Invited talk at IBRO UIU EEG Signal Processing

State-of-the-Art EEG Signal Processing
Techniques in the Diagnosis and
Treatment of Neurological Diseases
Md. Kafiul Islam, PhD, SMIEEE
Assistant Professor, Dept. of EEE, IUB
Lab Head, Biomedical Instrumentation and Signal Processing Lab
Web: https://www.researchgate.net/profile/Md_Kafiul_Islam
Email: kafiul_islam@iub.edu.bd
Dr. Md. Kafiul Islam
1

About Us!
Biomedical Instrumentation and Signal
Processing Lab
Featured Projects:
1. EOG based Computer Mouse Cursor Control for Physically Challenged
People
2. Design and Development of a EOG-based System to Control Electric
Wheelchair for People Suffering from Quadriplegia/Quadriparesis
3. Design and Implementation of a Low-cost EMG Signal Recorder for
Application in Prosthetic Arm Control for Developing Countries.
4. Development of a Low Cost and Portable ECG Monitoring System for
Rural/Remote Areas of Bangladesh
5. Emotion Classification using Wireless EEG Devices
6. Motion Artifact Removal from Ambulatory EEG
2

Motivation
 Patient Monitoring (critical care)
 ICU, Coma, NICU
 Disease Detection/Diagnosis
 Brain (EEG)
 Preventive Healthcare (Prediction)
 Brain-Machine Interfacing (BMI)
 BCI, Prosthetesis
 Controlling wheelchair, prosthetic arm
 Treatment and Rehabilitation
 Basic understanding of the brain’s physiology and function
Patient › EEG Signals › Processing › Decision2
3
[2] https://www.embs.org/about-biomedical-engineering/our-areas-of-research/biomedical-signal-processing/

Digital Signal Analysis and Processing
Analysis
 Measurement of signal properties
 Looking at the signals in other than time domain (frequency, wavelet, etc.)
Processing
 Remove unwanted noise/interference/artifacts (Filtering)
 Improve signal quality (SNR)
 Extract specific or critical information
 Detect useful events
4

Challenges with EEG Signals3
 Very low SNR
 Non-stationarity and non-linearity
properties
 Diverse types of noise
 Noise and Artifacts overlap both in
Spectral and Temporal Domain
 False alarms and errors can
mislead the diagnosis, treatment or
control of any external devices
 Traditional Signal processing
techniques fail
5
[3] Biomedical Instrumentation by Ákos Jobbágy and Sándor Varga

Brain Recordings!
 Non-Invasive
 EEG (electrical) and MEG (magnetic)
 Invasive
 Sub-scalp EEG (S-EEG)
 ECoG / iEEG
 Intracortical Implant
 Better signal quality but …!?
Motivation to record brain signals:
 How brain works?
 Information processing
 Memory formation
 Understanding neurological disorders
& providing treatment
6

What is EEG?
 Recording of the brain's spontaneous electrical activity over a period of time
by placing flat metal discs (electrodes) attached to the scalp.
 Measures voltage fluctuations resulting from ionic current within the neurons
of the brain.
 Scalp-EEG: Most popular brain recording technique
 Low cost
 Non-invasive
 Portable
 Reasonable temporal resolution
The first human EEG recording obtained by Hans Berger in 1924. The
upper tracing is EEG, and the lower is a 10 Hz timing signal.
Electro-encephalo-gram Electrical-Brain-Picture
7

EEG Acquisition
Standard 10-20 Electrode Montage Acquisition involves
 Electrodes
 Amplification (IA)
 Filtering (Active)
 Digitizing (ADC)
 Storage
Challenge: To detect signal as
low as 1 µV
8

 Delta: (< 4 Hz)
◦ adult slow-wave sleep
◦ in babies
◦ continuous-attention tasks
 Theta: (4 - 8 Hz)
◦ higher in young children
◦ drowsiness in adults and teens
◦ idling
 Alpha: (8 - 13 Hz)
◦ relaxed/reflecting
◦ closing the eyes
 Beta: (14 - 30 Hz)
◦ active thinking, focus, high alert, anxious
 Gamma: (> 30 Hz)
◦ Displays during cross-modal sensory processing
 Mu: (7.5 - 12.5 Hz)
◦ Shows rest-state motor neurons
Gamma
•Rhythmic: EEG activity consisting in waves of approximately constant frequency.
•Arrhythmic: EEG activity in which no stable rhythms are present.
•Dysrhythmic: Rhythms and/or patterns of EEG activity that characteristically appear in patient
groups or rarely or seen in healthy subjects.
9

