Training labels for hippocampal segmentation based on the EADC-ADNI harmonized hippocampal protocol

Marina Boccardi, Martina Bocchetta, Félix C. Morency, D. Louis Collins, Masami Nishikawa, Rossana Ganzola, Michel J. Grothe, Dominik Wolf, Alberto Redolfi, Michela Pievani, Luigi Antelmi, Andreas Fellgiebel, Hiroshi Matsuda, Stefan Teipel, Simon Duchesne, Clifford R Jr. Jack, Giovanni B. Frisoni

Research output: Contribution to journalArticle

63 Citations (Scopus)

Abstract

Background: The European Alzheimer's Disease Consortium and Alzheimer's Disease Neuroimaging Initiative (ADNI) Harmonized Protocol (HarP) is a Delphi definition of manual hippocampal segmentation from magnetic resonance imaging (MRI) that can be used as the standard of truth to train new tracers, and to validate automated segmentation algorithms. Training requires large and representative data sets of segmented hippocampi. This work aims to produce a set of HarP labels for the proper training and certification of tracers and algorithms. Methods: Sixty-eight 1.5 T and 67 3 T volumetric structural ADNI scans from different subjects, balanced by age, medial temporal atrophy, and scanner manufacturer, were segmented by five qualified HarP tracers whose absolute interrater intraclass correlation coefficients were 0.953 and 0.975 (left and right). Labels were validated as HarP compliant through centralized quality check and correction. Results: Hippocampal volumes (mm3) were as follows: controls: left 5 3060 (standard deviation [SD], 502), right 5 3120 (SD, 897); mild cognitive impairment (MCI): left 5 2596 (SD, 447), right 5 2686 (SD, 473); and Alzheimer's disease (AD): left 5 2301 (SD, 492), right 5 2445 (SD, 525). Volumes significantly correlated with atrophy severity at Scheltens' scale (Spearman's r5 ,20.468, P5 ,.0005). Background: The European Alzheimer's Disease Consortium and Alzheimer's Disease Neuroimaging Initiative (ADNI) Harmonized Protocol (HarP) is a Delphi definition of manual hippocampal segmentation from magnetic resonance imaging (MRI) that can be used as the standard of truth to train new tracers, and to validate automated segmentation algorithms. Training requires large and representative data sets of segmented hippocampi. This work aims to produce a set of HarP labels for the proper training and certification of tracers and algorithms. Methods: Sixty-eight 1.5 T and 67 3 T volumetric structural ADNI scans from different subjects, balanced by age, medial temporal atrophy, and scanner manufacturer, were segmented by five qualified HarP tracers whose absolute interrater intraclass correlation coefficients were 0.953 and 0.975 (left and right). Labels were validated as HarP compliant through centralized quality check and correction. Results: Hippocampal volumes (mm<sup>3</sup>) were as follows: controls: left 5 3060 (standard deviation [SD], 502), right 5 3120 (SD, 897); mild cognitive impairment (MCI): left 5 2596 (SD, 447), right 5 2686 (SD, 473); and Alzheimer's disease (AD): left 5 2301 (SD, 492), right 5 2445 (SD, 525). Volumes significantly correlated with atrophy severity at Scheltens' scale (Spearman's r5 ,20.468, P5 ,.0005).

Original languageEnglish (US)
Pages (from-to)175-183
Number of pages9
JournalAlzheimer's and Dementia
Volume11
Issue number2
DOIs
StatePublished - 2015

Fingerprint

Neuroimaging
Alzheimer Disease
Atrophy
Certification
Hippocampus
Magnetic Resonance Imaging
Datasets
Alzheimer Disease 5
Cognitive Dysfunction

Keywords

  • Algorithm training
  • Automated segmentation algorithms
  • Benchmark images
  • Harmonized protocol
  • Hippocampal segmentation
  • Hippocampus
  • MRI

ASJC Scopus subject areas

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

Cite this

Boccardi, M., Bocchetta, M., Morency, F. C., Collins, D. L., Nishikawa, M., Ganzola, R., ... Frisoni, G. B. (2015). Training labels for hippocampal segmentation based on the EADC-ADNI harmonized hippocampal protocol. Alzheimer's and Dementia, 11(2), 175-183. https://doi.org/10.1016/j.jalz.2014.12.002

