Automated Brainstem Evoked Response Audio Me Try Using Wavelet

39
Auditory Brainstem Evoked Response using Wavelets And Neural Networks Dr. V. UDAYASHANKARA PROF. DEPT OF IT,SJCE MYSORE BY JYOTHI.B ASST.PROFF, DEPT.OF E&C, NIE-IT, MYSORE GUIDED BY 1

Transcript of Automated Brainstem Evoked Response Audio Me Try Using Wavelet

Page 1: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

Automated Analysis of Auditory Brainstem Evoked Response using Wavelets And Neural Networks

Dr. V. UDAYASHANKARA PROF. DEPT OF IT,SJCE

MYSORE 

BY

JYOTHI.BASST.PROFF, DEPT.OF E&C,

NIE-IT, MYSORE

GUIDEDBY

1

Page 2: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

CONTENTS

• Introduction

• Algorithm

• Implementation

• Results

• Conclusion

2

Page 3: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

INTRODUCTION

• What is Brainstem Evoked Response Audiometry(BERA)?

• What is the principle?

• What are its applications?

3

Page 4: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

• Brainstem response is Electrical signal evoked in human Brainstem due to presentation of sound such as click or tone.

• Brainstem Evoked Response Audiometry is a screening test to monitor the Hearing loss or Deafness in a patient .

4

Page 5: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

BLOCK DIAGRAM

5

Page 6: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

CLINICAL APPLICATIONS

• Estimation of threshold

• Investigation of hearing loss

6

Page 7: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

TYPICAL BERA WAVEFORM

7

Page 8: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

ORIGIN OF EACH WAVE:

PEAK ORIGIN

I Cochlear nerve

IIDorsal & Ventral cochlear

nucleus

III Superior olivary complex

IV Nucleus of lateral lemniscus

V Inferior colliculus

VI Medial geniculate body

VII Auditory radiation(cortex8

Page 9: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

OBJECTIVE :

The aim of this paper is to develop software

classification model to assist the audiologist with

an automated detection of the ABR waveform and

also detection of peaks for identification of

pathologies.9

Page 10: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

ALGORITHM:

• Extraction of BERA from recorded EEG

• Identification of peaks

• Classification

10

Page 11: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

FLOW CHART

Get the EEG Data

Is a BERA response present

Identification of peaks

Peak detection

Abnormal Normal

no

Classification

11

Page 12: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

IMPLEMENTATION:

Data Acquisition: EEG data is collected in JSS hospital and data

base is created which consists of 30 normal (neonates)and 25

abnormal patients..

12

Page 13: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

EXTRACTION:

• Band pass filtering with cut-off freq. 30-3000 Hz.

• Signal adaptive filtering using complex wavelets

• This algorithm uses Dual tree complex wavelet

transform.13

Page 14: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

PEAK IDENTIFICATION

• Gaussian Derivative estimation filter used

Steps :

• Find Zero Crossings and

• Peak Detection using Local Max And Min Value.

• Finally Peak Labeling.

14

Page 15: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

FLOW CHART:

15

Page 16: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

PARAMETERS USED FOR LABELING PEAKS

16

Page 17: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

17

Page 18: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

CLASSIFICATION :

• Artificial Neural Network(ANN) is used .

• Diagnosis of hearing disorder is one of the applications of

neural network.

18

Page 19: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

• ANN is defined by 3 types of parameters:

1. Inter connection pattern layers of neurons.- nonlinear

2. Learning process for updating weights

3. The activation function

19

Page 20: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

FEED-FORWARD ARCHITECTURE

20

Page 21: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

BLOCK DIAGRAM

21

Page 22: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

LEARNING ALGORITHM :

22

Page 23: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

PATIENT INFORMATION

• Intensity• Ear• peak I• Amplitude of Peak I• peak III• Amplitude of peak III• peak V• Amplitude of peak V• Inter peak (I – III)• Inter peak (III – V)• Inter peak (I – V)

23

Page 24: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

RESULT:

1. If the output node value is >0.7467 --- Normal

2. Else if output node value is <= 0.7467 --- Abnormal

24

Page 25: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

TESTS AND RESULTS:

0 100 200 300 400 500 600 700 800-5000

0

5000

10000

0 100 200 300 400 500 600-1

-0.5

0

0.5

1x 10

4 Complex 1-D wavelet

t

(t

)

Fig: Extracted BERA signal25

Page 26: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

Fig: Gaussian First Derivative:26

Page 27: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

Fig: First deriv. of the Input signal

-15 -10 -5 0 5 10 15-4

-3

-2

-1

0

1

2

3First Derivative

Time

Am

plitu

de

27

Page 28: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

Fig: Zero crossing & peak identification28

Page 29: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

Fig: Peak Labeled29

Page 30: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

GUI in MATLAB :

30

Page 31: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

31

Page 32: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

GUI in C:

32

Page 33: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

33

Page 34: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

ANN RESULTS:

Normal Abnormal

Training Number 30 25

Test Number 25 20

Correct Classification

24 18

Rate of classification

96% 90%

34

Page 35: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

Accuracy of ANN classification

35

Page 36: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

CONCLUSION

• This paper demonstrates the feasibility of an algorithm for extraction of clean BAER waveforms and subsequent automatic peak identification in order to perform functional assessment of the brainstem.

• Automated method gives 96% for normal 90% Accuracy for Abnormal patients.

36

Page 37: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

REFERENCES:

• [1]A. Jacquin, E. Causevic, E. R. John, and L. S. Prichep, “Optimal denoising of brainstem auditory evoked response (BAER) for automatic peak identi- fication and brainstem assessment,” in Proc. 28th IEEE 

• [2]A. Jacquin, E. Causevic, E.R. John, J. Kovacevic “Adaptive complex wavelet-based filtering of EEG for extraction of evoked potential responses,” ICASSP’04, 2004.

• [3]Automated Analysis of the Auditory Brainstem Response Using Derivative Estimation Wavelets Andrew P. Bradleya, Wayne J. Wilsonb

• [4]Hall III, J., Handbook of auditory evoked responses,Needham Heights, Massachusetts: Allyn and Bacon,1992.

• [5] Mallat, S.G., A Wavelet tour of signal processing,2nd Ed., San Diego: Academic Press, 1999.

37

Page 38: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

THANK U

38

Page 39: Automated Brainstem Evoked Response Audio Me Try Using Wavelet

39