Fabrizio De Carli1, Flavio Nobili2, Marco Pagani3,4, Matteo Bauckneht5,6, Federico Massa2, Matteo Grazzini2, Cathrine Jonsson4, Enrico Peira7, Silvia Morbelli5,6, Dario Arnaldi2. 1. Institute of Molecular Bioimaging and Physiology, National Research Council, Largo Paolo Daneo, 3, 16132, Genoa, Italy. f.decarli@ibfm.cnr.it. 2. Department of Neuroscience (DINOGMI), IRCCS Polyclinic San Martino-IST, University of Genoa, Genoa, Italy. 3. Institute of Cognitive Sciences and Technologies, CNR, Rome, Italy. 4. Medical Radiation Physics and Nuclear Medicine, Imaging and Physiology, Karolinska University Hospital, Stockholm, Sweden. 5. Department of Health Sciences (DISSAL), University of Genoa, Genoa, Italy. 6. Nuclear Medicine Unit, Polyclinic San Martino Hospital, Genoa, Italy. 7. National Institute of Nuclear Physics (INFN), Genoa, Italy.
Abstract
PURPOSE: The aim of this study was to verify the reliability and generalizability of an automatic tool for the detection of Alzheimer-related hypometabolic pattern based on a Support-Vector-Machine (SVM) model analyzing 18F-fluorodeoxyglucose (FDG) PET data. METHODS: The SVM model processed metabolic data from anatomical volumes of interest also considering interhemispheric asymmetries. It was trained on a homogeneous dataset from a memory clinic center and tested on an independent multicentric dataset drawn from the Alzheimer's Disease Neuroimaging Initiative. Subjects were included in the study and classified based on a diagnosis confirmed after an adequate follow-up time. RESULTS: The accuracy of the discrimination between patients with Alzheimer Disease (AD), in either prodromal or dementia stage, and normal aging subjects was 95.8%, after cross-validation, in the training set. The accuracy of the same model in the testing set was 86.5%. The role of the two datasets was then reversed, and the accuracy was 89.8% in the multicentric training set and 88.0% in the monocentric testing set. The classification rate was also evaluated in different subgroups, including non-converter mild cognitive impairment (MCI) patients, subjects with MCI reverted to normal conditions and subjects with non-confirmed memory concern. The percent of pattern detections increased from 77% in early prodromal AD to 91% in AD dementia, while it was about 10% for healthy controls and non-AD patients. CONCLUSIONS: The present findings show a good level of reproducibility and generalizability of a model for detecting the hypometabolic pattern in AD and confirm the accuracy of FDG-PET in Alzheimer disease.
PURPOSE: The aim of this study was to verify the reliability and generalizability of an automatic tool for the detection of Alzheimer-related hypometabolic pattern based on a Support-Vector-Machine (SVM) model analyzing 18F-fluorodeoxyglucose (FDG) PET data. METHODS: The SVM model processed metabolic data from anatomical volumes of interest also considering interhemispheric asymmetries. It was trained on a homogeneous dataset from a memory clinic center and tested on an independent multicentric dataset drawn from the Alzheimer's Disease Neuroimaging Initiative. Subjects were included in the study and classified based on a diagnosis confirmed after an adequate follow-up time. RESULTS: The accuracy of the discrimination between patients with Alzheimer Disease (AD), in either prodromal or dementia stage, and normal aging subjects was 95.8%, after cross-validation, in the training set. The accuracy of the same model in the testing set was 86.5%. The role of the two datasets was then reversed, and the accuracy was 89.8% in the multicentric training set and 88.0% in the monocentric testing set. The classification rate was also evaluated in different subgroups, including non-converter mild cognitive impairment (MCI) patients, subjects with MCI reverted to normal conditions and subjects with non-confirmed memory concern. The percent of pattern detections increased from 77% in early prodromal AD to 91% in AD dementia, while it was about 10% for healthy controls and non-ADpatients. CONCLUSIONS: The present findings show a good level of reproducibility and generalizability of a model for detecting the hypometabolic pattern in AD and confirm the accuracy of FDG-PET in Alzheimer disease.
Entities:
Keywords:
Alzheimer disease; Classification and prediction; Discriminant analysis; FDG-PET; MCI due to AD; Neurodegenerative disorders; Neuroimage classification; Support vector machine
Authors: Guy M McKhann; David S Knopman; Howard Chertkow; Bradley T Hyman; Clifford R Jack; Claudia H Kawas; William E Klunk; Walter J Koroshetz; Jennifer J Manly; Richard Mayeux; Richard C Mohs; John C Morris; Martin N Rossor; Philip Scheltens; Maria C Carrillo; Bill Thies; Sandra Weintraub; Creighton H Phelps Journal: Alzheimers Dement Date: 2011-04-21 Impact factor: 21.566
Authors: Jerod M Rasmussen; Anita Lakatos; Theo G M van Erp; Frithjof Kruggel; David B Keator; James T Fallon; Fabio Macciardi; Steven G Potkin Journal: Biochim Biophys Acta Date: 2011-09-19
Authors: Roland Zahn; Freimut Juengling; Philine Bubrowski; Elke Jost; Petra Dykierek; Jochen Talazko; Michael Huell Journal: Psychiatry Res Date: 2004-12-15 Impact factor: 3.222
Authors: Silvia Morbelli; Alex Drzezga; Robert Perneczky; Giovanni B Frisoni; Anna Caroli; Bart N M van Berckel; Rik Ossenkoppele; Eric Guedj; Mira Didic; Andrea Brugnolo; Gianmario Sambuceti; Marco Pagani; Eric Salmon; Flavio Nobili Journal: Neurobiol Aging Date: 2012-02-23 Impact factor: 4.673
Authors: Richard J Kryscio; Erin L Abner; Gregory E Cooper; David W Fardo; Gregory A Jicha; Peter T Nelson; Charles D Smith; Linda J Van Eldik; Lijie Wan; Frederick A Schmitt Journal: Neurology Date: 2014-09-24 Impact factor: 9.910
Authors: M Signorini; E Paulesu; K Friston; D Perani; A Colleluori; G Lucignani; F Grassi; V Bettinardi; R S Frackowiak; F Fazio Journal: Neuroimage Date: 1999-01 Impact factor: 6.556
Authors: Jeremy N Ford; Elizabeth M Sweeney; Myrto Skafida; Shannon Glynn; Michael Amoashiy; Dale J Lange; Eaton Lin; Gloria C Chiang; Joseph R Osborne; Silky Pahlajani; Mony J de Leon; Jana Ivanidze Journal: Am J Nucl Med Mol Imaging Date: 2021-08-15