Manual segmentation qualification platform for the EADC-ADNI harmonized protocol for hippocampal segmentation project

Simon Duchesne, Fernando Valdivia, Nicolas Robitaille, Abderazzak Mouiha, F. Abiel Valdivia, Martina Bocchetta, Liana G. Apostolova, Rossana Ganzola, Greg Preboske, Dominik Wolf, Marina Boccardi, Clifford R. Jack, Giovanni B. Frisoni

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Background: The use of hippocampal volumetry as a biomarker for Alzheimer's disease (AD) requires that tracers from different laboratories comply with the same segmentation method. Here we present a platform for training and qualifying new tracers to perform the manual segmentation of the hippocampus on magnetic resonance images (MRI) following the European Alzheimer's Disease Consortium and Alzheimer's Disease Neuroimaging Initiative (EADC-ADNI) Harmonized Protocol (HarP). Our objective was to demonstrate that the training process embedded in the platform leads to increased compliance and qualification with the HarP. Method: Thirteen new tracers' segmentations were compared with benchmark images with respect to: (a) absolute segmentation volume; (b) spatial overlap of contour with the reference using the Jaccard similarity index; and (c) spatial distance of contour with the reference. Point by point visual feedback was provided through three training phases on 10 MRI. Tracers were then tested on 10 different MRIs in the qualification phase. Results: Statistical testing of training over three phases showed a significant increase of Jaccard (i.e. mean Jaccard overlap P ,.001) between phases on average for all raters, demonstrating that training positively increased compliance with the HarP. Based on these results we defined qualification thresholds which all tracers were able to meet. Conclusions: This platform is an adequate infrastructure allowing standardized training and evaluation of tracers' compliance with the HarP. This is a necessary step allowing the use of hippocampal volumetry as a biomarker for AD in clinical and research centers.

Original languageEnglish
Pages (from-to)161-174
Number of pages14
JournalAlzheimer's and Dementia
Volume11
Issue number2
DOIs
Publication statusPublished - 2015

Fingerprint

Neuroimaging
Alzheimer Disease
Magnetic Resonance Spectroscopy
Biomarkers
Benchmarking
Sensory Feedback
Compliance
Hippocampus
Research

Keywords

  • Alzheimer's disease
  • Area
  • Harmonized protocol
  • Hippocampal segmentation
  • Magnetic resonance imaging
  • Qualification platform
  • Qualitative criteria
  • Quantitative criteria
  • Spatial distance
  • Spatial overlap

ASJC Scopus subject areas

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

Cite this

Manual segmentation qualification platform for the EADC-ADNI harmonized protocol for hippocampal segmentation project. / Duchesne, Simon; Valdivia, Fernando; Robitaille, Nicolas; Mouiha, Abderazzak; Valdivia, F. Abiel; Bocchetta, Martina; Apostolova, Liana G.; Ganzola, Rossana; Preboske, Greg; Wolf, Dominik; Boccardi, Marina; Jack, Clifford R.; Frisoni, Giovanni B.

In: Alzheimer's and Dementia, Vol. 11, No. 2, 2015, p. 161-174.

Research output: Contribution to journalArticle

Duchesne, S, Valdivia, F, Robitaille, N, Mouiha, A, Valdivia, FA, Bocchetta, M, Apostolova, LG, Ganzola, R, Preboske, G, Wolf, D, Boccardi, M, Jack, CR & Frisoni, GB 2015, 'Manual segmentation qualification platform for the EADC-ADNI harmonized protocol for hippocampal segmentation project', Alzheimer's and Dementia, vol. 11, no. 2, pp. 161-174. https://doi.org/10.1016/j.jalz.2015.01.002
Duchesne, Simon ; Valdivia, Fernando ; Robitaille, Nicolas ; Mouiha, Abderazzak ; Valdivia, F. Abiel ; Bocchetta, Martina ; Apostolova, Liana G. ; Ganzola, Rossana ; Preboske, Greg ; Wolf, Dominik ; Boccardi, Marina ; Jack, Clifford R. ; Frisoni, Giovanni B. / Manual segmentation qualification platform for the EADC-ADNI harmonized protocol for hippocampal segmentation project. In: Alzheimer's and Dementia. 2015 ; Vol. 11, No. 2. pp. 161-174.
@article{d84e8e275524405b8ee4fc4b64b10f14,
title = "Manual segmentation qualification platform for the EADC-ADNI harmonized protocol for hippocampal segmentation project",
abstract = "Background: The use of hippocampal volumetry as a biomarker for Alzheimer's disease (AD) requires that tracers from different laboratories comply with the same segmentation method. Here we present a platform for training and qualifying new tracers to perform the manual segmentation of the hippocampus on magnetic resonance images (MRI) following the European Alzheimer's Disease Consortium and Alzheimer's Disease Neuroimaging Initiative (EADC-ADNI) Harmonized Protocol (HarP). Our objective was to demonstrate that the training process embedded in the platform leads to increased compliance and qualification with the HarP. Method: Thirteen new tracers' segmentations were compared with benchmark images with respect to: (a) absolute segmentation volume; (b) spatial overlap of contour with the reference using the Jaccard similarity index; and (c) spatial distance of contour with the reference. Point by point visual feedback was provided through three training phases on 10 MRI. Tracers were then tested on 10 different MRIs in the qualification phase. Results: Statistical testing of training over three phases showed a significant increase of Jaccard (i.e. mean Jaccard overlap P ,.001) between phases on average for all raters, demonstrating that training positively increased compliance with the HarP. Based on these results we defined qualification thresholds which all tracers were able to meet. Conclusions: This platform is an adequate infrastructure allowing standardized training and evaluation of tracers' compliance with the HarP. This is a necessary step allowing the use of hippocampal volumetry as a biomarker for AD in clinical and research centers.",
keywords = "Alzheimer's disease, Area, Harmonized protocol, Hippocampal segmentation, Magnetic resonance imaging, Qualification platform, Qualitative criteria, Quantitative criteria, Spatial distance, Spatial overlap",
author = "Simon Duchesne and Fernando Valdivia and Nicolas Robitaille and Abderazzak Mouiha and Valdivia, {F. Abiel} and Martina Bocchetta and Apostolova, {Liana G.} and Rossana Ganzola and Greg Preboske and Dominik Wolf and Marina Boccardi and Jack, {Clifford R.} and Frisoni, {Giovanni B.}",
year = "2015",
doi = "10.1016/j.jalz.2015.01.002",
language = "English",
volume = "11",
pages = "161--174",
journal = "Alzheimer's and Dementia",
issn = "1552-5260",
publisher = "Elsevier Inc.",
number = "2",