Training labels for hippocampal segmentation based on the EADC-ADNI harmonized hippocampal protocol. / Boccardi, Marina; Bocchetta, Martina; Morency, Félix C.; Collins, D. Louis; Nishikawa, Masami; Ganzola, Rossana; Grothe, Michel J.; Wolf, Dominik; Redolfi, Alberto; Pievani, Michela; Antelmi, Luigi; Fellgiebel, Andreas; Matsuda, Hiroshi; Teipel, Stefan; Duchesne, Simon; Jack, Clifford R Jr.; Frisoni, Giovanni B.

In: Alzheimer's and Dementia, Vol. 11, No. 2, 2015, p. 175-183.

Research output: Contribution to journalArticle

Boccardi, M, Bocchetta, M, Morency, FC, Collins, DL, Nishikawa, M, Ganzola, R, Grothe, MJ, Wolf, D, Redolfi, A, Pievani, M, Antelmi, L, Fellgiebel, A, Matsuda, H, Teipel, S, Duchesne, S, Jack, CRJ & Frisoni, GB 2015, 'Training labels for hippocampal segmentation based on the EADC-ADNI harmonized hippocampal protocol', Alzheimer's and Dementia, vol. 11, no. 2, pp. 175-183. https://doi.org/10.1016/j.jalz.2014.12.002
Boccardi, Marina ; Bocchetta, Martina ; Morency, Félix C. ; Collins, D. Louis ; Nishikawa, Masami ; Ganzola, Rossana ; Grothe, Michel J. ; Wolf, Dominik ; Redolfi, Alberto ; Pievani, Michela ; Antelmi, Luigi ; Fellgiebel, Andreas ; Matsuda, Hiroshi ; Teipel, Stefan ; Duchesne, Simon ; Jack, Clifford R Jr. ; Frisoni, Giovanni B. / Training labels for hippocampal segmentation based on the EADC-ADNI harmonized hippocampal protocol. In: Alzheimer's and Dementia. 2015 ; Vol. 11, No. 2. pp. 175-183.
@article{d71553dd090b4b6c8306b78c93fe526c,
title = "Training labels for hippocampal segmentation based on the EADC-ADNI harmonized hippocampal protocol",
abstract = "Background: The European Alzheimer's Disease Consortium and Alzheimer's Disease Neuroimaging Initiative (ADNI) Harmonized Protocol (HarP) is a Delphi definition of manual hippocampal segmentation from magnetic resonance imaging (MRI) that can be used as the standard of truth to train new tracers, and to validate automated segmentation algorithms. Training requires large and representative data sets of segmented hippocampi. This work aims to produce a set of HarP labels for the proper training and certification of tracers and algorithms. Methods: Sixty-eight 1.5 T and 67 3 T volumetric structural ADNI scans from different subjects, balanced by age, medial temporal atrophy, and scanner manufacturer, were segmented by five qualified HarP tracers whose absolute interrater intraclass correlation coefficients were 0.953 and 0.975 (left and right). Labels were validated as HarP compliant through centralized quality check and correction. Results: Hippocampal volumes (mm3) were as follows: controls: left 5 3060 (standard deviation [SD], 502), right 5 3120 (SD, 897); mild cognitive impairment (MCI): left 5 2596 (SD, 447), right 5 2686 (SD, 473); and Alzheimer's disease (AD): left 5 2301 (SD, 492), right 5 2445 (SD, 525). Volumes significantly correlated with atrophy severity at Scheltens' scale (Spearman's r5 ,20.468, P5 ,.0005). Background: The European Alzheimer's Disease Consortium and Alzheimer's Disease Neuroimaging Initiative (ADNI) Harmonized Protocol (HarP) is a Delphi definition of manual hippocampal segmentation from magnetic resonance imaging (MRI) that can be used as the standard of truth to train new tracers, and to validate automated segmentation algorithms. Training requires large and representative data sets of segmented hippocampi. This work aims to produce a set of HarP labels for the proper training and certification of tracers and algorithms. Methods: Sixty-eight 1.5 T and 67 3 T volumetric structural ADNI scans from different subjects, balanced by age, medial temporal atrophy, and scanner manufacturer, were segmented by five qualified HarP tracers whose absolute interrater intraclass correlation coefficients were 0.953 and 0.975 (left and right). Labels were validated as HarP compliant through centralized quality check and correction. Results: Hippocampal volumes (mm3) were as follows: controls: left 5 3060 (standard deviation [SD], 502), right 5 3120 (SD, 897); mild cognitive impairment (MCI): left 5 2596 (SD, 447), right 5 2686 (SD, 473); and Alzheimer's disease (AD): left 5 2301 (SD, 492), right 5 2445 (SD, 525). Volumes significantly correlated with atrophy severity at Scheltens' scale (Spearman's r5 ,20.468, P5 ,.0005).",
keywords = "Algorithm training, Automated segmentation algorithms, Benchmark images, Harmonized protocol, Hippocampal segmentation, Hippocampus, MRI",
author = "Marina Boccardi and Martina Bocchetta and Morency, {F{\'e}lix C.} and Collins, {D. Louis} and Masami Nishikawa and Rossana Ganzola and Grothe, {Michel J.} and Dominik Wolf and Alberto Redolfi and Michela Pievani and Luigi Antelmi and Andreas Fellgiebel and Hiroshi Matsuda and Stefan Teipel and Simon Duchesne and Jack, {Clifford R Jr.} and Frisoni, {Giovanni B.}",
year = "2015",
doi = "10.1016/j.jalz.2014.12.002",
language = "English (US)",
volume = "11",
pages = "175--183",
journal = "Alzheimer's and Dementia",
issn = "1552-5260",
publisher = "Elsevier Inc.",
number = "2",

