Upload
samantha-goodwin
View
220
Download
2
Tags:
Embed Size (px)
Citation preview
Epileptic Seizure Epileptic Seizure Detection SystemDetection System
Team Members Valerie Kuzmick, Biomedical Engineering John Lafferty, Computer Engineering April Serfass, Biomedical Engineering Doug Szperka, Computer Engineering Benjamin Zale, Computer Engineering
Advisors Prawat Nagvajara, PhD, Computer Engineering Karen Moxon, PhD, Biomedical Engineering Jeremy Johnson, PhD, MCS/ECE
Problem: EpilepsyProblem: Epilepsy
Chronic Brain Function Disorder
Characterized by Seizures
Over two million suffering from epilepsy 1% of US population
Current Treatments NOT Effective for 20% (400,000 patients) of Epileptics
VISION:VISION:Complete SystemComplete System
Data AcquisitionSystem
Seizure Detection Unit
Stimulation Device
Design ChallengeDesign Challenge
Data AcquisitionSystem
Seizure Detection Unit
Stimulation Device
Prevention of SeizuresPrevention of SeizuresNCP Brain ‘Pacemaker’
– Intermittent electrical pulses 24 hours a day– Implanted under the collarbone – Delivers electrical signals to the brain via
vagus nerve in the neck – When patient senses seizure coming, he or
she can activate the stimulator manually
Developed SolutionDeveloped Solution
Prototype– Microprocessor-based device that
detects the neural activity associated with an epileptic seizure
Results– Seizure Detection: 100% Accuracy– Low False Positive Rate
Solutions for Seizure Solutions for Seizure DetectionDetection
Analysis of EEG Data With ANN
– Advantages Noninvasive
– Disadvantages Signal detection far
from epicenter of seizure
Loss of signal fidelity through bone & scalp
65% detection rate
Analysis of Multiple Single-Neuron Data– Disadvantages
Invasive
– Advantages Signal detection at the
epicenter of seizure Ideal signal fidelity via
direct recording from neurons
Preliminary data suggest 100% detection rate
Method of SolutionMethod of Solution
Data Collection & AnalysisAlgorithm DevelopmentSoftware SimulationDetection Unit Implementation
Data CollectionData Collection
Certified laboratory rat handlers– IACUC approved protocol
Electrodes surgically implanted– Temporal lobes
PTZ administration– Seizures induced
Data CollectionData Collection
RECORDINGDEVICE
EIGHT-ARRAY ELECTRODE
TEMPORAL LOBE
Multiple Single NeuronsMultiple Single Neurons
AnalysisAnalysis
Videotape– Seizure/No Seizure
NEX (NeuroExplorer)– Rate Histograms– Bin Size/Smooth Data
Excel– Imported NEX Files– Seizures Distinguished– Consolidation for Algorithm Development
AnalysisAnalysis
Algorithm DevelopmentAlgorithm Development
Research from EEG Seizure Detectors– Artificial Neural Network (ANN)– Signal Processing Techniques
Artificial Neural Network– MATLAB Toolkit– Created Various Feedforward Neural
Networks Highest detection rate was 60%
Cross Correlation SolutionCross Correlation Solution
Neural activity becomes synchronized during a seizure
Cross correlate data over a window of time– Shows synchronization of neural action
potentials Graphed the sum of pair-wise cross
correlation Shape of the cross-correlation is
determining factor
Data ConversionData Conversion
Data ConversionData Conversion
Cross Correlation SolutionCross Correlation Solution
Standard DeviationStandard Deviation
Statistic that tells you how tightly all the various data points are clustered around the mean
– Small standard deviation Data points are pretty tightly bunched together
– Large standard deviation Data points are spread apart
Cross Correlation SolutionCross Correlation Solution
Non Seizure Data Seizure Data
Threshold ValueThreshold Value
Experimentally determined dividing line between seizure and non-seizure
Algorithm Summary– Data streamed into bins of finite length– Cross Correlate– Determine 1st standard deviation of cross
