Classification of neurodegenerative dementia by Gaussian Mixture Models applied to SPECT images

Stühler, Elisabeth; Platsch, Günther; Weih, Markus; Kornhuber, Johannes; Kuwert, Torsten; Merhof, Dorit

Classification of neurodegenerative dementia by Gaussian Mixture Models applied to SPECT images

Dateien

Zu diesem Dokument gibt es keine Dateien.

Datum

2012

Autor:innen

Stühler, Elisabeth

Platsch, Günther

Weih, Markus

Kornhuber, Johannes

Kuwert, Torsten

Merhof, Dorit

Publikationstyp

Beitrag zu einem Konferenzband

unikn.publication.listelement.citation.prefix.version.undefined

2012 IEEE Nuclear Science Symposium and Medical Imaging Conference Record (NSS/MIC). IEEE, 2012, pp. 3165-3169. ISBN 978-1-4673-2028-3. Available under: doi: 10.1109/NSSMIC.2012.6551722

Zusammenfassung

Gaussian mixture (GM) models can be applied for statistical classification of various types of dementia. As opposed to linear boundaries, they do not only provide the class membership of a case, but also a measure of its probability. This enables an improved interpretation and classification of neurodegenerative dementia datasets which comprise various stages of the disease, and also mixed forms of dementia. In this work, GM models are applied to a total number of 103 technetium-99methylcysteinatedimer (99mTc-ECD) SPECT datasets of asymptomatic controls (CTR), as well as Alzheimer’s disease (AD) and frontotemporal dementia (FTD) patients in early or moderate stages of the disease. Prior to classification, multivariate analysis is applied: Principal component analysis (PCA) is used for dimensionality reduction, followed by a differentiation of the datasets via multiple discriminant analysis (MDA). A GM model on the resulting discrimination plane is constructed by computing the GM distribution associated with the underlying training set. The posterior probabilities of each case indicate its class membership probability. The performance of GM models for classification is assessed by bootstrap resampling and cross validation. Accuracy and robustness of the method are evaluated for different numbers of principal components (PCs), and furthermore the detection rate of dementia in early stages is calculated. The GM model outperfomes classification with linear boundaries in both predicted accuracy and detection rate of early dementia, and is equally robust.

Fachgebiet (DDC)

004 Informatik

Schlagwörter

SPECT, Alzheimer’s Disease, Frontotemporal Dementia, Multivariate Analysis, Gaussian Mixture Model, Probabilistic Classification

Konferenz

2012 IEEE Nuclear Science Symposium and Medical Imaging Conference (2012 NSS/MIC), 27. Okt. 2012 - 3. Nov. 2012, Anaheim, CA, USA

Zitieren

ISO 690

STÜHLER, Elisabeth, Günther PLATSCH, Markus WEIH, Johannes KORNHUBER, Torsten KUWERT, Dorit MERHOF, 2012. Classification of neurodegenerative dementia by Gaussian Mixture Models applied to SPECT images. 2012 IEEE Nuclear Science Symposium and Medical Imaging Conference (2012 NSS/MIC). Anaheim, CA, USA, 27. Okt. 2012 - 3. Nov. 2012. In: 2012 IEEE Nuclear Science Symposium and Medical Imaging Conference Record (NSS/MIC). IEEE, 2012, pp. 3165-3169. ISBN 978-1-4673-2028-3. Available under: doi: 10.1109/NSSMIC.2012.6551722

BibTex

@inproceedings{Stuhler2012-10Class-21451,
  year={2012},
  doi={10.1109/NSSMIC.2012.6551722},
  title={Classification of neurodegenerative dementia by Gaussian Mixture Models applied to SPECT images},
  isbn={978-1-4673-2028-3},
  publisher={IEEE},
  booktitle={2012 IEEE Nuclear Science Symposium and Medical Imaging Conference Record (NSS/MIC)},
  pages={3165--3169},
  author={Stühler, Elisabeth and Platsch, Günther and Weih, Markus and Kornhuber, Johannes and Kuwert, Torsten and Merhof, Dorit}
}

RDF

<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/21451">
    <dcterms:issued>2012-10</dcterms:issued>
    <dc:contributor>Kornhuber, Johannes</dc:contributor>
    <dcterms:bibliographicCitation>2012 IEEE Nuclear Science Symposium and Medical Imaging Conference : (NSS/MIC 2012) ; October 29 - November 3, 2012, Disneyland Hotel, Anaheim, California ; and International Workshop on Room-Temperature Semiconductor X-ray and Gamma-ray Detectors / Yu, Bo [Guest Ed.]. - Piscataway, NJ : IEEE, 2012. - S. 3165-3169. - ISBN 978-1-4673-2029-0</dcterms:bibliographicCitation>
    <dc:rights>terms-of-use</dc:rights>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2013-02-26T11:00:14Z</dcterms:available>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>Weih, Markus</dc:contributor>
    <dc:language>eng</dc:language>
    <dcterms:title>Classification of neurodegenerative dementia by Gaussian Mixture Models applied to SPECT images</dcterms:title>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2013-02-26T11:00:14Z</dc:date>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:creator>Platsch, Günther</dc:creator>
    <dc:creator>Weih, Markus</dc:creator>
    <dc:contributor>Merhof, Dorit</dc:contributor>
    <dc:creator>Kornhuber, Johannes</dc:creator>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:creator>Stühler, Elisabeth</dc:creator>
    <dcterms:abstract xml:lang="eng">Gaussian mixture (GM) models can be applied for statistical classification of various types of dementia. As opposed to linear boundaries, they do not only provide the class membership of a case, but also a measure of its probability. This enables an improved interpretation and classification of neurodegenerative dementia datasets which comprise various stages of the disease, and also mixed forms of dementia. In this work, GM models are applied to a total number of 103 technetium-99methylcysteinatedimer (99mTc-ECD) SPECT datasets of asymptomatic controls (CTR), as well as Alzheimer’s disease (AD) and frontotemporal dementia (FTD) patients in early or moderate stages of the disease. Prior to classification, multivariate analysis is applied: Principal component analysis (PCA) is used for dimensionality reduction, followed by a differentiation of the datasets via multiple discriminant analysis (MDA). A GM model on the resulting discrimination plane is constructed by computing the GM distribution associated with the underlying training set. The posterior probabilities of each case indicate its class membership probability. The performance of GM models for classification is assessed by bootstrap resampling and cross validation. Accuracy and robustness of the method are evaluated for different numbers of principal components (PCs), and furthermore the detection rate of dementia in early stages is calculated. The GM model outperfomes classification with linear boundaries in both predicted accuracy and detection rate of early dementia, and is equally robust.</dcterms:abstract>
    <dc:contributor>Kuwert, Torsten</dc:contributor>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:contributor>Stühler, Elisabeth</dc:contributor>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dc:contributor>Platsch, Günther</dc:contributor>
    <dc:creator>Kuwert, Torsten</dc:creator>
    <bibo:uri rdf:resource="http://kops.uni-konstanz.de/handle/123456789/21451"/>
    <dc:creator>Merhof, Dorit</dc:creator>
  </rdf:Description>
</rdf:RDF>

Universitätsbibliographie

Ja