Applications of EEG
 Epilepsy Diagnosis: Seizure Detection Most
Common
 Also to diagnose Alzheimer’s disease,
Parkinson’s, Sleep
disorders, Coma, Encephalopathy, brain injury,
and brain death
 Brain-Computer Interface (BCI) / Neural
Prosthesis
 Basic Neuroscience Research
 Cognitive science, cognitive psychology, and
psychophysiological research.
10

Applications of EEG
(Epilepsy Diagnosis: Seizure Detection)
11
Typical waveforms recorded during seizures in
an animal model of absence epilepsy caused
by the chemo convulsant pentyleneterzol (PTZ).
The anterior thalamus is a sub-cortical
element that has shown to have strong
association with cortex during these seizures.
The spike and wave shape is clearly evident in
anterior thalamic and cortical derivations

Applications of EEG
(Alzheimer’s Disease Diagnosis)
Fiscon, Giulia, et al. "Combining EEG signal processing with supervised methods for Alzheimer’s
patients classification." BMC medical informatics and decision making 18.1 (2018): 35.
12

Applications of EEG
(Depression Diagnosis)
13

Applications of EEG
(Diagnosis of Encephalopathy)
14
Jacob, Jisu Elsa, Gopakumar Kuttappan Nair, Thomas Iype, and Ajith Cherian. "Diagnosis of encephalopathy based on energies of
EEG subbands using discrete wavelet transform and support vector machine." Neurology research international 2018 (2018).

Common Signal Analysis & Processing Techniques
 Fourier Transform / Power Spectral Density (PSD/Pwelch)
 Filtering (FIR/IIR: Notch, LPF, BPF, HPF)
Advanced Techniques
 Adaptive filtering (use of reference channel)
 A-priori user input required
 Wiener/Kalman/Particle Filtering
 Blind Source Separation
 ICA/CCA/MCA/SVD
 Time-series Analysis
 Wavelet transform / Spectrogram (STFT)
 Empirical Techniques (Non-linear & non-stationary)
 HHT/EMD/EEMD
15

Power Spectral Density, PSD (Pwelch)
16
Effect of Notch Filtering on Time Domain Signal
Effect of Notch Filtering on PSD

Spectrogram (using STFT)4
17
[4] https://neupsykey.com/seizures-and-quantitative-eeg/

Adaptive Filtering (EEG Artifact Removal6)
18
[5] http://www.jscholaronline.org/articles/JBER/Signal-Processing.pdf
[6] https://www.sciencedirect.com/science/article/pii/S098770531630199X
Reference ECG
Artifactual EEG
Clean EEG after ECG pulses are removed

Independent Component Analysis (ICA)
(for EOG and EMG artifact removal from EEG7)
19
[7] https://sccn.ucsd.edu/~jung/Site/EEG_artifact_removal.html
Recorded Multi-channel EEG Signals
Artifacts Contaminated EEG ( 𝑿)
After applying ICA, Independent
Components are separated and
Identified ( 𝑺′)
Artifactual ICs are removed
followed by Inverse ICA to get
Artifacts Corrected EEG
ICA
Un-mixing 𝑾
Inverse ICA
Mixing 𝑨
Blink Artifact
EMG Artifact

20
Wavelet Transform
(A Multi-resolution Analysis)
 Split Up the Signal into a Bunch of Signals
 Representing the Same Signal, but all Corresponding to Different
Frequency Bands
 Only Providing What Frequency Bands Exists at What Time Intervals
Presented By Md Kafiul Islam
Translation
(The location of
the window)
Scale
Mother Wavelet
      dt
s
t
tx
s
ss xx 




 
 
 *1
,,CWT
Translation
(The location of
the window)
Scale
Mother Wavelet
From http://www.cerm.unifi.it/EUcourse2001/Gunther_lecturenotes.pdf, p.10
Wavelet
Small wave
Means the window function is of finite length
Mother Wavelet
 A prototype for generating the other window functions
 All the used windows are its dilated or compressed
and shifted versions
Scale S>1: dilate the signal
S<1: compress the signal

