Gaussian Mixture Models and Model Selection for [18F] Fluorodeoxyglucose Positron Emission Tomography Classification in Alzheimer's Disease.

We present a method to discover discriminative brain metabolism patterns in [18F] fluorodeoxyglucose positron emission tomography (PET) scans, facilitating the clinical diagnosis of Alzheimer's disease. In the work, the term "pattern" stands for a certain brain region that characteriz...

Full description

Saved in:
Bibliographic Details
Main Authors: Rui Li, Robert Perneczky, Igor Yakushev, Stefan Förster, Alexander Kurz, Alexander Drzezga, Stefan Kramer, Alzheimer’s Disease Neuroimaging Initiative
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2014-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0122731
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850125480898854912
author Rui Li
Robert Perneczky
Igor Yakushev
Stefan Förster
Alexander Kurz
Alexander Drzezga
Stefan Kramer
Alzheimer’s Disease Neuroimaging Initiative
author_facet Rui Li
Robert Perneczky
Igor Yakushev
Stefan Förster
Alexander Kurz
Alexander Drzezga
Stefan Kramer
Alzheimer’s Disease Neuroimaging Initiative
author_sort Rui Li
collection DOAJ
description We present a method to discover discriminative brain metabolism patterns in [18F] fluorodeoxyglucose positron emission tomography (PET) scans, facilitating the clinical diagnosis of Alzheimer's disease. In the work, the term "pattern" stands for a certain brain region that characterizes a target group of patients and can be used for a classification as well as interpretation purposes. Thus, it can be understood as a so-called "region of interest (ROI)". In the literature, an ROI is often found by a given brain atlas that defines a number of brain regions, which corresponds to an anatomical approach. The present work introduces a semi-data-driven approach that is based on learning the characteristics of the given data, given some prior anatomical knowledge. A Gaussian Mixture Model (GMM) and model selection are combined to return a clustering of voxels that may serve for the definition of ROIs. Experiments on both an in-house dataset and data of the Alzheimer's Disease Neuroimaging Initiative (ADNI) suggest that the proposed approach arrives at a better diagnosis than a merely anatomical approach or conventional statistical hypothesis testing.
format Article
id doaj-art-57fdbafe1d6c4b2fbe1b23067086565c
institution OA Journals
issn 1932-6203
language English
publishDate 2014-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-57fdbafe1d6c4b2fbe1b23067086565c2025-08-20T02:34:07ZengPublic Library of Science (PLoS)PLoS ONE1932-62032014-01-01104e012273110.1371/journal.pone.0122731Gaussian Mixture Models and Model Selection for [18F] Fluorodeoxyglucose Positron Emission Tomography Classification in Alzheimer's Disease.Rui LiRobert PerneczkyIgor YakushevStefan FörsterAlexander KurzAlexander DrzezgaStefan KramerAlzheimer’s Disease Neuroimaging InitiativeWe present a method to discover discriminative brain metabolism patterns in [18F] fluorodeoxyglucose positron emission tomography (PET) scans, facilitating the clinical diagnosis of Alzheimer's disease. In the work, the term "pattern" stands for a certain brain region that characterizes a target group of patients and can be used for a classification as well as interpretation purposes. Thus, it can be understood as a so-called "region of interest (ROI)". In the literature, an ROI is often found by a given brain atlas that defines a number of brain regions, which corresponds to an anatomical approach. The present work introduces a semi-data-driven approach that is based on learning the characteristics of the given data, given some prior anatomical knowledge. A Gaussian Mixture Model (GMM) and model selection are combined to return a clustering of voxels that may serve for the definition of ROIs. Experiments on both an in-house dataset and data of the Alzheimer's Disease Neuroimaging Initiative (ADNI) suggest that the proposed approach arrives at a better diagnosis than a merely anatomical approach or conventional statistical hypothesis testing.https://doi.org/10.1371/journal.pone.0122731
spellingShingle Rui Li
Robert Perneczky
Igor Yakushev
Stefan Förster
Alexander Kurz
Alexander Drzezga
Stefan Kramer
Alzheimer’s Disease Neuroimaging Initiative
Gaussian Mixture Models and Model Selection for [18F] Fluorodeoxyglucose Positron Emission Tomography Classification in Alzheimer's Disease.
PLoS ONE
title Gaussian Mixture Models and Model Selection for [18F] Fluorodeoxyglucose Positron Emission Tomography Classification in Alzheimer's Disease.
title_full Gaussian Mixture Models and Model Selection for [18F] Fluorodeoxyglucose Positron Emission Tomography Classification in Alzheimer's Disease.
title_fullStr Gaussian Mixture Models and Model Selection for [18F] Fluorodeoxyglucose Positron Emission Tomography Classification in Alzheimer's Disease.
title_full_unstemmed Gaussian Mixture Models and Model Selection for [18F] Fluorodeoxyglucose Positron Emission Tomography Classification in Alzheimer's Disease.
title_short Gaussian Mixture Models and Model Selection for [18F] Fluorodeoxyglucose Positron Emission Tomography Classification in Alzheimer's Disease.
title_sort gaussian mixture models and model selection for 18f fluorodeoxyglucose positron emission tomography classification in alzheimer s disease
url https://doi.org/10.1371/journal.pone.0122731
work_keys_str_mv AT ruili gaussianmixturemodelsandmodelselectionfor18ffluorodeoxyglucosepositronemissiontomographyclassificationinalzheimersdisease
AT robertperneczky gaussianmixturemodelsandmodelselectionfor18ffluorodeoxyglucosepositronemissiontomographyclassificationinalzheimersdisease
AT igoryakushev gaussianmixturemodelsandmodelselectionfor18ffluorodeoxyglucosepositronemissiontomographyclassificationinalzheimersdisease
AT stefanforster gaussianmixturemodelsandmodelselectionfor18ffluorodeoxyglucosepositronemissiontomographyclassificationinalzheimersdisease
AT alexanderkurz gaussianmixturemodelsandmodelselectionfor18ffluorodeoxyglucosepositronemissiontomographyclassificationinalzheimersdisease
AT alexanderdrzezga gaussianmixturemodelsandmodelselectionfor18ffluorodeoxyglucosepositronemissiontomographyclassificationinalzheimersdisease
AT stefankramer gaussianmixturemodelsandmodelselectionfor18ffluorodeoxyglucosepositronemissiontomographyclassificationinalzheimersdisease
AT alzheimersdiseaseneuroimaginginitiative gaussianmixturemodelsandmodelselectionfor18ffluorodeoxyglucosepositronemissiontomographyclassificationinalzheimersdisease