schliessen

Filtern

 

Bibliotheken

Accuracy and generalization capability of an automatic method for the detection of typical brain hypometabolism in prodromal 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 18 F-fluorodeoxyglucose (FDG) PET data. Methods The SVM model processed metabolic... Full description

Journal Title: European journal of nuclear medicine and molecular imaging 2018-10-31, Vol.46 (2), p.334-347
Main Author: De Carli, Fabrizio
Other Authors: Nobili, Flavio , Pagani, Marco , Bauckneht, Matteo , Massa, Federico , Grazzini, Matteo , Jonsson, Cathrine , Peira, Enrico , Morbelli, Silvia , Arnaldi, Dario
Format: Electronic Article Electronic Article
Language: English
Subjects:
Publisher: Berlin/Heidelberg: Springer Berlin Heidelberg
ID: ISSN: 1619-7070
Link: https://www.ncbi.nlm.nih.gov/pubmed/30382303
Zum Text:
SendSend as email Add to Book BagAdd to Book Bag
Staff View
recordid: cdi_proquest_miscellaneous_2127948918
title: Accuracy and generalization capability of an automatic method for the detection of typical brain hypometabolism in prodromal Alzheimer disease
format: Article
creator:
  • De Carli, Fabrizio
  • Nobili, Flavio
  • Pagani, Marco
  • Bauckneht, Matteo
  • Massa, Federico
  • Grazzini, Matteo
  • Jonsson, Cathrine
  • Peira, Enrico
  • Morbelli, Silvia
  • Arnaldi, Dario
subjects:
  • Accuracy
  • Aged
  • Aging
  • Alzheimer Disease - diagnostic imaging
  • Alzheimer Disease - metabolism
  • Alzheimer's disease
  • Automation
  • Brain
  • Brain - diagnostic imaging
  • Brain - metabolism
  • Cardiology
  • Cerebral hemispheres
  • Cognitive ability
  • Converters
  • Dementia
  • Dementia disorders
  • Female
  • Fluorodeoxyglucose F18
  • Humans
  • Hypometabolism
  • Image Processing, Computer-Assisted
  • Imaging
  • Male
  • Medical imaging
  • Medicine
  • Medicine & Public Health
  • Memory
  • Model accuracy
  • Model testing
  • Neurodegenerative diseases
  • Neuroimaging
  • Neurology
  • Nuclear Medicine
  • Oncology
  • Original Article
  • Orthopedics
  • Patients
  • Positron emission tomography
  • Radiology
  • Reproducibility
  • Subgroups
  • Support Vector Machine
  • Training
ispartof: European journal of nuclear medicine and molecular imaging, 2018-10-31, Vol.46 (2), p.334-347
description: 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 18 F-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.
language: eng
source:
identifier: ISSN: 1619-7070
fulltext: no_fulltext
issn:
  • 1619-7070
  • 1619-7089
url: Link


@attributes
NO1
SEARCH_ENGINEprimo_central_multiple_fe
SEARCH_ENGINE_TYPEPrimo Central Search Engine
RANK2.5705366
LOCALfalse
PrimoNMBib
record
control
sourceidgale_proqu
recordidTN_cdi_proquest_miscellaneous_2127948918
sourceformatXML
sourcesystemPC
galeidA569771885
sourcerecordidA569771885
originalsourceidFETCH-LOGICAL-c382t-8c7007905d6749ad1a59ff2d0616d2139d35d9dc3722175287ea9422f24e7ae40
addsrcrecordideNp1kt9uFSEQxjdGY2vrA3hjSLzxZiuwf4DLk6ZVkybe2GvCgdlzaNhlBfZi-xA-s3N6ahuNhgTIzO_7MgNTVe8YvWCUik-ZUt6pmjJZt0yJWryoTlnPVC2oVC-f7oKeVG9yvqMIcqleVycNbSTH7bT6ubF2ScauxEyO7GCCZIK_N8XHiVgzm60PvqwkDggQs5Q4Ys6SEco-OjLERMoeiIMC9kGDYFlnb00g22T8RPbrHJE22xh8HglG5hRdQp9ANuF-D36ERJzPYDKcV68GEzK8fTzPqtvrq--XX-qbb5-_Xm5uaouFl1pagf0r2rletMo4Zjo1DNzRnvWOs0a5pnPK2UZwzkTHpQCjWs4H3oIw0NKz6uPRF2v5sUAuevTZQghmgrhkzRkXqpWKSUQ__IXexSVNWN0D1UnZyv6Z2pkA2k9DLPiqB1O96XolBJOyQ-riHxQuB6O3cYLBY_wPATsKbIo5Jxj0nPxo0qoZ1YcZ0McZ0Pi1-jADWqDm_WPBy3YE96T4_ekI8COQMTXtID139H_XX-kpvBg
