Artefact detection and removal algorithms for EEG diagnostic systems

The electroencephalogram (EEG) is a medical technology that is used in the monitoring of the brain and in the diagnosis of many neurological illnesses. Although coarse in its precision, the EEG is a non-invasive tool that requires minimal set-up times, and is suitably unobtrusive and mobile to allow continuous monitoring of the patient, either in clinical or domestic environments. Consequently, the EEG is the current tool-of-choice with which to continuously monitor the brain where temporal resolution, ease-of- use and mobility are important. Traditionally, EEG data are examined by a trained clinician who identifies neurological events of interest. However, recent advances in signal processing and machine learning techniques have allowed the automated detection of neurological events for many medical applications. In doing so, the burden of work on the clinician has been significantly reduced, improving the response time to illness, and allowing the relevant medical treatment to be administered within minutes rather than hours. However, as typical EEG signals are of the order of microvolts (μV ), contamination by signals arising from sources other than the brain is frequent. These extra-cerebral sources, known as artefacts, can significantly distort the EEG signal, making its interpretation difficult, and can dramatically disimprove automatic neurological event detection classification performance. This thesis therefore, contributes to the further improvement of auto- mated neurological event detection systems, by identifying some of the major obstacles in deploying these EEG systems in ambulatory and clinical environments so that the EEG technologies can emerge from the laboratory towards real-world settings, where they can have a real-impact on the lives of patients. In this context, the thesis tackles three major problems in EEG monitoring, namely: (i) the problem of head-movement artefacts in ambulatory EEG, (ii) the high numbers of false detections in state-of-the-art, automated, epileptiform activity detection systems and (iii) false detections in state-of-the-art, automated neonatal seizure detection systems. To accomplish this, the thesis employs a wide range of statistical, signal processing and machine learning techniques drawn from mathematics, engineering and computer science. The first body of work outlined in this thesis proposes a system to automatically detect head-movement artefacts in ambulatory EEG and utilises supervised machine learning classifiers to do so. The resulting head-movement artefact detection system is the first of its kind and offers accurate detection of head-movement artefacts in ambulatory EEG. Subsequently, addtional physiological signals, in the form of gyroscopes, are used to detect head-movements and in doing so, bring additional information to the head- movement artefact detection task. A framework for combining EEG and gyroscope signals is then developed, offering improved head-movement arte- fact detection. The artefact detection methods developed for ambulatory EEG are subsequently adapted for use in an automated epileptiform activity detection system. Information from support vector machines classifiers used to detect epileptiform activity is fused with information from artefact-specific detection classifiers in order to significantly reduce the number of false detections in the epileptiform activity detection system. By this means, epileptiform activity detection which compares favourably with other state-of-the-art systems is achieved. Finally, the problem of false detections in automated neonatal seizure detection is approached in an alternative manner; blind source separation techniques, complimented with information from additional physiological signals are used to remove respiration artefact from the EEG. In utilising these methods, some encouraging advances have been made in detecting and removing respiration artefacts from the neonatal EEG, and in doing so, the performance of the underlying diagnostic technology is improved, bringing its deployment in the real-world, clinical domain one step closer.

Investigations into the cellular and molecular changes in the amygdala in models of temporal lobe epilepsy and maternal immune activation

The amygdala is a limbic structure that is involved in many of our emotions and processing of these emotions such as fear, anger and pleasure. Conditions such as anxiety, autism, and also epilepsy, have been linked to abnormal functioning of the amygdala, owing to improper neurodevelopment or damage. This thesis investigated the cellular and molecular changes in the amygdala in models of temporal lobe epilepsy (TLE) and maternal immune activation (MIA). The kainic acid (KA) model of temporal lobe epilepsy (TLE) was used to induce Ammon’s-horn sclerosis (AHS) and to investigate behavioural and cytoarchitectural changes that occur in the amygdala related to Neuropeptide Y1 receptor expression. Results showed that KA-injected animals showed increased anxiety-like behaviours and displayed histopathological hallmarks of AHS including CA1 ablation, granule cell dispersion, volume reduction and astrogliosis. Amygdalar volume and neuronal loss was observed in the ipsilateral nuclei which was accompanied by astrogliosis. In addition, a decrease in Y1 receptor expressing cells in the ipsilateral CA1 and CA3 sectors of the hippocampus, ipsi- and contralateral granule cell layer of the dentate gyrus and ipsilateral central nucleus of the amygdala was found, consistent with a reduction in Y1 receptor protein levels. The results suggest that plastic changes in hippocampal and/or amygdalar Y1 receptor expression may negatively impact anxiety levels. Gamma-aminobutyric acid (GABA) is the main inhibitory neurotransmitter in the brain and tight regulation and appropriate control of GABA is vital for neurochemical homeostasis. GABA transporter-1 (GAT-1) is abundantly expressed by neurones and astrocytes and plays a key role in GABA reuptake and regulation. Imbalance in GABA homeostasis has been implicated in epilepsy with GAT-1 being an attractive pharmacological target. Electron microscopy was used to examine the distribution, expression and morphology of GAT-1 expressing structures in the amygdala of the TLE model. Results suggest that GAT-1 was preferentially expressed on putative axon terminals over astrocytic processes in this TLE model. Myelin integrity was examined and results suggested that in the TLE model myelinated fibres were damaged in comparison to controls. Synaptic morphology was studied and results suggested that asymmetric (excitatory) synapses occurred more frequently than symmetric (inhibitory) synapses in the TLE model in comparison to controls. This study illustrated that the amygdala undergoes ultrastructural alterations in this TLE model. Maternal immune activation (MIA) is a risk factor for neurodevelopmental disorders such as autism, schizophrenia and also epilepsy. MIA was induced at a critical window of amygdalar development at E12 using bacterial mimetic lipopolysaccharide (LPS). Results showed that MIA activates cytokine, toll-like receptor and chemokine expression in the fetal brain that is prolonged in the postnatal amygdala. Inflammation elicited by MIA may prime the fetal brain for alterations seen in the glial environment and this in turn have deleterious effects on neuronal populations as seen in the amygdala at P14. These findings may suggest that MIA induced during amygdalar development may predispose offspring to amygdalar related disorders such as heightened anxiety, fear impairment and also neurodevelopmental disorders.