Deep assessment process : Objective assessment process for unilateral peripheral facial paralysis via deep convolutional neural network

Guo, Zhe-Xiao; Shen, Minmin; Duan, Le; Zhou, Yongjin; Xiang, Jianghuai; Ding, Huijun; Chen, Shifeng; Deussen, Oliver; Dan, Guo

Deep assessment process : Objective assessment process for unilateral peripheral facial paralysis via deep convolutional neural network

Files

There are no files associated with this item.

Date

2017

Authors

Guo, Zhe-Xiao

Shen, Minmin

Duan, Le

Zhou, Yongjin

Xiang, Jianghuai

Ding, Huijun

Chen, Shifeng

Deussen, Oliver

Dan, Guo

DOI (citable link)

10.1109/ISBI.2017.7950486

Collections

Informatik und Informationswissenschaft
Zukunftskolleg

Publication type

Contribution to a conference collection

Publication status

Published

Published in

2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017) : From Nano to Macro. - Piscataway, NJ : IEEE, 2017. - pp. 135-138. - eISSN 1945-8452. - ISBN 978-1-5090-1172-8

Abstract

Unilateral peripheral facial paralysis (UPFP) is a form of facial nerve paralysis and clinically classified according to facial asymmetry. Prompt and precise assessment is crucial to the neural rehabilitation of UPFP. For UPFP assessment, most of the existing assessment systems are subjective and empirical. Therefore, an objective assessment system will help clinical doctors to obtain a prompt and precise assessment. Distinguishing precisely between degrees of asymmetry is hard using pure pattern recognition methods. Thus, a novel objective assessment process based on convolutional neuronal networks is proposed in this paper that provides an end-to-end solution. This method could alleviate the problem and produced a classification accuracy of 91.25% for predicting the House-Brackmann degree on a given UPFP image dataset.

Subject (DDC)

004 Computer Science

Keywords

Unilateral peripheral facial paralysis, objective assessment process, deep convolutional neural network, House-Brackmann facial nerve grading system

Conference

2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), Apr 18, 2017 - Apr 21, 2017, Melbourne, Australia

Cite This

ISO 690

GUO, Zhe-Xiao, Minmin SHEN, Le DUAN, Yongjin ZHOU, Jianghuai XIANG, Huijun DING, Shifeng CHEN, Oliver DEUSSEN, Guo DAN, 2017. Deep assessment process : Objective assessment process for unilateral peripheral facial paralysis via deep convolutional neural network. 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017). Melbourne, Australia, Apr 18, 2017 - Apr 21, 2017. In: 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017) : From Nano to Macro. Piscataway, NJ:IEEE, pp. 135-138. eISSN 1945-8452. ISBN 978-1-5090-1172-8. Available under: doi: 10.1109/ISBI.2017.7950486

BibTex

@inproceedings{Guo2017-04asses-39638,
  year={2017},
  doi={10.1109/ISBI.2017.7950486},
  title={Deep assessment process : Objective assessment process for unilateral peripheral facial paralysis via deep convolutional neural network},
  isbn={978-1-5090-1172-8},
  publisher={IEEE},
  address={Piscataway, NJ},
  booktitle={2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017) : From Nano to Macro},
  pages={135--138},
  author={Guo, Zhe-Xiao and Shen, Minmin and Duan, Le and Zhou, Yongjin and Xiang, Jianghuai and Ding, Huijun and Chen, Shifeng and Deussen, Oliver and Dan, Guo}
}

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/123456789/39638">
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/52"/>
    <dc:contributor>Deussen, Oliver</dc:contributor>
    <dc:creator>Ding, Huijun</dc:creator>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:language>eng</dc:language>
    <dc:contributor>Xiang, Jianghuai</dc:contributor>
    <dc:creator>Dan, Guo</dc:creator>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/52"/>
    <dcterms:issued>2017-04</dcterms:issued>
    <dc:contributor>Duan, Le</dc:contributor>
    <dc:creator>Zhou, Yongjin</dc:creator>
    <dc:contributor>Shen, Minmin</dc:contributor>
    <dc:creator>Duan, Le</dc:creator>
    <dc:creator>Chen, Shifeng</dc:creator>
    <dc:creator>Xiang, Jianghuai</dc:creator>
    <dc:contributor>Dan, Guo</dc:contributor>
    <dc:creator>Guo, Zhe-Xiao</dc:creator>
    <dc:contributor>Chen, Shifeng</dc:contributor>
    <dc:contributor>Zhou, Yongjin</dc:contributor>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:creator>Shen, Minmin</dc:creator>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2017-07-21T12:43:48Z</dc:date>
    <dcterms:title>Deep assessment process : Objective assessment process for unilateral peripheral facial paralysis via deep convolutional neural network</dcterms:title>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/39638"/>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2017-07-21T12:43:48Z</dcterms:available>
    <dc:creator>Deussen, Oliver</dc:creator>
    <dcterms:abstract xml:lang="eng">Unilateral peripheral facial paralysis (UPFP) is a form of facial nerve paralysis and clinically classified according to facial asymmetry. Prompt and precise assessment is crucial to the neural rehabilitation of UPFP. For UPFP assessment, most of the existing assessment systems are subjective and empirical. Therefore, an objective assessment system will help clinical doctors to obtain a prompt and precise assessment. Distinguishing precisely between degrees of asymmetry is hard using pure pattern recognition methods. Thus, a novel objective assessment process based on convolutional neuronal networks is proposed in this paper that provides an end-to-end solution. This method could alleviate the problem and produced a classification accuracy of 91.25% for predicting the House-Brackmann degree on a given UPFP image dataset.</dcterms:abstract>
    <dc:contributor>Guo, Zhe-Xiao</dc:contributor>
    <dc:contributor>Ding, Huijun</dc:contributor>
  </rdf:Description>
</rdf:RDF>

Bibliography of Konstanz

Yes