Wavelet Transform on EEG Signals
(for separating different EEG sub-band rhythms8)
21
[8] http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7856467

Empirical Mode Decomposition (EMD) on EEG Signals
(for detecting Eye-blink artifacts9)
22
[9] https://www.researchgate.net/publication/228524659_Real_time_characterisation_of_neural_signals_with_application_to_neonatal_monitoring/figures?lo=1

Artifacts & Interferences in EEG10
23
[10] https://emedicine.medscape.com/article/1140247-overview

Artifacts Found in EEG* (1)
Horizontal Eye
Movement (T1-T2)
and
Blink Artifacts
(Frontal channels)
EOG 
*Chang, B. S., Schachter, S. C., & Schomer, D. L. (2005). Atlas of ambulatory EEG.
Amsterdam ; London: Amsterdam ; London : Elsevier Academic Press, c2005.
24

Artifacts Found in EEG (2)
Rhythmic eye flutter can occur at quite high frequencies, in this case 5–8 Hz, and
trigger automated seizure detection algorithms.
This artifact can be distinguished from ictal events in different ways, including the
lack of evolution in frequency or amplitude over time.
Eye Flutter Artifact
recorded by Seizure
Detection Algorithm
25

Electrode Tapping
Artifact
With ambulatory EEG recording, there may be periods in which the patient
is scratching or pressing on the scalp electrodes.
26

Jaw-Clenching
Artifact
 Periods of jaw clenching and biting during ambulatory EEG recording can be associated with artifact.
 This activity is often most prominent over the temporal regions, presumably due to temporalis or
masseter muscle contraction.
27

Chewing Artifact
 Chewing artifact can often have rhythmic features and at times may resemble ictal activity.
 This artifacts are characterized by the rhythmic appearance of muscle artifact centered mostly
over the temporal regions bilaterally.
28

Chewing Artifact
Recorded by
Spike Detection
Algorithm
 Chewing artifact can have rhythmic and sharp features, and can thus be picked up by
automated detection algorithms.
Here, the spike detections at 23:53:23 and at 23:53:34 capture high frequency sharp waveforms
that are artifactual in nature, in association with a nighttime snack.
29

Dry Electrode Artifact
 One disadvantage of ambulatory EEG monitoring is the inability of technologists to check on
recording quality frequently in real time and to respond with appropriate technical adjustments as
needed throughout the day, as would typically occur in an inpatient monitoring unit.
 Here, a dry electrode at F8 causes an artifact seen throughout this excerpt.
30

Forehead Rubbing
Artifact
 As with many other patient movement artifacts, rhythmic rubbing artifact can be a potentially
confusing finding on ambulatory EEG monitoring, particularly in the absence of concomitant video
recording. Here, rhythmic rubbing of the forehead produces an artifact in the anterior channels,
extending from the beginning of this excerpt through 20:50:16.
 Differentiation of such artifact from an ictal event, based on the lack of evolution of the artifact
in frequency or amplitude, is critical.
31

Pulse Artifact
 Pulse artifact is caused by the rhythmic movement of scalp electrodes, usually over the
temporal regions, by the pulsations of blood through vessels close to the skin, such as the
superficial temporal artery.
 It is to be distinguished from the more common electrocardiographic (EKG) artifact in that pulse
artifact is typically not as sharply contoured, resembles a slow wave, and follows the QRS complex
rather than being simultaneous to it.
 Here, pulse artifact is seen in channels 9 and 10 over the left temporal region throughout this
entire excerpt.
32

 Purpose:
 Diagnosis/Detection of Epilepsy Seizure by Long-term EEG Monitoring (up to 72 hours)
 Early warning of seizures (prediction) onset in order to stop seizure
 Special Features
 Continuous monitoring
 Wireless EEG (up to 10 m or so)
 Usually Dry electrode
 Few no. of channels
 typically 4-8 channels
 Patient can lead normal daily life
 Except few tasks (e.g. taking bath)
Ambulatory EEG

 Head Movement ( < 10 Hz )
 Shake
 Nod
 Roll
 Hand Movement
 Eye Movement
 Eyebrow Movement
 Eye blinking
 Horizontal and Vertical Eye Movement
 Extra-ocular muscle activity
 Jaw Clenching/Eating/Drinking
 Walking
 Running
 Sleeping
 Drowsiness, Light Sleep, Deep Sleep, REM
 Talking
 Working on PC
 Watching TV
 And Many More!
Movements Associated with Ambulatory EEG
Consequence:
Too Many Motion Artifacts!