}

TY - JOUR

T1 - Training labels for hippocampal segmentation based on the EADC-ADNI harmonized hippocampal protocol

AU - Boccardi, Marina

AU - Bocchetta, Martina

AU - Morency, Félix C.

AU - Collins, D. Louis

AU - Nishikawa, Masami

AU - Ganzola, Rossana

AU - Grothe, Michel J.

AU - Wolf, Dominik

AU - Redolfi, Alberto

AU - Pievani, Michela

AU - Antelmi, Luigi

AU - Fellgiebel, Andreas

AU - Matsuda, Hiroshi

AU - Teipel, Stefan

AU - Duchesne, Simon

AU - Jack, Clifford R Jr.

AU - Frisoni, Giovanni B.

PY - 2015

Y1 - 2015

N2 - Background: The European Alzheimer's Disease Consortium and Alzheimer's Disease Neuroimaging Initiative (ADNI) Harmonized Protocol (HarP) is a Delphi definition of manual hippocampal segmentation from magnetic resonance imaging (MRI) that can be used as the standard of truth to train new tracers, and to validate automated segmentation algorithms. Training requires large and representative data sets of segmented hippocampi. This work aims to produce a set of HarP labels for the proper training and certification of tracers and algorithms. Methods: Sixty-eight 1.5 T and 67 3 T volumetric structural ADNI scans from different subjects, balanced by age, medial temporal atrophy, and scanner manufacturer, were segmented by five qualified HarP tracers whose absolute interrater intraclass correlation coefficients were 0.953 and 0.975 (left and right). Labels were validated as HarP compliant through centralized quality check and correction. Results: Hippocampal volumes (mm3) were as follows: controls: left 5 3060 (standard deviation [SD], 502), right 5 3120 (SD, 897); mild cognitive impairment (MCI): left 5 2596 (SD, 447), right 5 2686 (SD, 473); and Alzheimer's disease (AD): left 5 2301 (SD, 492), right 5 2445 (SD, 525). Volumes significantly correlated with atrophy severity at Scheltens' scale (Spearman's r5 ,20.468, P5 ,.0005). Background: The European Alzheimer's Disease Consortium and Alzheimer's Disease Neuroimaging Initiative (ADNI) Harmonized Protocol (HarP) is a Delphi definition of manual hippocampal segmentation from magnetic resonance imaging (MRI) that can be used as the standard of truth to train new tracers, and to validate automated segmentation algorithms. Training requires large and representative data sets of segmented hippocampi. This work aims to produce a set of HarP labels for the proper training and certification of tracers and algorithms. Methods: Sixty-eight 1.5 T and 67 3 T volumetric structural ADNI scans from different subjects, balanced by age, medial temporal atrophy, and scanner manufacturer, were segmented by five qualified HarP tracers whose absolute interrater intraclass correlation coefficients were 0.953 and 0.975 (left and right). Labels were validated as HarP compliant through centralized quality check and correction. Results: Hippocampal volumes (mm3) were as follows: controls: left 5 3060 (standard deviation [SD], 502), right 5 3120 (SD, 897); mild cognitive impairment (MCI): left 5 2596 (SD, 447), right 5 2686 (SD, 473); and Alzheimer's disease (AD): left 5 2301 (SD, 492), right 5 2445 (SD, 525). Volumes significantly correlated with atrophy severity at Scheltens' scale (Spearman's r5 ,20.468, P5 ,.0005).

