Detection of unilateral hearing loss by stationary wavelet entropy

Yudong Zhang; Deepak Ranjan Nayak; Ming Yang; Ti Fei Yuan; Bin Liu; Huimin Lu; Shuihua Wang

doi:10.2174/1871527315666161026115046

Detection of unilateral hearing loss by stationary wavelet entropy

Yudong Zhang, Deepak Ranjan Nayak, Ming Yang, Ti Fei Yuan, Bin Liu, Huimin Lu, Shuihua Wang^*

^*Corresponding author for this work

Research output: Contribution to journal › Review article › peer-review

38 Citations (Scopus)

Abstract

Aim: Sensorineural hearing loss is correlated to massive neurological or psychiatric disease. Materials: T1-weighted volumetric images were acquired from fourteen subjects with right-sided hearing loss (RHL), fifteen subjects with left-sided hearing loss (LHL), and twenty healthy controls (HC). Method: We treated a three-class classification problem: HC, LHL, and RHL. Stationary wavelet entropy was employed to extract global features from magnetic resonance images of each subject. Those stationary wavelet entropy features were used as input to a single-hidden layer feedforward neural-network classifier. Results: The 10 repetition results of 10-fold cross validation show that the accuracies of HC, LHL, and RHL are 96.94%, 97.14%, and 97.35%, respectively. Conclusion: Our developed system is promising and effective in detecting hearing loss.

Original language	English
Pages (from-to)	122-128
Number of pages	7
Journal	CNS and Neurological Disorders - Drug Targets
Volume	16
Issue number	2
DOIs	https://doi.org/10.2174/1871527315666161026115046
Publication status	Published - 2017
Externally published	Yes

Keywords

Computer-aided diagnosis
Sensorineural hearing loss
Single-hidden layer feed forward neural-network
Stationary wavelet entropy
Unilateral hearing loss

Access to Document

10.2174/1871527315666161026115046

Cite this

@article{ba19bec4df0e419ba3a6cc11c332e90b,

title = "Detection of unilateral hearing loss by stationary wavelet entropy",

abstract = "Aim: Sensorineural hearing loss is correlated to massive neurological or psychiatric disease. Materials: T1-weighted volumetric images were acquired from fourteen subjects with right-sided hearing loss (RHL), fifteen subjects with left-sided hearing loss (LHL), and twenty healthy controls (HC). Method: We treated a three-class classification problem: HC, LHL, and RHL. Stationary wavelet entropy was employed to extract global features from magnetic resonance images of each subject. Those stationary wavelet entropy features were used as input to a single-hidden layer feedforward neural-network classifier. Results: The 10 repetition results of 10-fold cross validation show that the accuracies of HC, LHL, and RHL are 96.94%, 97.14%, and 97.35%, respectively. Conclusion: Our developed system is promising and effective in detecting hearing loss.",

keywords = "Computer-aided diagnosis, Sensorineural hearing loss, Single-hidden layer feed forward neural-network, Stationary wavelet entropy, Unilateral hearing loss",

author = "Yudong Zhang and Nayak, {Deepak Ranjan} and Ming Yang and Yuan, {Ti Fei} and Bin Liu and Huimin Lu and Shuihua Wang",

note = "Publisher Copyright: {\textcopyright} 2017 Bentham Science Publishers.",

year = "2017",

doi = "10.2174/1871527315666161026115046",

language = "English",

volume = "16",

pages = "122--128",

journal = "CNS and Neurological Disorders - Drug Targets",

issn = "1871-5273",

number = "2",

}

TY - JOUR

T1 - Detection of unilateral hearing loss by stationary wavelet entropy

AU - Zhang, Yudong

AU - Nayak, Deepak Ranjan

AU - Yang, Ming

AU - Yuan, Ti Fei

AU - Liu, Bin

AU - Lu, Huimin

AU - Wang, Shuihua

PY - 2017

Y1 - 2017

N2 - Aim: Sensorineural hearing loss is correlated to massive neurological or psychiatric disease. Materials: T1-weighted volumetric images were acquired from fourteen subjects with right-sided hearing loss (RHL), fifteen subjects with left-sided hearing loss (LHL), and twenty healthy controls (HC). Method: We treated a three-class classification problem: HC, LHL, and RHL. Stationary wavelet entropy was employed to extract global features from magnetic resonance images of each subject. Those stationary wavelet entropy features were used as input to a single-hidden layer feedforward neural-network classifier. Results: The 10 repetition results of 10-fold cross validation show that the accuracies of HC, LHL, and RHL are 96.94%, 97.14%, and 97.35%, respectively. Conclusion: Our developed system is promising and effective in detecting hearing loss.

AB - Aim: Sensorineural hearing loss is correlated to massive neurological or psychiatric disease. Materials: T1-weighted volumetric images were acquired from fourteen subjects with right-sided hearing loss (RHL), fifteen subjects with left-sided hearing loss (LHL), and twenty healthy controls (HC). Method: We treated a three-class classification problem: HC, LHL, and RHL. Stationary wavelet entropy was employed to extract global features from magnetic resonance images of each subject. Those stationary wavelet entropy features were used as input to a single-hidden layer feedforward neural-network classifier. Results: The 10 repetition results of 10-fold cross validation show that the accuracies of HC, LHL, and RHL are 96.94%, 97.14%, and 97.35%, respectively. Conclusion: Our developed system is promising and effective in detecting hearing loss.

KW - Computer-aided diagnosis

KW - Sensorineural hearing loss

KW - Single-hidden layer feed forward neural-network

KW - Stationary wavelet entropy

KW - Unilateral hearing loss

UR - http://www.scopus.com/inward/record.url?scp=85015622428&partnerID=8YFLogxK

U2 - 10.2174/1871527315666161026115046

DO - 10.2174/1871527315666161026115046

M3 - Review article

C2 - 27784224

AN - SCOPUS:85015622428

SN - 1871-5273

VL - 16

SP - 122

EP - 128

JO - CNS and Neurological Disorders - Drug Targets

JF - CNS and Neurological Disorders - Drug Targets

IS - 2

ER -

Detection of unilateral hearing loss by stationary wavelet entropy

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this