correlated data– Smaller than threshold value = SEIZURE
SimulationSimulation
Used MATLAB to Simulate– Used Saved Data as Inputs– Allowed Varying of Algorithm Parameters– Saved Results of Each Run to File
Final Parameters from Results– Bin Size– Bins per Window Size– Threshold Value
Simulation ResultsSimulation Results
50ms Bin Size and 128 Bins per Window Promising Results
– Threshold Value was the Same– Detected 100% of Observed Seizures– Low False Positive Rate of 0.3% ~ 4.3
min/day– Detected Seizures 4.5s Early on Average
Some as early as 17s Few detected late – 2.5s was the latest
Simulation ResultsSimulation ResultsSeizure vs Baseline Histogram
Rat #2
0
500
1000
1500
2000
2500
0 525
1050
1575
2100
2625
3150
3675
4200
4725
5250
5775
6300
6825
7350
7875
8400
8925
9450
9975
Standard Deviation9 Channels - 50ms Bins - 128 Bins/Window
Nu
mb
er
of
Oc
cu
rra
nc
es
.00%
20.00%
40.00%
60.00%
80.00%
100.00%
120.00%
Basline Data
Seizure Data
Baseline Cumulative %
Seizure Cumulative %
Detection Unit ImplementationDetection Unit Implementation
Implement algorithm to execute on dedicated microprocessor– Speed– Prototyping
QED RM5231 RISC Processor– MIPS Instruction Set– V3 Hurricane Evaluation Board
HardwareHardwareHurricane Evaluation Board
– Inserted into PCI slot of Windows-based computer
– Communication Protocols PCI Serial
Embedded SoftwareEmbedded Software
ANSI C for portability
Compiled into Motorola S-Record format
Downloaded to board via serial port
Dataflow DiagramDataflow Diagram
ActionPotential
DataNEX Excel
DataConcatenator
RatStat(HardwareSimulation)
SimulationOutput
SerialComm
HurricaneEvaluation
Board(Prototype)
PrototypeOutput
Host PC SoftwareHost PC Software
Automates Data Transmission
– Sums data into bins– Generates S-Records of data– Transmits data to evaluation board via
serial port connection– Tells evaluation board to execute embedded
software– Captures and reports seizure notification
from evaluation board
Host PC SoftwareHost PC Software
Economic AnalysisEconomic Analysis
Prototype Development– Approximately $141,500 in equipment
Future Commercial Development– Needs to be System-on-a-Chip Solution
– Data Acquisition System: $ 8,000– Seizure Detection Unit: $ 1,000– NCP Brain Pacemaker: $11,000
– Entire System: $20,000 or less to be marketable and profitable
Results Results Cross Correlation
Window (bins)
Cross Correlation Window
(seconds)
Average Execution Time (milliseconds)
32 1.6 13.2
64 3.2 50.3
128 6.4 182
256 12.8 718
Prototype does not operate in real time when data is streamed
ConclusionsConclusions
Collected and Evaluated Approximately 1 Hour of Data from Three Specimens– Only 45 minutes (2 Rats / 3 Trials) usable– Remaining data corrupted
100% Seizure Detection Rate
0.3% False Positive Rate
Seizures Predicted on an Average of 4.5 Seconds Beforehand
Automatic Seizure Automatic Seizure Detection SystemDetection System
Team Members
Valerie Kuzmick, Biomedical Engineering John Lafferty, Computer Engineering April Serfass, Biomedical Engineering Doug Szperka, Computer Engineering Benjamin Zale, Computer Engineering
Epileptic EpisodesEpileptic Episodes
Encompasses Pre-Seizure and Seizure
Highly correlated neural action potential data
Epileptic Episode
Seizure Pre-
Seizure
Neural Action PotentialsNeural Action Potentials
Phase Angle MappingPhase Angle Mapping
Results Indicate Seizure Detection Rate Greater than 90%
Frequency ContentFrequency Content
Frequency (Hz)
Mag
nit
ud
e
(dB
)
Frequency ContentFrequency Content
Phase AnglePhase Angle
Seizure SignatureSeizure Signature
Pattern RecognitionPattern Recognition
Time (seconds)
Weig
hte
d S
um
of
Act
ion
Pote
nti
als
PrototypePrototype
Data AcquisitionSystem
Seizure Detection Unit
Stimulation Device
Receives Binary Data
Processes Data Using Custom Algorithm
Detects and Outputs Results