Automatic temporal lobe atrophy assessment in prodromal AD: Data from the DESCRIPA study

Andrea Chincarini, Paolo Bosco, Gianluca Gemme, Mario Esposito, Luca Rei, Sandro Squarcia, Roberto Bellotti, Lennart Minthon, Giovanni Frisoni, Philip Scheltens, Lutz Frölich, Hilkka Soininen, Pieter Jelle Visser, Flavio Nobili

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Background In the framework of the clinical validation of research tools, this investigation presents a validation study of an automatic medial temporal lobe atrophy measure that is applied to a naturalistic population sampled from memory clinic patients across Europe. Methods The procedure was developed on 1.5-T magnetic resonance images from the Alzheimer's Disease Neuroimaging Initiative database, and it was validated on an independent data set coming from the DESCRIPA study. All images underwent an automatic processing procedure to assess tissue atrophy that was targeted at the hippocampal region. For each subject, the procedure returns a classification index. Once provided with the clinical assessment at baseline and follow-up, subjects were grouped into cohorts to assess classification performance. Each cohort was divided into converters (co) and nonconverters (nc) depending on the clinical outcome at follow-up visit. Results We found the area under the receiver operating characteristic curve (AUC) was 0.81 for all co versus nc subjects, and AUC was 0.90 for subjective memory complaint (SMCnc) versus all co subjects. Furthermore, when training on mild cognitive impairment (MCI-nc/MCI-co), the classification performance generally exceeds that found when training on controls versus Alzheimer's disease (CTRL/AD). Conclusions Automatic magnetic resonance imaging analysis may assist clinical classification of subjects in a memory clinic setting even when images are not specifically acquired for automatic analysis.

Original languageEnglish
Pages (from-to)456-467
Number of pages12
JournalAlzheimer's and Dementia
Volume10
Issue number4
DOIs
Publication statusPublished - 2014

Fingerprint

Temporal Lobe
Atrophy
Area Under Curve
Alzheimer Disease
Validation Studies
Neuroimaging
ROC Curve
Magnetic Resonance Spectroscopy
Magnetic Resonance Imaging
Databases
Research
Population

Keywords

  • Alzheimer's disease
  • Hippocampus
  • Image analysis
  • Medial temporal lobe
  • Memory clinics
  • MRI
  • Naturalistic population

ASJC Scopus subject areas

  • Clinical Neurology
  • Developmental Neuroscience
  • Cellular and Molecular Neuroscience
  • Psychiatry and Mental health
  • Geriatrics and Gerontology
  • Epidemiology
  • Health Policy

Cite this

Automatic temporal lobe atrophy assessment in prodromal AD : Data from the DESCRIPA study. / Chincarini, Andrea; Bosco, Paolo; Gemme, Gianluca; Esposito, Mario; Rei, Luca; Squarcia, Sandro; Bellotti, Roberto; Minthon, Lennart; Frisoni, Giovanni; Scheltens, Philip; Frölich, Lutz; Soininen, Hilkka; Visser, Pieter Jelle; Nobili, Flavio.

In: Alzheimer's and Dementia, Vol. 10, No. 4, 2014, p. 456-467.

Research output: Contribution to journalArticle

Chincarini, A, Bosco, P, Gemme, G, Esposito, M, Rei, L, Squarcia, S, Bellotti, R, Minthon, L, Frisoni, G, Scheltens, P, Frölich, L, Soininen, H, Visser, PJ & Nobili, F 2014, 'Automatic temporal lobe atrophy assessment in prodromal AD: Data from the DESCRIPA study', Alzheimer's and Dementia, vol. 10, no. 4, pp. 456-467. https://doi.org/10.1016/j.jalz.2013.05.1774
Chincarini, Andrea ; Bosco, Paolo ; Gemme, Gianluca ; Esposito, Mario ; Rei, Luca ; Squarcia, Sandro ; Bellotti, Roberto ; Minthon, Lennart ; Frisoni, Giovanni ; Scheltens, Philip ; Frölich, Lutz ; Soininen, Hilkka ; Visser, Pieter Jelle ; Nobili, Flavio. / Automatic temporal lobe atrophy assessment in prodromal AD : Data from the DESCRIPA study. In: Alzheimer's and Dementia. 2014 ; Vol. 10, No. 4. pp. 456-467.
@article{7479b5b869f14bc4ae325e332fc17e1e,
title = "Automatic temporal lobe atrophy assessment in prodromal AD: Data from the DESCRIPA study",
abstract = "Background In the framework of the clinical validation of research tools, this investigation presents a validation study of an automatic medial temporal lobe atrophy measure that is applied to a naturalistic population sampled from memory clinic patients across Europe. Methods The procedure was developed on 1.5-T magnetic resonance images from the Alzheimer's Disease Neuroimaging Initiative database, and it was validated on an independent data set coming from the DESCRIPA study. All images underwent an automatic processing procedure to assess tissue atrophy that was targeted at the hippocampal region. For each subject, the procedure returns a classification index. Once provided with the clinical assessment at baseline and follow-up, subjects were grouped into cohorts to assess classification performance. Each cohort was divided into converters (co) and nonconverters (nc) depending on the clinical outcome at follow-up visit. Results We found the area under the receiver operating characteristic curve (AUC) was 0.81 for all co versus nc subjects, and AUC was 0.90 for subjective memory complaint (SMCnc) versus all co subjects. Furthermore, when training on mild cognitive impairment (MCI-nc/MCI-co), the classification performance generally exceeds that found when training on controls versus Alzheimer's disease (CTRL/AD). Conclusions Automatic magnetic resonance imaging analysis may assist clinical classification of subjects in a memory clinic setting even when images are not specifically acquired for automatic analysis.",
keywords = "Alzheimer's disease, Hippocampus, Image analysis, Medial temporal lobe, Memory clinics, MRI, Naturalistic population",
author = "Andrea Chincarini and Paolo Bosco and Gianluca Gemme and Mario Esposito and Luca Rei and Sandro Squarcia and Roberto Bellotti and Lennart Minthon and Giovanni Frisoni and Philip Scheltens and Lutz Fr{\"o}lich and Hilkka Soininen and Visser, {Pieter Jelle} and Flavio Nobili",
year = "2014",
doi = "10.1016/j.jalz.2013.05.1774",
language = "English",
volume = "10",
pages = "456--467",
journal = "Alzheimer's and Dementia",
issn = "1552-5260",
publisher = "Elsevier Inc.",
number = "4",

