Head-to-Head Comparison among Semi-Quantification Tools of Brain FDG-PET to Aid the Diagnosis of Prodromal Alzheimer's Disease

Andrea Brugnolo, Fabrizio De Carli, Marco Pagani, Slivia Morbelli, Cathrine Jonsson, Andrea Chincarini, Giovanni B. Frisoni, Samantha Galluzzi, Robert Perneczky, Alexander Drzezga, Bart N.M. Van Berckel, Rik Ossenkoppele, Mira Didic, Eric Guedj, Dario Arnaldi, Federico Massa, Matteo Grazzini, Matteo Pardini, Patrizia Mecocci, Massimo E. DottoriniMatteo Bauckneht, Gianmario Sambuceti, Flavio Nobili

Research output: Contribution to journalArticle

Abstract

Background: Several automatic tools have been implemented for semi-quantitative assessment of brain [ 18 ]F-FDG-PET. Objective: We aimed to head-to-head compare the diagnostic performance among three statistical parametric mapping (SPM)-based approaches, another voxel-based tool (i.e., PALZ), and a volumetric region of interest (VROI-SVM)-based approach, in distinguishing patients with prodromal Alzheimer's disease (pAD) from controls. Methods: Sixty-two pAD patients (MMSE score = 27.0±1.6) and one hundred-nine healthy subjects (CTR) (MMSE score = 29.2±1.2) were enrolled in five centers of the European Alzheimer's Disease Consortium. The three SPM-based methods, based on different rationales, included 1) a cluster identified through the correlation analysis between [ 18 ]F-FDG-PET and a verbal memory test (VROI-1), 2) a VROI derived from the comparison between pAD and CTR (VROI-2), and 3) visual analysis of individual maps obtained by the comparison between each subject and CTR (SPM-Maps). The VROI-SVM approach was based on 6 VROI plus 6 VROI asymmetry values derived from the pAD versus CTR comparison thanks to support vector machine (SVM). Results: The areas under the ROC curves between pAD and CTR were 0.84 for VROI-1, 0.83 for VROI-2, 0.79 for SPM maps, 0.87 for PALZ, and 0.95 for VROI-SVM. Pairwise comparisons of Youden index did not show statistically significant differences in diagnostic performance between VROI-1, VROI-2, SPM-Maps, and PALZ score whereas VROI-SVM performed significantly (p < 0.005) better than any of the other methods. Conclusion: The study confirms the good accuracy of [ 18 ]F-FDG-PET in discriminating healthy subjects from pAD and highlights that a non-linear, automatic VROI classifier based on SVM performs better than the voxel-based methods.

Original languageEnglish
Pages (from-to)383-394
Number of pages12
JournalJournal of Alzheimer's Disease
Volume68
Issue number1
DOIs
Publication statusPublished - Jan 1 2019

Fingerprint

Alzheimer Disease
Brain
Healthy Volunteers
ROC Curve
Area Under Curve
Support Vector Machine

Keywords

  • European Alzheimer Disease Consortium
  • FDG-PET
  • head-to-head comparison
  • prodromal Alzheimer's disease
  • statistical parametric mapping
  • volumetric region of interest

ASJC Scopus subject areas

  • Neuroscience(all)
  • Clinical Psychology
  • Geriatrics and Gerontology
  • Psychiatry and Mental health

Cite this

Head-to-Head Comparison among Semi-Quantification Tools of Brain FDG-PET to Aid the Diagnosis of Prodromal Alzheimer's Disease. / Brugnolo, Andrea; De Carli, Fabrizio; Pagani, Marco; Morbelli, Slivia; Jonsson, Cathrine; Chincarini, Andrea; Frisoni, Giovanni B.; Galluzzi, Samantha; Perneczky, Robert; Drzezga, Alexander; Van Berckel, Bart N.M.; Ossenkoppele, Rik; Didic, Mira; Guedj, Eric; Arnaldi, Dario; Massa, Federico; Grazzini, Matteo; Pardini, Matteo; Mecocci, Patrizia; Dottorini, Massimo E.; Bauckneht, Matteo; Sambuceti, Gianmario; Nobili, Flavio.

In: Journal of Alzheimer's Disease, Vol. 68, No. 1, 01.01.2019, p. 383-394.