sourcetypeAggregation Database
isCDItrue
recordtypearticle
pqid2127588486
display
typearticle
titleAccuracy and generalization capability of an automatic method for the detection of typical brain hypometabolism in prodromal Alzheimer disease
creatorDe Carli, Fabrizio ; Nobili, Flavio ; Pagani, Marco ; Bauckneht, Matteo ; Massa, Federico ; Grazzini, Matteo ; Jonsson, Cathrine ; Peira, Enrico ; Morbelli, Silvia ; Arnaldi, Dario
creatorcontribDe Carli, Fabrizio ; Nobili, Flavio ; Pagani, Marco ; Bauckneht, Matteo ; Massa, Federico ; Grazzini, Matteo ; Jonsson, Cathrine ; Peira, Enrico ; Morbelli, Silvia ; Arnaldi, Dario ; Alzheimer’s Disease Neuroimaging Initiative ; for the Alzheimer’s Disease Neuroimaging Initiative
descriptionPurpose 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 18 F-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.
identifier
0ISSN: 1619-7070
1EISSN: 1619-7089
2DOI: 10.1007/s00259-018-4197-7
3PMID: 30382303
languageeng
publisherBerlin/Heidelberg: Springer Berlin Heidelberg
subjectAccuracy ; Aged ; Aging ; Alzheimer Disease - diagnostic imaging ; Alzheimer Disease - metabolism ; Alzheimer's disease ; Automation ; Brain ; Brain - diagnostic imaging ; Brain - metabolism ; Cardiology ; Cerebral hemispheres ; Cognitive ability ; Converters ; Dementia ; Dementia disorders ; Female ; Fluorodeoxyglucose F18 ; Humans ; Hypometabolism ; Image Processing, Computer-Assisted ; Imaging ; Male ; Medical imaging ; Medicine ; Medicine & Public Health ; Memory ; Model accuracy ; Model testing ; Neurodegenerative diseases ; Neuroimaging ; Neurology ; Nuclear Medicine ; Oncology ; Original Article ; Orthopedics ; Patients ; Positron emission tomography ; Radiology ; Reproducibility ; Subgroups ; Support Vector Machine ; Training
ispartofEuropean journal of nuclear medicine and molecular imaging, 2018-10-31, Vol.46 (2), p.334-347
rights
0Springer-Verlag GmbH Germany, part of Springer Nature 2018
1COPYRIGHT 2019 Springer
2European Journal of Nuclear Medicine and Molecular Imaging is a copyright of Springer, (2018). All Rights Reserved.
lds50peer_reviewed
citesFETCH-LOGICAL-c382t-8c7007905d6749ad1a59ff2d0616d2139d35d9dc3722175287ea9422f24e7ae40
orcidid0000-0002-1841-5146
links
openurl$$Topenurl_article
thumbnail$$Usyndetics_thumb_exl
backlink$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/30382303$$D View this record in MEDLINE/PubMed
search
creatorcontrib
0De Carli, Fabrizio
1Nobili, Flavio
2Pagani, Marco
3Bauckneht, Matteo
4Massa, Federico
5Grazzini, Matteo
6Jonsson, Cathrine
7Peira, Enrico
8Morbelli, Silvia
9Arnaldi, Dario
10Alzheimer’s Disease Neuroimaging Initiative
11for the Alzheimer’s Disease Neuroimaging Initiative
title
0Accuracy and generalization capability of an automatic method for the detection of typical brain hypometabolism in prodromal Alzheimer disease
1European journal of nuclear medicine and molecular imaging
addtitle
0Eur J Nucl Med Mol Imaging
1Eur J Nucl Med Mol Imaging
descriptionPurpose 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 18 F-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.
