Profiling bell's palsy based on House-Brackmann score

Insu Song, Nguwi Yok Yen, John Vong, Joahchim Diederich, Peter Mackinlay Yellowlees

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

In this study, we propose to examine facial nerve palsy using Support Vector Machines (SVMs) and Emergent Self-Organizing Map (ESOM). This research seeks to analyze facial palsy domain using facial features and grade the degree of nerve damage according to House-Brackmann score. Traditional evaluation methods involve a medical doctor taking a thorough history of a patient and determines the onset of the paralysis, the rate of progression and etc. The most important step is to assess the degree of voluntary movement present and document the grade of facial paralysis using House-Brackmann score. The significance of this work is that we attempt to apprehend this grading using semi-supervised learning with the aim of automating this grading process. The value of this research stems from the fact that there is a lack of literature seen in this area. The use of automated grading system greatly reduces assessment time and increases consistency because references of all palsy images are stored to provide references and comparison. The proposed automated diagnostics methods are computationally efficient making them ideal for remote assessment of facial palsy, profiling of a large number of facial images captured using mobile phones and digital cameras.

Original languageEnglish (US)
Title of host publicationProceedings of the 2013 IEEE Symposium on Computational Intelligence in Healthcare and e-Health, CICARE 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013
Pages1-6
Number of pages6
DOIs
StatePublished - 2013
Event2013 1st IEEE Symposium on Computational Intelligence in Healthcare and e-Health, CICARE 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013 - Singapore, Singapore
Duration: Apr 16 2013Apr 19 2013

Other

Other2013 1st IEEE Symposium on Computational Intelligence in Healthcare and e-Health, CICARE 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013
CountrySingapore
CitySingapore
Period4/16/134/19/13

Fingerprint

Bell Palsy
Facial Paralysis
Paralysis
Supervised learning
Self organizing maps
Digital cameras
Mobile phones
Cell Phones
Support vector machines
Facial Nerve
Research

Keywords

  • eHealth
  • face
  • Facial
  • Health Informatics
  • Medical Data Analysis
  • palsy
  • SOM
  • SVM

ASJC Scopus subject areas

  • Artificial Intelligence
  • Health Informatics
  • Health Information Management

Cite this

Song, I., Yen, N. Y., Vong, J., Diederich, J., & Yellowlees, P. M. (2013). Profiling bell's palsy based on House-Brackmann score. In Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Healthcare and e-Health, CICARE 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013 (pp. 1-6). [6583060] https://doi.org/10.1109/CICARE.2013.6583060

Profiling bell's palsy based on House-Brackmann score. / Song, Insu; Yen, Nguwi Yok; Vong, John; Diederich, Joahchim; Yellowlees, Peter Mackinlay.

Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Healthcare and e-Health, CICARE 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013. 2013. p. 1-6 6583060.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Song, I, Yen, NY, Vong, J, Diederich, J & Yellowlees, PM 2013, Profiling bell's palsy based on House-Brackmann score. in Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Healthcare and e-Health, CICARE 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013., 6583060, pp. 1-6, 2013 1st IEEE Symposium on Computational Intelligence in Healthcare and e-Health, CICARE 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013, Singapore, Singapore, 4/16/13. https://doi.org/10.1109/CICARE.2013.6583060
Song I, Yen NY, Vong J, Diederich J, Yellowlees PM. Profiling bell's palsy based on House-Brackmann score. In Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Healthcare and e-Health, CICARE 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013. 2013. p. 1-6. 6583060 https://doi.org/10.1109/CICARE.2013.6583060
Song, Insu ; Yen, Nguwi Yok ; Vong, John ; Diederich, Joahchim ; Yellowlees, Peter Mackinlay. / Profiling bell's palsy based on House-Brackmann score. Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Healthcare and e-Health, CICARE 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013. 2013. pp. 1-6
@inproceedings{24e42b9344654b4a92252fcdc3f44a3d,
title = "Profiling bell's palsy based on House-Brackmann score",
abstract = "In this study, we propose to examine facial nerve palsy using Support Vector Machines (SVMs) and Emergent Self-Organizing Map (ESOM). This research seeks to analyze facial palsy domain using facial features and grade the degree of nerve damage according to House-Brackmann score. Traditional evaluation methods involve a medical doctor taking a thorough history of a patient and determines the onset of the paralysis, the rate of progression and etc. The most important step is to assess the degree of voluntary movement present and document the grade of facial paralysis using House-Brackmann score. The significance of this work is that we attempt to apprehend this grading using semi-supervised learning with the aim of automating this grading process. The value of this research stems from the fact that there is a lack of literature seen in this area. The use of automated grading system greatly reduces assessment time and increases consistency because references of all palsy images are stored to provide references and comparison. The proposed automated diagnostics methods are computationally efficient making them ideal for remote assessment of facial palsy, profiling of a large number of facial images captured using mobile phones and digital cameras.",
keywords = "eHealth, face, Facial, Health Informatics, Medical Data Analysis, palsy, SOM, SVM",
author = "Insu Song and Yen, {Nguwi Yok} and John Vong and Joahchim Diederich and Yellowlees, {Peter Mackinlay}",
year = "2013",
doi = "10.1109/CICARE.2013.6583060",
language = "English (US)",
isbn = "9781467358835",
pages = "1--6",
booktitle = "Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Healthcare and e-Health, CICARE 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013",

}

TY - GEN

T1 - Profiling bell's palsy based on House-Brackmann score

AU - Song, Insu

AU - Yen, Nguwi Yok

AU - Vong, John

AU - Diederich, Joahchim

AU - Yellowlees, Peter Mackinlay

PY - 2013

Y1 - 2013

N2 - In this study, we propose to examine facial nerve palsy using Support Vector Machines (SVMs) and Emergent Self-Organizing Map (ESOM). This research seeks to analyze facial palsy domain using facial features and grade the degree of nerve damage according to House-Brackmann score. Traditional evaluation methods involve a medical doctor taking a thorough history of a patient and determines the onset of the paralysis, the rate of progression and etc. The most important step is to assess the degree of voluntary movement present and document the grade of facial paralysis using House-Brackmann score. The significance of this work is that we attempt to apprehend this grading using semi-supervised learning with the aim of automating this grading process. The value of this research stems from the fact that there is a lack of literature seen in this area. The use of automated grading system greatly reduces assessment time and increases consistency because references of all palsy images are stored to provide references and comparison. The proposed automated diagnostics methods are computationally efficient making them ideal for remote assessment of facial palsy, profiling of a large number of facial images captured using mobile phones and digital cameras.

AB - In this study, we propose to examine facial nerve palsy using Support Vector Machines (SVMs) and Emergent Self-Organizing Map (ESOM). This research seeks to analyze facial palsy domain using facial features and grade the degree of nerve damage according to House-Brackmann score. Traditional evaluation methods involve a medical doctor taking a thorough history of a patient and determines the onset of the paralysis, the rate of progression and etc. The most important step is to assess the degree of voluntary movement present and document the grade of facial paralysis using House-Brackmann score. The significance of this work is that we attempt to apprehend this grading using semi-supervised learning with the aim of automating this grading process. The value of this research stems from the fact that there is a lack of literature seen in this area. The use of automated grading system greatly reduces assessment time and increases consistency because references of all palsy images are stored to provide references and comparison. The proposed automated diagnostics methods are computationally efficient making them ideal for remote assessment of facial palsy, profiling of a large number of facial images captured using mobile phones and digital cameras.

KW - eHealth

KW - face

KW - Facial

KW - Health Informatics

KW - Medical Data Analysis

KW - palsy

KW - SOM

KW - SVM

UR - http://www.scopus.com/inward/record.url?scp=84883689135&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883689135&partnerID=8YFLogxK

U2 - 10.1109/CICARE.2013.6583060

DO - 10.1109/CICARE.2013.6583060

M3 - Conference contribution

SN - 9781467358835

SP - 1

EP - 6

BT - Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Healthcare and e-Health, CICARE 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013

ER -