A comparison of accurate automatic hippocampal segmentation methods

2017
Authors
Zandifar, Azar
Coupé, Pierrick
Collins, D. Louis
Journal article
Published
Published in
NeuroImage ; 155 (2017). - pp. 383-393. - ISSN 1053-8119. - eISSN 1095-9572
Abstract
The hippocampus is one of the first brain structures affected by Alzheimer's disease (AD). While many automatic methods for hippocampal segmentation exist, few studies have compared them on the same data. In this study, we compare four fully automated hippocampal segmentation methods in terms of their conformity with manual segmentation and their ability to be used as an AD biomarker in clinical settings. We also apply error correction to the four automatic segmentation methods, and complete a comprehensive validation to investigate differences between the methods. The effect size and classification performance is measured for AD versus normal control (NC) groups and for stable mild cognitive impairment (sMCI) versus progressive mild cognitive impairment (pMCI) groups. Our study shows that the nonlinear patch-based segmentation method with error correction is the most accurate automatic segmentation method and yields the most conformity with manual segmentation (κ=0.894). The largest effect size between AD versus NC and sMCI versus pMCI is produced by FreeSurfer with error correction. We further show that, using only hippocampal volume, age, and sex as features, the area under the receiver operating characteristic curve reaches up to 0.8813 for AD versus NC and 0.6451 for sMCI versus pMCI. However, the automatic segmentation methods are not significantly different in their performance.
150 Psychology
Keywords
Hippocampal segmentation; Alzheimer's disease; Dice's κ; Cohen's d; Area under receiver operating characteristic curve
Cite This
ISO 690ZANDIFAR, Azar, Vladimir FONOV, Pierrick COUPÉ, Jens C. PRUESSNER, D. Louis COLLINS, 2017. A comparison of accurate automatic hippocampal segmentation methods. In: NeuroImage. 155, pp. 383-393. ISSN 1053-8119. eISSN 1095-9572. Available under: doi: 10.1016/j.neuroimage.2017.04.018
BibTex
@article{Zandifar2017-07-15compa-41155,
year={2017},
doi={10.1016/j.neuroimage.2017.04.018},
title={A comparison of accurate automatic hippocampal segmentation methods},
volume={155},
issn={1053-8119},
journal={NeuroImage},
pages={383--393},
author={Zandifar, Azar and Fonov, Vladimir and Coupé, Pierrick and Pruessner, Jens C. and Collins, D. Louis}
}

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#" >
<dc:language>eng</dc:language>
<dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2018-01-25T10:13:48Z</dcterms:available>
<dc:contributor>Collins, D. Louis</dc:contributor>
<dcterms:title>A comparison of accurate automatic hippocampal segmentation methods</dcterms:title>
<dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/43"/>
<dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/41155/1/Zandifar_2-skvhn40sgzrz5.pdf"/>
<dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/41155/1/Zandifar_2-skvhn40sgzrz5.pdf"/>
<dc:creator>Zandifar, Azar</dc:creator>
<dc:rights>terms-of-use</dc:rights>
<void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
<dcterms:issued>2017-07-15</dcterms:issued>
<dc:contributor>Zandifar, Azar</dc:contributor>
<dc:contributor>Pruessner, Jens C.</dc:contributor>
<dc:creator>Pruessner, Jens C.</dc:creator>
<bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/41155"/>
<dc:creator>Collins, D. Louis</dc:creator>
<dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/43"/>
<foaf:homepage rdf:resource="http://localhost:8080/"/>
<dc:creator>Coupé, Pierrick</dc:creator>
<dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2018-01-25T10:13:48Z</dc:date>
<dc:contributor>Coupé, Pierrick</dc:contributor>
<dcterms:abstract xml:lang="eng">The hippocampus is one of the first brain structures affected by Alzheimer's disease (AD). While many automatic methods for hippocampal segmentation exist, few studies have compared them on the same data. In this study, we compare four fully automated hippocampal segmentation methods in terms of their conformity with manual segmentation and their ability to be used as an AD biomarker in clinical settings. We also apply error correction to the four automatic segmentation methods, and complete a comprehensive validation to investigate differences between the methods. The effect size and classification performance is measured for AD versus normal control (NC) groups and for stable mild cognitive impairment (sMCI) versus progressive mild cognitive impairment (pMCI) groups. Our study shows that the nonlinear patch-based segmentation method with error correction is the most accurate automatic segmentation method and yields the most conformity with manual segmentation (κ=0.894). The largest effect size between AD versus NC and sMCI versus pMCI is produced by FreeSurfer with error correction. We further show that, using only hippocampal volume, age, and sex as features, the area under the receiver operating characteristic curve reaches up to 0.8813 for AD versus NC and 0.6451 for sMCI versus pMCI. However, the automatic segmentation methods are not significantly different in their performance.</dcterms:abstract>
<dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
</rdf:Description>
</rdf:RDF>

Yes