AB - Background: The European Alzheimer's Disease Consortium and Alzheimer's Disease Neuroimaging Initiative (ADNI) Harmonized Protocol (HarP) is a Delphi definition of manual hippocampal segmentation from magnetic resonance imaging (MRI) that can be used as the standard of truth to train new tracers, and to validate automated segmentation algorithms. Training requires large and representative data sets of segmented hippocampi. This work aims to produce a set of HarP labels for the proper training and certification of tracers and algorithms. Methods: Sixty-eight 1.5 T and 67 3 T volumetric structural ADNI scans from different subjects, balanced by age, medial temporal atrophy, and scanner manufacturer, were segmented by five qualified HarP tracers whose absolute interrater intraclass correlation coefficients were 0.953 and 0.975 (left and right). Labels were validated as HarP compliant through centralized quality check and correction. Results: Hippocampal volumes (mm3) were as follows: controls: left 5 3060 (standard deviation [SD], 502), right 5 3120 (SD, 897); mild cognitive impairment (MCI): left 5 2596 (SD, 447), right 5 2686 (SD, 473); and Alzheimer's disease (AD): left 5 2301 (SD, 492), right 5 2445 (SD, 525). Volumes significantly correlated with atrophy severity at Scheltens' scale (Spearman's r5 ,20.468, P5 ,.0005). Background: The European Alzheimer's Disease Consortium and Alzheimer's Disease Neuroimaging Initiative (ADNI) Harmonized Protocol (HarP) is a Delphi definition of manual hippocampal segmentation from magnetic resonance imaging (MRI) that can be used as the standard of truth to train new tracers, and to validate automated segmentation algorithms. Training requires large and representative data sets of segmented hippocampi. This work aims to produce a set of HarP labels for the proper training and certification of tracers and algorithms. Methods: Sixty-eight 1.5 T and 67 3 T volumetric structural ADNI scans from different subjects, balanced by age, medial temporal atrophy, and scanner manufacturer, were segmented by five qualified HarP tracers whose absolute interrater intraclass correlation coefficients were 0.953 and 0.975 (left and right). Labels were validated as HarP compliant through centralized quality check and correction. Results: Hippocampal volumes (mm3) were as follows: controls: left 5 3060 (standard deviation [SD], 502), right 5 3120 (SD, 897); mild cognitive impairment (MCI): left 5 2596 (SD, 447), right 5 2686 (SD, 473); and Alzheimer's disease (AD): left 5 2301 (SD, 492), right 5 2445 (SD, 525). Volumes significantly correlated with atrophy severity at Scheltens' scale (Spearman's r5 ,20.468, P5 ,.0005).

KW - Algorithm training

KW - Automated segmentation algorithms

KW - Benchmark images

KW - Harmonized protocol

KW - Hippocampal segmentation

KW - Hippocampus

KW - MRI

UR - http://www.scopus.com/inward/record.url?scp=84933522176&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84933522176&partnerID=8YFLogxK

U2 - 10.1016/j.jalz.2014.12.002

DO - 10.1016/j.jalz.2014.12.002

M3 - Article

C2 - 25616957

AN - SCOPUS:84933522176

VL - 11

SP - 175

EP - 183

JO - Alzheimer's and Dementia

JF - Alzheimer's and Dementia

SN - 1552-5260

IS - 2

ER -