an average 2.2 (1.4) years [mean age 76.6 (4.7) years, MMSE 27.1 (2.3)], while 11 remained non-demented on average 5.6 (2.6) years after baseline [mean age 73.3 (7.2) years, MMSE 28.2 (1.8)]. Leave-one-out classification was performed within a multidimensional MRI feature space built from intensity and local volume estimate data of a reference group of 75 probable AD and 75 age-matched control subjects. Prediction using aMCI data reached 81% accuracy, 70% sensitivity and 100% specificity. This automated and objective method has potential in helping predict future clinical status in aMCI.

AB - Amnestic mild cognitive impairment (aMCI) individuals are known to be at risk for progression to clinically probable Alzheimer's disease (AD). The objective of this work is to measure the accuracy of an automated classification technique based on clinical-quality, single time-point structural magnetic resonance imaging (MRI) scans for the retrospective prediction of future clinical status in aMCI. Thirty-one aMCI research subjects were followed with annual clinical reassessment after baseline MRI. Twenty subjects progressed to probable AD within an average 2.2 (1.4) years [mean age 76.6 (4.7) years, MMSE 27.1 (2.3)], while 11 remained non-demented on average 5.6 (2.6) years after baseline [mean age 73.3 (7.2) years, MMSE 28.2 (1.8)]. Leave-one-out classification was performed within a multidimensional MRI feature space built from intensity and local volume estimate data of a reference group of 75 probable AD and 75 age-matched control subjects. Prediction using aMCI data reached 81% accuracy, 70% sensitivity and 100% specificity. This automated and objective method has potential in helping predict future clinical status in aMCI.

KW - Automated computer classification

KW - Early detection

KW - Magnetic resonance imaging

KW - Mild cognitive impairment

UR - http://www.scopus.com/inward/record.url?scp=77954959197&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77954959197&partnerID=8YFLogxK

U2 - 10.1016/j.neurobiolaging.2008.09.003

DO - 10.1016/j.neurobiolaging.2008.09.003

M3 - Article

C2 - 18947902

AN - SCOPUS:77954959197

VL - 31

SP - 1606

EP - 1617

JO - Neurobiology of Aging

JF - Neurobiology of Aging

SN - 0197-4580

IS - 9

ER -