Research output: Contribution to journalArticle

Brugnolo, A, De Carli, F, Pagani, M, Morbelli, S, Jonsson, C, Chincarini, A, Frisoni, GB, Galluzzi, S, Perneczky, R, Drzezga, A, Van Berckel, BNM, Ossenkoppele, R, Didic, M, Guedj, E, Arnaldi, D, Massa, F, Grazzini, M, Pardini, M, Mecocci, P, Dottorini, ME, Bauckneht, M, Sambuceti, G & Nobili, F 2019, 'Head-to-Head Comparison among Semi-Quantification Tools of Brain FDG-PET to Aid the Diagnosis of Prodromal Alzheimer's Disease', Journal of Alzheimer's Disease, vol. 68, no. 1, pp. 383-394. https://doi.org/10.3233/JAD-181022
Brugnolo, Andrea ; De Carli, Fabrizio ; Pagani, Marco ; Morbelli, Slivia ; Jonsson, Cathrine ; Chincarini, Andrea ; Frisoni, Giovanni B. ; Galluzzi, Samantha ; Perneczky, Robert ; Drzezga, Alexander ; Van Berckel, Bart N.M. ; Ossenkoppele, Rik ; Didic, Mira ; Guedj, Eric ; Arnaldi, Dario ; Massa, Federico ; Grazzini, Matteo ; Pardini, Matteo ; Mecocci, Patrizia ; Dottorini, Massimo E. ; Bauckneht, Matteo ; Sambuceti, Gianmario ; Nobili, Flavio. / Head-to-Head Comparison among Semi-Quantification Tools of Brain FDG-PET to Aid the Diagnosis of Prodromal Alzheimer's Disease. In: Journal of Alzheimer's Disease. 2019 ; Vol. 68, No. 1. pp. 383-394.
@article{97f555cd11884ebba5d544f06c750532,
title = "Head-to-Head Comparison among Semi-Quantification Tools of Brain FDG-PET to Aid the Diagnosis of Prodromal Alzheimer's Disease",
abstract = "Background: Several automatic tools have been implemented for semi-quantitative assessment of brain [ 18 ]F-FDG-PET. Objective: We aimed to head-to-head compare the diagnostic performance among three statistical parametric mapping (SPM)-based approaches, another voxel-based tool (i.e., PALZ), and a volumetric region of interest (VROI-SVM)-based approach, in distinguishing patients with prodromal Alzheimer's disease (pAD) from controls. Methods: Sixty-two pAD patients (MMSE score = 27.0±1.6) and one hundred-nine healthy subjects (CTR) (MMSE score = 29.2±1.2) were enrolled in five centers of the European Alzheimer's Disease Consortium. The three SPM-based methods, based on different rationales, included 1) a cluster identified through the correlation analysis between [ 18 ]F-FDG-PET and a verbal memory test (VROI-1), 2) a VROI derived from the comparison between pAD and CTR (VROI-2), and 3) visual analysis of individual maps obtained by the comparison between each subject and CTR (SPM-Maps). The VROI-SVM approach was based on 6 VROI plus 6 VROI asymmetry values derived from the pAD versus CTR comparison thanks to support vector machine (SVM). Results: The areas under the ROC curves between pAD and CTR were 0.84 for VROI-1, 0.83 for VROI-2, 0.79 for SPM maps, 0.87 for PALZ, and 0.95 for VROI-SVM. Pairwise comparisons of Youden index did not show statistically significant differences in diagnostic performance between VROI-1, VROI-2, SPM-Maps, and PALZ score whereas VROI-SVM performed significantly (p < 0.005) better than any of the other methods. Conclusion: The study confirms the good accuracy of [ 18 ]F-FDG-PET in discriminating healthy subjects from pAD and highlights that a non-linear, automatic VROI classifier based on SVM performs better than the voxel-based methods.",
keywords = "European Alzheimer Disease Consortium, FDG-PET, head-to-head comparison, prodromal Alzheimer's disease, statistical parametric mapping, volumetric region of interest",
author = "Andrea Brugnolo and {De Carli}, Fabrizio and Marco Pagani and Slivia Morbelli and Cathrine Jonsson and Andrea Chincarini and Frisoni, {Giovanni B.} and Samantha Galluzzi and Robert Perneczky and Alexander Drzezga and {Van Berckel}, {Bart N.M.} and Rik Ossenkoppele and Mira Didic and Eric Guedj and Dario Arnaldi and Federico Massa and Matteo Grazzini and Matteo Pardini and Patrizia Mecocci and Dottorini, {Massimo E.} and Matteo Bauckneht and Gianmario Sambuceti and Flavio Nobili",
year = "2019",
month = "1",
day = "1",
doi = "10.3233/JAD-181022",
language = "English",
volume = "68",
pages = "383--394",
journal = "Journal of Alzheimer's Disease",
issn = "1387-2877",
publisher = "IOS Press",
number = "1",

}

TY - JOUR

T1 - Head-to-Head Comparison among Semi-Quantification Tools of Brain FDG-PET to Aid the Diagnosis of Prodromal Alzheimer's Disease

AU - Brugnolo, Andrea

AU - De Carli, Fabrizio

AU - Pagani, Marco

AU - Morbelli, Slivia

AU - Jonsson, Cathrine

AU - Chincarini, Andrea

AU - Frisoni, Giovanni B.