subject
0Accuracy
1Aged
2Aging
3Alzheimer Disease - diagnostic imaging
4Alzheimer Disease - metabolism
5Alzheimer's disease
6Automation
7Brain
8Brain - diagnostic imaging
9Brain - metabolism
10Cardiology
11Cerebral hemispheres
12Cognitive ability
13Converters
14Dementia
15Dementia disorders
16Female
17Fluorodeoxyglucose F18
18Humans
19Hypometabolism
20Image Processing, Computer-Assisted
21Imaging
22Male
23Medical imaging
24Medicine
25Medicine & Public Health
26Memory
27Model accuracy
28Model testing
29Neurodegenerative diseases
30Neuroimaging
31Neurology
32Nuclear Medicine
33Oncology
34Original Article
35Orthopedics
36Patients
37Positron emission tomography
38Radiology
39Reproducibility
40Subgroups
41Support Vector Machine
42Training
issn
01619-7070
11619-7089
fulltextfalse
rsrctypearticle
creationdate2018
recordtypearticle
recordideNp1kt9uFSEQxjdGY2vrA3hjSLzxZiuwf4DLk6ZVkybe2GvCgdlzaNhlBfZi-xA-s3N6ahuNhgTIzO_7MgNTVe8YvWCUik-ZUt6pmjJZt0yJWryoTlnPVC2oVC-f7oKeVG9yvqMIcqleVycNbSTH7bT6ubF2ScauxEyO7GCCZIK_N8XHiVgzm60PvqwkDggQs5Q4Ys6SEco-OjLERMoeiIMC9kGDYFlnb00g22T8RPbrHJE22xh8HglG5hRdQp9ANuF-D36ERJzPYDKcV68GEzK8fTzPqtvrq--XX-qbb5-_Xm5uaouFl1pagf0r2rletMo4Zjo1DNzRnvWOs0a5pnPK2UZwzkTHpQCjWs4H3oIw0NKz6uPRF2v5sUAuevTZQghmgrhkzRkXqpWKSUQ__IXexSVNWN0D1UnZyv6Z2pkA2k9DLPiqB1O96XolBJOyQ-riHxQuB6O3cYLBY_wPATsKbIo5Jxj0nPxo0qoZ1YcZ0McZ0Pi1-jADWqDm_WPBy3YE96T4_ekI8COQMTXtID139H_XX-kpvBg
startdate20181031
enddate20181031
creator
0De Carli, Fabrizio
1Nobili, Flavio
2Pagani, Marco
3Bauckneht, Matteo
4Massa, Federico
5Grazzini, Matteo
6Jonsson, Cathrine
7Peira, Enrico
8Morbelli, Silvia
9Arnaldi, Dario
general
0Springer Berlin Heidelberg
1Springer
2Springer Nature B.V
scope
0CGR
1CUY
2CVF
3ECM
4EIF
5NPM
6AAYXX
7CITATION
8BSHEE
93V.
107RV
117TK
127X7
137XB
1488E
158AO
168FE
178FG
188FH
198FI
208FJ
218FK
22ABUWG
23ARAPS
24AZQEC
25BBNVY
26BENPR
27BGLVJ
28BHPHI
29DWQXO
30FYUFA
31GHDGH
32GNUQQ
33HCIFZ
34K9.
