Patient-specific epileptic seizure detection in long-term EEG recording in paediatric patients with intractable seizures
Zabihi, Morteza (2013)
Zabihi, Morteza
2013
Master's Degree Programme in Biomedical Engineering
Tieto- ja sähkötekniikan tiedekunta - Faculty of Computing and Electrical Engineering
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Hyväksymispäivämäärä
2013-06-05
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:tty-201306121202
https://urn.fi/URN:NBN:fi:tty-201306121202
Tiivistelmä
Over recent years, due to the increase in the epileptic patient population, issues of diagnosing and treatment of epilepsy have become more and more prominent and much research has been done in this field in consequence. However, there are still many gaps and lack of knowledge in interpreting Electroencephalograph (EEG) signals in order to solve the problem.
Particular problems in this area include difficulties in detecting the seizure events (due to the different seizure types and their variability from patient to patient or even in an individual over time), and dealing with long-term EEG recordings, which is an onerous and time consuming task for electroencephalographers.
The thesis discusses the two problem areas using EEG data from four subjects with overall 21 hours of recording from the CHB-MIT scalp benchmark EEG dataset. We propose a patient specific seizure detection technique, which selects the optimal feature subsets, and train a dedicated classifier for each patient in order to maximize the classification performance. To exploit the characteristics of a patient’s EEG pattern as much as possible, we used a large set of features in the proposed framework, namely time domain, frequency domain, time-frequency domain and nonlinear features, and selected the most crucial features among them by using Conditional Mutual Information Maximization (CMIM) technique. We further performed extensive comparative evaluations against 6 other feature selection methods to demonstrate the superiority of the CMIM.
Support Vector Machine (SVM) with the linear kernel is used as the classifier. The experimental results show a delicate classification performance over the test set, i.e. an average of 90.62% sensitivity and 99.32% specificity are acquired when all channels and recordings are used to form a composite feature vector. In addition, an average sensitivity and specificity rates of 93.78% and 99.05% are obtained using CMIM, respectively.
Particular problems in this area include difficulties in detecting the seizure events (due to the different seizure types and their variability from patient to patient or even in an individual over time), and dealing with long-term EEG recordings, which is an onerous and time consuming task for electroencephalographers.
The thesis discusses the two problem areas using EEG data from four subjects with overall 21 hours of recording from the CHB-MIT scalp benchmark EEG dataset. We propose a patient specific seizure detection technique, which selects the optimal feature subsets, and train a dedicated classifier for each patient in order to maximize the classification performance. To exploit the characteristics of a patient’s EEG pattern as much as possible, we used a large set of features in the proposed framework, namely time domain, frequency domain, time-frequency domain and nonlinear features, and selected the most crucial features among them by using Conditional Mutual Information Maximization (CMIM) technique. We further performed extensive comparative evaluations against 6 other feature selection methods to demonstrate the superiority of the CMIM.
Support Vector Machine (SVM) with the linear kernel is used as the classifier. The experimental results show a delicate classification performance over the test set, i.e. an average of 90.62% sensitivity and 99.32% specificity are acquired when all channels and recordings are used to form a composite feature vector. In addition, an average sensitivity and specificity rates of 93.78% and 99.05% are obtained using CMIM, respectively.