AU - Galluzzi, Samantha

AU - Perneczky, Robert

AU - Drzezga, Alexander

AU - Van Berckel, Bart N.M.

AU - Ossenkoppele, Rik

AU - Didic, Mira

AU - Guedj, Eric

AU - Arnaldi, Dario

AU - Massa, Federico

AU - Grazzini, Matteo

AU - Pardini, Matteo

AU - Mecocci, Patrizia

AU - Dottorini, Massimo E.

AU - Bauckneht, Matteo

AU - Sambuceti, Gianmario

AU - Nobili, Flavio

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Background: Several automatic tools have been implemented for semi-quantitative assessment of brain [ 18 ]F-FDG-PET. Objective: We aimed to head-to-head compare the diagnostic performance among three statistical parametric mapping (SPM)-based approaches, another voxel-based tool (i.e., PALZ), and a volumetric region of interest (VROI-SVM)-based approach, in distinguishing patients with prodromal Alzheimer's disease (pAD) from controls. Methods: Sixty-two pAD patients (MMSE score = 27.0±1.6) and one hundred-nine healthy subjects (CTR) (MMSE score = 29.2±1.2) were enrolled in five centers of the European Alzheimer's Disease Consortium. The three SPM-based methods, based on different rationales, included 1) a cluster identified through the correlation analysis between [ 18 ]F-FDG-PET and a verbal memory test (VROI-1), 2) a VROI derived from the comparison between pAD and CTR (VROI-2), and 3) visual analysis of individual maps obtained by the comparison between each subject and CTR (SPM-Maps). The VROI-SVM approach was based on 6 VROI plus 6 VROI asymmetry values derived from the pAD versus CTR comparison thanks to support vector machine (SVM). Results: The areas under the ROC curves between pAD and CTR were 0.84 for VROI-1, 0.83 for VROI-2, 0.79 for SPM maps, 0.87 for PALZ, and 0.95 for VROI-SVM. Pairwise comparisons of Youden index did not show statistically significant differences in diagnostic performance between VROI-1, VROI-2, SPM-Maps, and PALZ score whereas VROI-SVM performed significantly (p < 0.005) better than any of the other methods. Conclusion: The study confirms the good accuracy of [ 18 ]F-FDG-PET in discriminating healthy subjects from pAD and highlights that a non-linear, automatic VROI classifier based on SVM performs better than the voxel-based methods.

AB - Background: Several automatic tools have been implemented for semi-quantitative assessment of brain [ 18 ]F-FDG-PET. Objective: We aimed to head-to-head compare the diagnostic performance among three statistical parametric mapping (SPM)-based approaches, another voxel-based tool (i.e., PALZ), and a volumetric region of interest (VROI-SVM)-based approach, in distinguishing patients with prodromal Alzheimer's disease (pAD) from controls. Methods: Sixty-two pAD patients (MMSE score = 27.0±1.6) and one hundred-nine healthy subjects (CTR) (MMSE score = 29.2±1.2) were enrolled in five centers of the European Alzheimer's Disease Consortium. The three SPM-based methods, based on different rationales, included 1) a cluster identified through the correlation analysis between [ 18 ]F-FDG-PET and a verbal memory test (VROI-1), 2) a VROI derived from the comparison between pAD and CTR (VROI-2), and 3) visual analysis of individual maps obtained by the comparison between each subject and CTR (SPM-Maps). The VROI-SVM approach was based on 6 VROI plus 6 VROI asymmetry values derived from the pAD versus CTR comparison thanks to support vector machine (SVM). Results: The areas under the ROC curves between pAD and CTR were 0.84 for VROI-1, 0.83 for VROI-2, 0.79 for SPM maps, 0.87 for PALZ, and 0.95 for VROI-SVM. Pairwise comparisons of Youden index did not show statistically significant differences in diagnostic performance between VROI-1, VROI-2, SPM-Maps, and PALZ score whereas VROI-SVM performed significantly (p < 0.005) better than any of the other methods. Conclusion: The study confirms the good accuracy of [ 18 ]F-FDG-PET in discriminating healthy subjects from pAD and highlights that a non-linear, automatic VROI classifier based on SVM performs better than the voxel-based methods.

KW - European Alzheimer Disease Consortium

KW - FDG-PET

KW - head-to-head comparison

KW - prodromal Alzheimer's disease

KW - statistical parametric mapping

KW - volumetric region of interest

UR - http://www.scopus.com/inward/record.url?scp=85062885225&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062885225&partnerID=8YFLogxK

U2 - 10.3233/JAD-181022

DO - 10.3233/JAD-181022

M3 - Article

AN - SCOPUS:85062885225

VL - 68

SP - 383

EP - 394

JO - Journal of Alzheimer's Disease

JF - Journal of Alzheimer's Disease

SN - 1387-2877

IS - 1

ER -