35KB0
36LK8
37M0S
38M1P
39M7P
40NAPCQ
41P5Z
42P62
43PQEST
44PQQKQ
45PQUKI
46PRINS
477X8
orcididhttps://orcid.org/0000-0002-1841-5146
sort
creationdate20181031
titleAccuracy and generalization capability of an automatic method for the detection of typical brain hypometabolism in prodromal Alzheimer disease
authorDe Carli, Fabrizio ; Nobili, Flavio ; Pagani, Marco ; Bauckneht, Matteo ; Massa, Federico ; Grazzini, Matteo ; Jonsson, Cathrine ; Peira, Enrico ; Morbelli, Silvia ; Arnaldi, Dario
facets
frbrtype5
frbrgroupidcdi_FETCH-LOGICAL-c382t-8c7007905d6749ad1a59ff2d0616d2139d35d9dc3722175287ea9422f24e7ae40
rsrctypearticles
prefilterarticles
languageeng
creationdate2018
topic
0Accuracy
1Aged
2Aging
3Alzheimer Disease - diagnostic imaging
4Alzheimer Disease - metabolism
5Alzheimer's disease
6Automation
7Brain
8Brain - diagnostic imaging
9Brain - metabolism
10Cardiology
11Cerebral hemispheres
12Cognitive ability
13Converters
14Dementia
15Dementia disorders
16Female
17Fluorodeoxyglucose F18
18Humans
19Hypometabolism
20Image Processing, Computer-Assisted
21Imaging
22Male
23Medical imaging
24Medicine
25Medicine & Public Health
26Memory
27Model accuracy
28Model testing
29Neurodegenerative diseases
30Neuroimaging
31Neurology
32Nuclear Medicine
33Oncology
34Original Article
35Orthopedics
36Patients
37Positron emission tomography
38Radiology
39Reproducibility
40Subgroups
41Support Vector Machine
42Training
toplevelpeer_reviewed
creatorcontrib
0De Carli, Fabrizio
1Nobili, Flavio
2Pagani, Marco
3Bauckneht, Matteo
4Massa, Federico
5Grazzini, Matteo
6Jonsson, Cathrine
7Peira, Enrico
8Morbelli, Silvia
9Arnaldi, Dario
10Alzheimer’s Disease Neuroimaging Initiative
11for the Alzheimer’s Disease Neuroimaging Initiative
collection
0Medline
1MEDLINE
2MEDLINE (Ovid)
3MEDLINE
4MEDLINE
5PubMed
6CrossRef
7Academic OneFile (A&I only)
8ProQuest Central (Corporate)
9Nursing & Allied Health Database
10Neurosciences Abstracts
11Health & Medical Collection
12ProQuest Central (purchase pre-March 2016)
13Medical Database (Alumni Edition)
14ProQuest Pharma Collection
15ProQuest SciTech Collection
16ProQuest Technology Collection
17ProQuest Natural Science Collection
18Hospital Premium Collection
19Hospital Premium Collection (Alumni Edition)
20ProQuest Central (Alumni) (purchase pre-March 2016)
21ProQuest Central (Alumni Edition)
22Advanced Technologies & Aerospace Collection
23ProQuest Central Essentials
24Biological Science Collection
25ProQuest Central
26Technology Collection
27Natural Science Collection
28ProQuest Central Korea
29Health Research Premium Collection
30Health Research Premium Collection (Alumni)
31ProQuest Central Student
32SciTech Premium Collection
33ProQuest Health & Medical Complete (Alumni)
34Nursing & Allied Health Database (Alumni Edition)
35ProQuest Biological Science Collection
36Health & Medical Collection (Alumni Edition)
37Medical Database
38Biological Science Database
39Nursing & Allied Health Premium
40Advanced Technologies & Aerospace Database
41ProQuest Advanced Technologies & Aerospace Collection
42ProQuest One Academic Eastern Edition
43ProQuest One Academic
44ProQuest One Academic UKI Edition
45ProQuest Central China
46MEDLINE - Academic
jtitleEuropean journal of nuclear medicine and molecular imaging
delivery
delcategoryRemote Search Resource
fulltextno_fulltext
addata
au
0De Carli, Fabrizio
1Nobili, Flavio
2Pagani, Marco
3Bauckneht, Matteo
4Massa, Federico
5Grazzini, Matteo
6Jonsson, Cathrine
7Peira, Enrico
8Morbelli, Silvia
9Arnaldi, Dario
aucorp
0Alzheimer’s Disease Neuroimaging Initiative
1for the Alzheimer’s Disease Neuroimaging Initiative
formatjournal
genrearticle
ristypeJOUR
atitleAccuracy and generalization capability of an automatic method for the detection of typical brain hypometabolism in prodromal Alzheimer disease
jtitleEuropean journal of nuclear medicine and molecular imaging
stitleEur J Nucl Med Mol Imaging
addtitleEur J Nucl Med Mol Imaging
date2018-10-31
risdate2018
volume46
issue2
spage334
epage347
pages334-347
issn1619-7070
eissn1619-7089
abstractPurpose 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 18 F-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.
copBerlin/Heidelberg
pubSpringer Berlin Heidelberg
pmid30382303
doi10.1007/s00259-018-4197-7
orcididhttps://orcid.org/0000-0002-1841-5146