Challenge: Differentiate
between artifacts, epileptic
seizures and normal EEG activities!
How …!???

35
Summery of Existing Artifact Removal Methods
Single artifact type
Reference channel
Mostly general purpose
Often Manual or Semi-automatic
Often suitable for Multi channel
Real-time/Online processing capability
Not enough quantitative evaluation
Often after-effects not reported
Lack of adequate dataset used
Often hybrid methods (wICA, EEMD-CCA, etc.)

EEG Signal Classification techniques
36
 Supervised Classification
 SVM
 (Better for binary classification)
 ANN
 (Suitable for multi-classes)
 Deep CNN
 Preprocessing may be ignored
 Feature Extraction may not needed
 KNN
 Un-Supervised
 Clustering (K-means)

 Domain
 Time
 Frequency
 Wavelet
 Statistical Features
 Entropy
 ApEn, MSE, CMSE, MMSE, etc.
 Kurtosis
 Skew
 RMS/Variance/S.D.
 Max/Min/Mean
 Maxima/Minima
Features for Epileptic Seizure Detection
(Example of Feature Extraction)
High Frequency Oscillations
(HFO)
80 Hz – 200 Hz
Ripple
200 Hz – 600 Hz
Typical Scalp EEG!
0.05Hz – 128 Hz
Seizure Appears in Scalp EEG
0.5 Hz - 29 Hz [1,2]
1. J. Gotman, “Automatic recognition of epileptic seizures in the EEG,”
Electoencephalogr Clin. Neurophysiol., vol. 54, pp. 530–540, 1982
2. M. E. Saab and J. Gotman, “A system to detect the onset of epileptic
seizures in scalp EEG,” Clin. Neurophysiol., vol. 116, pp. 427–442,
2005.

EEG Features before and after Artifact Removal
Features Extracted:
(i) Entropy (ii) Kurtosis (iii) Line Length (iv) Peak
(v) NEO (vi) Variance (vii) FFT (viii) FFT Peak
Note: The features between seizure and non-seizure data are more separable after artifact removal which
suggests that it increases the detection rate and minimizes false alarms (false alarms are due to artifacts).

39
Effect of Artifact Removal from EEG (Epilepsy Diagnosis)
False alarms improvement

40
BCI Performance ImprovementSNDR Improvement
Effect of Artifact Removal from EEG (BCI)

EEGLAB: Open Source MATLAB toolbox for processing continuous &
event-related EEG
41
EEGLAB Features
•Graphic user interface
•Multi-format data importing
•High-density data scrolling
•Interactive plotting functions
•Semi-automated artifact removal
•ICA & time/frequency transforms
•Event & channel location handling
•Forward/inverse head/source modeling
•Defined EEG & STUDY data structures
• Over 100 advanced plug-in/extensions
https://sccn.ucsd.edu/eeglab/index.php

EEGLAB Plug-ins
42

EEGLAB Plug-ins (Cont..)
43

Future Challenges & Recommendations
Challenges
 Ambulatory Recording ->
motion artifacts
 Real-time processing ->
computational complexity
 On-chip on-the-Fly Decision
Making
 Big Data storage and use for
future prediction (preventive
healthcare)
44
Recommendations
 Application Specific Models
 Artifact Specific
 Standard performance evaluation
 Ground truth data
 Considering ML & AI (Deep CNN)

Thank You
45

Invited talk at IBRO UIU EEG Signal Processing

Recommended

Recommended

More Related Content

What's hot

What's hot (20)

Similar to Invited talk at IBRO UIU EEG Signal Processing

Similar to Invited talk at IBRO UIU EEG Signal Processing (20)

More from Md Kafiul Islam

More from Md Kafiul Islam (20)

Recently uploaded

Recently uploaded (20)

Invited talk at IBRO UIU EEG Signal Processing