Andrea Brugnolo1,2, Fabrizio De Carli3, Marco Pagani4,5, Slivia Morbelli6,7, Cathrine Jonsson8, Andrea Chincarini9, Giovanni B Frisoni10,11, Samantha Galluzzi10, Robert Perneczky12,13,14,15, Alexander Drzezga16, Bart N M van Berckel17, Rik Ossenkoppele17, Mira Didic18, Eric Guedj19, Dario Arnaldi1,20, Federico Massa1, Matteo Grazzini1, Matteo Pardini1,20, Patrizia Mecocci21, Massimo E Dottorini22, Matteo Bauckneht6,7, Gianmario Sambuceti6,7, Flavio Nobili1,20. 1. Department of Neuroscience, Rehabilitation, Ophthalmology, Genetics, and Mother-Child health (DINOGMI), University of Genoa, Italy. 2. Clinical Psychology Unit, IRCCS Ospedale Policlinico San Martino, Genoa, Italy. 3. Institute of Bioimaging and Molecular Physiology, Consiglio Nazionale delle Ricerche (CNR), Genoa, Italy. 4. Institute of Cognitive Sciences and Technologies, Consiglio Nazionale delle Ricerche (CNR), Rome, Italy. 5. Department of Nuclear Medicine, Karolinska Hospital, Stockholm, Sweden. 6. Department of Health Sciences (DISSAL), University of Genoa, Italy. 7. Nuclear Medicine Unit, IRCCS Ospedale Policlinico San Martino, Genoa, Italy. 8. Medical Radiation Physics and Nuclear Medicine, Imaging and Physiology, Karolinska University Hospital, Stockholm, Sweden. 9. National Institute for Nuclear Physics (INFN), Genoa, Italy. 10. LENITEM Laboratory of Epidemiology and Neuroimaging, IRCCS S. Giovanni di Dio-FBF, Brescia, Italy. 11. University Hospitals and University of Geneva, Geneva, Switzerland. 12. Department of Psychiatry and Psychotherapy, University Hospital, LMU Munich, Germany. 13. Department of Psychiatry and Psychotherapy, Technische Universität München, Munich, Germany. 14. German Center for Neurodegenerative Diseases (DZNE) Munich, Germany. 15. Neuroepidemiology and Ageing Research Unit, School of Public Health, Faculty of Medicine, The Imperial College London of Science, Technology and Medicine, London, UK. 16. Department of Nuclear Medicine, University Hospital of Cologne, Germany; previously at Department of Nuclear Medicine, Technische Universität, Munich, Germany. 17. Department of Nuclear Medicine & PET Research, VU University Medical Center, Amsterdam, The Netherlands. 18. APHM, CHU Timone, Service de Neurologie et Neuropsychologie, Aix-Marseille University, Marseille, France. 19. APHM, CHU Timone, Service de Médecine Nucléaire, CERIMED, Institut Fresnel, CNRS, Ecole Centrale Marseille, Aix-Marseille University, France. 20. Neurology Clinics, IRCCS Ospedale Policlinico San Martino, Genoa, Italy. 21. Section of Gerontology and Geriatrics, University of Perugia, Perugia, Italy. 22. Department of Diagnostic Imaging, Nuclear Medicine Unit, Perugia General Hospital, Perugia, Italy.
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.
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 pADpatients (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.
Entities:
Keywords:
European Alzheimer Disease Consortium; FDG-PET; head-to-head comparison; prodromal Alzheimer’s disease; statistical parametric mapping; volumetric region of interest
Authors: Annika Kreuzer; Julia Sauerbeck; Maximilian Scheifele; Anna Stockbauer; Sonja Schönecker; Catharina Prix; Elisabeth Wlasich; Sandra V Loosli; Philipp M Kazmierczak; Marcus Unterrainer; Cihan Catak; Daniel Janowitz; Oliver Pogarell; Carla Palleis; Robert Perneczky; Nathalie L Albert; Peter Bartenstein; Adrian Danek; Katharina Buerger; Johannes Levin; Andreas Zwergal; Axel Rominger; Matthias Brendel; Leonie Beyer Journal: Front Aging Neurosci Date: 2021-02-02 Impact factor: 5.750