}

TY - JOUR

T1 - Automatic temporal lobe atrophy assessment in prodromal AD

T2 - Data from the DESCRIPA study

AU - Chincarini, Andrea

AU - Bosco, Paolo

AU - Gemme, Gianluca

AU - Esposito, Mario

AU - Rei, Luca

AU - Squarcia, Sandro

AU - Bellotti, Roberto

AU - Minthon, Lennart

AU - Frisoni, Giovanni

AU - Scheltens, Philip

AU - Frölich, Lutz

AU - Soininen, Hilkka

AU - Visser, Pieter Jelle

AU - Nobili, Flavio

PY - 2014

Y1 - 2014

N2 - Background In the framework of the clinical validation of research tools, this investigation presents a validation study of an automatic medial temporal lobe atrophy measure that is applied to a naturalistic population sampled from memory clinic patients across Europe. Methods The procedure was developed on 1.5-T magnetic resonance images from the Alzheimer's Disease Neuroimaging Initiative database, and it was validated on an independent data set coming from the DESCRIPA study. All images underwent an automatic processing procedure to assess tissue atrophy that was targeted at the hippocampal region. For each subject, the procedure returns a classification index. Once provided with the clinical assessment at baseline and follow-up, subjects were grouped into cohorts to assess classification performance. Each cohort was divided into converters (co) and nonconverters (nc) depending on the clinical outcome at follow-up visit. Results We found the area under the receiver operating characteristic curve (AUC) was 0.81 for all co versus nc subjects, and AUC was 0.90 for subjective memory complaint (SMCnc) versus all co subjects. Furthermore, when training on mild cognitive impairment (MCI-nc/MCI-co), the classification performance generally exceeds that found when training on controls versus Alzheimer's disease (CTRL/AD). Conclusions Automatic magnetic resonance imaging analysis may assist clinical classification of subjects in a memory clinic setting even when images are not specifically acquired for automatic analysis.

AB - Background In the framework of the clinical validation of research tools, this investigation presents a validation study of an automatic medial temporal lobe atrophy measure that is applied to a naturalistic population sampled from memory clinic patients across Europe. Methods The procedure was developed on 1.5-T magnetic resonance images from the Alzheimer's Disease Neuroimaging Initiative database, and it was validated on an independent data set coming from the DESCRIPA study. All images underwent an automatic processing procedure to assess tissue atrophy that was targeted at the hippocampal region. For each subject, the procedure returns a classification index. Once provided with the clinical assessment at baseline and follow-up, subjects were grouped into cohorts to assess classification performance. Each cohort was divided into converters (co) and nonconverters (nc) depending on the clinical outcome at follow-up visit. Results We found the area under the receiver operating characteristic curve (AUC) was 0.81 for all co versus nc subjects, and AUC was 0.90 for subjective memory complaint (SMCnc) versus all co subjects. Furthermore, when training on mild cognitive impairment (MCI-nc/MCI-co), the classification performance generally exceeds that found when training on controls versus Alzheimer's disease (CTRL/AD). Conclusions Automatic magnetic resonance imaging analysis may assist clinical classification of subjects in a memory clinic setting even when images are not specifically acquired for automatic analysis.

KW - Alzheimer's disease

KW - Hippocampus

KW - Image analysis

KW - Medial temporal lobe

KW - Memory clinics

KW - MRI

KW - Naturalistic population

UR - http://www.scopus.com/inward/record.url?scp=84903714501&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903714501&partnerID=8YFLogxK

U2 - 10.1016/j.jalz.2013.05.1774

DO - 10.1016/j.jalz.2013.05.1774

M3 - Article

C2 - 24035058

AN - SCOPUS:84903714501

VL - 10

SP - 456

EP - 467

JO - Alzheimer's and Dementia

JF - Alzheimer's and Dementia

SN - 1552-5260

IS - 4

ER -