Towards low cost automated smartphone- and cloud-based otitis media diagnosis

Hermanus C. Myburgh, Stacy Jose, De Wet Swanepoel, Claude Laurent

Research output: Contribution to journalArticle

  • 1 Citations

Abstract

Otitis media is one of the most common childhood illnesses. Access to ear specialists and specialist equipment is rudimentary in many third world countries, and general practitioners do not always have enough experience in diagnosing the different otitis medias. In this paper a system recently proposed by three of the authors for automated diagnosis of middle ear pathology, or otitis media, is extended to enable the use of the system on a smartphone with an Internet connection. In addition, a neural network is also proposed in the current system as a classifier, and compared to a decision tree similar to what was proposed before. The system is able to diagnose with high accuracy (1) a normal tympanic membrane, (2) obstructing wax or foreign bodies in the external ear canal (W/O), (3) acute otitis media (AOM), (4) otitis media with effusion (OME) and (5) chronic suppurative otitis media (CSOM). The average classification accuracy of the proposed system is 81.58% (decision tree) and 86.84% (neural network) for images captured with commercial video-otoscopes, using 80% of the 389 images for training, and 20% for testing and validation.

LanguageEnglish
Pages34-52
Number of pages19
JournalBiomedical Signal Processing and Control
Volume39
Early online date5 Aug 2017
DOIs
StatePublished - 1 Jan 2018

Fingerprint

Smartphones
Otitis Media
Decision trees
Decision Trees
Neural networks
Costs and Cost Analysis
Otoscopes
Waxes
Pathology
Canals
Suppurative Otitis Media
Costs
Otitis
Otitis Media with Effusion
Tympanic Membrane
Ear Canal
Classifiers
Internet
Middle Ear
Foreign Bodies

Cite this

@article{1374d337f8104aa78cc5b9271b841447,
title = "Towards low cost automated smartphone- and cloud-based otitis media diagnosis",
abstract = "Otitis media is one of the most common childhood illnesses. Access to ear specialists and specialist equipment is rudimentary in many third world countries, and general practitioners do not always have enough experience in diagnosing the different otitis medias. In this paper a system recently proposed by three of the authors for automated diagnosis of middle ear pathology, or otitis media, is extended to enable the use of the system on a smartphone with an Internet connection. In addition, a neural network is also proposed in the current system as a classifier, and compared to a decision tree similar to what was proposed before. The system is able to diagnose with high accuracy (1) a normal tympanic membrane, (2) obstructing wax or foreign bodies in the external ear canal (W/O), (3) acute otitis media (AOM), (4) otitis media with effusion (OME) and (5) chronic suppurative otitis media (CSOM). The average classification accuracy of the proposed system is 81.58{\%} (decision tree) and 86.84{\%} (neural network) for images captured with commercial video-otoscopes, using 80{\%} of the 389 images for training, and 20{\%} for testing and validation.",
keywords = "Decision tree, Feature extraction, Image processing, Neural network, Otitis media, Otoscope, Tympanic membrane",
author = "Myburgh, {Hermanus C.} and Stacy Jose and Swanepoel, {De Wet} and Claude Laurent",
year = "2018",
month = "1",
day = "1",
doi = "10.1016/j.bspc.2017.07.015",
language = "English",
volume = "39",
pages = "34--52",
journal = "Biomedical Signal Processing and Control",
issn = "1746-8094",
publisher = "Elsevier",

}

Towards low cost automated smartphone- and cloud-based otitis media diagnosis. / Myburgh, Hermanus C.; Jose, Stacy; Swanepoel, De Wet; Laurent, Claude.

In: Biomedical Signal Processing and Control, Vol. 39, 01.01.2018, p. 34-52.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Towards low cost automated smartphone- and cloud-based otitis media diagnosis

AU - Myburgh,Hermanus C.

AU - Jose,Stacy

AU - Swanepoel,De Wet

AU - Laurent,Claude

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Otitis media is one of the most common childhood illnesses. Access to ear specialists and specialist equipment is rudimentary in many third world countries, and general practitioners do not always have enough experience in diagnosing the different otitis medias. In this paper a system recently proposed by three of the authors for automated diagnosis of middle ear pathology, or otitis media, is extended to enable the use of the system on a smartphone with an Internet connection. In addition, a neural network is also proposed in the current system as a classifier, and compared to a decision tree similar to what was proposed before. The system is able to diagnose with high accuracy (1) a normal tympanic membrane, (2) obstructing wax or foreign bodies in the external ear canal (W/O), (3) acute otitis media (AOM), (4) otitis media with effusion (OME) and (5) chronic suppurative otitis media (CSOM). The average classification accuracy of the proposed system is 81.58% (decision tree) and 86.84% (neural network) for images captured with commercial video-otoscopes, using 80% of the 389 images for training, and 20% for testing and validation.

AB - Otitis media is one of the most common childhood illnesses. Access to ear specialists and specialist equipment is rudimentary in many third world countries, and general practitioners do not always have enough experience in diagnosing the different otitis medias. In this paper a system recently proposed by three of the authors for automated diagnosis of middle ear pathology, or otitis media, is extended to enable the use of the system on a smartphone with an Internet connection. In addition, a neural network is also proposed in the current system as a classifier, and compared to a decision tree similar to what was proposed before. The system is able to diagnose with high accuracy (1) a normal tympanic membrane, (2) obstructing wax or foreign bodies in the external ear canal (W/O), (3) acute otitis media (AOM), (4) otitis media with effusion (OME) and (5) chronic suppurative otitis media (CSOM). The average classification accuracy of the proposed system is 81.58% (decision tree) and 86.84% (neural network) for images captured with commercial video-otoscopes, using 80% of the 389 images for training, and 20% for testing and validation.

KW - Decision tree

KW - Feature extraction

KW - Image processing

KW - Neural network

KW - Otitis media

KW - Otoscope

KW - Tympanic membrane

UR - http://www.scopus.com/inward/record.url?scp=85026784911&partnerID=8YFLogxK

U2 - 10.1016/j.bspc.2017.07.015

DO - 10.1016/j.bspc.2017.07.015

M3 - Article

VL - 39

SP - 34

EP - 52

JO - Biomedical Signal Processing and Control

T2 - Biomedical Signal Processing and Control

JF - Biomedical Signal Processing and Control

SN - 1746-8094

ER -