}

TY - JOUR

T1 - Manual segmentation qualification platform for the EADC-ADNI harmonized protocol for hippocampal segmentation project

AU - Duchesne, Simon

AU - Valdivia, Fernando

AU - Robitaille, Nicolas

AU - Mouiha, Abderazzak

AU - Valdivia, F. Abiel

AU - Bocchetta, Martina

AU - Apostolova, Liana G.

AU - Ganzola, Rossana

AU - Preboske, Greg

AU - Wolf, Dominik

AU - Boccardi, Marina

AU - Jack, Clifford R.

AU - Frisoni, Giovanni B.

PY - 2015

Y1 - 2015

N2 - Background: The use of hippocampal volumetry as a biomarker for Alzheimer's disease (AD) requires that tracers from different laboratories comply with the same segmentation method. Here we present a platform for training and qualifying new tracers to perform the manual segmentation of the hippocampus on magnetic resonance images (MRI) following the European Alzheimer's Disease Consortium and Alzheimer's Disease Neuroimaging Initiative (EADC-ADNI) Harmonized Protocol (HarP). Our objective was to demonstrate that the training process embedded in the platform leads to increased compliance and qualification with the HarP. Method: Thirteen new tracers' segmentations were compared with benchmark images with respect to: (a) absolute segmentation volume; (b) spatial overlap of contour with the reference using the Jaccard similarity index; and (c) spatial distance of contour with the reference. Point by point visual feedback was provided through three training phases on 10 MRI. Tracers were then tested on 10 different MRIs in the qualification phase. Results: Statistical testing of training over three phases showed a significant increase of Jaccard (i.e. mean Jaccard overlap P ,.001) between phases on average for all raters, demonstrating that training positively increased compliance with the HarP. Based on these results we defined qualification thresholds which all tracers were able to meet. Conclusions: This platform is an adequate infrastructure allowing standardized training and evaluation of tracers' compliance with the HarP. This is a necessary step allowing the use of hippocampal volumetry as a biomarker for AD in clinical and research centers.

AB - Background: The use of hippocampal volumetry as a biomarker for Alzheimer's disease (AD) requires that tracers from different laboratories comply with the same segmentation method. Here we present a platform for training and qualifying new tracers to perform the manual segmentation of the hippocampus on magnetic resonance images (MRI) following the European Alzheimer's Disease Consortium and Alzheimer's Disease Neuroimaging Initiative (EADC-ADNI) Harmonized Protocol (HarP). Our objective was to demonstrate that the training process embedded in the platform leads to increased compliance and qualification with the HarP. Method: Thirteen new tracers' segmentations were compared with benchmark images with respect to: (a) absolute segmentation volume; (b) spatial overlap of contour with the reference using the Jaccard similarity index; and (c) spatial distance of contour with the reference. Point by point visual feedback was provided through three training phases on 10 MRI. Tracers were then tested on 10 different MRIs in the qualification phase. Results: Statistical testing of training over three phases showed a significant increase of Jaccard (i.e. mean Jaccard overlap P ,.001) between phases on average for all raters, demonstrating that training positively increased compliance with the HarP. Based on these results we defined qualification thresholds which all tracers were able to meet. Conclusions: This platform is an adequate infrastructure allowing standardized training and evaluation of tracers' compliance with the HarP. This is a necessary step allowing the use of hippocampal volumetry as a biomarker for AD in clinical and research centers.

KW - Alzheimer's disease

KW - Area

KW - Harmonized protocol

KW - Hippocampal segmentation

KW - Magnetic resonance imaging

KW - Qualification platform

KW - Qualitative criteria

KW - Quantitative criteria

KW - Spatial distance

KW - Spatial overlap

UR - http://www.scopus.com/inward/record.url?scp=84933529246&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84933529246&partnerID=8YFLogxK

U2 - 10.1016/j.jalz.2015.01.002

DO - 10.1016/j.jalz.2015.01.002

M3 - Article

VL - 11

SP - 161

EP - 174

JO - Alzheimer's and Dementia

JF - Alzheimer's and Dementia

SN - 1552-5260

IS - 2

ER -