Recent studies in brain science and neurological medicine paid a particular attention to develop machine learning-based techniques for the detection and prediction of epileptic seizures with electroencephalogram (eeG). As a noninvasive monitoring method to record brain electrical activities, eeG has been widely used for capturing the underlying dynamics of disruptive neuronal responses across the brain in real-time to provide clinical guidance in support of epileptic seizure treatments in practice. In this study, we introduce a novel dynamic learning method that first infers a time-varying network constituted by multivariate eeG signals, which represents the overall dynamics of the brain network, and subsequently quantifies its topological property using graph theory. We demonstrate the efficacy of our learning method to detect relatively strong synchronization (characterized by the algebraic connectivity metric) caused by abnormal neuronal firing during a seizure onset. The computational results for a realistic scalp EEG database show a detection rate of 93.6% and a false positive rate of 0.16 per hour (FP/h); furthermore, our method observes potential pre-seizure phenomena in some cases. The human brain is undoubtedly one of the most complex dynamic systems known to mankind, which consists of billions of interconnected neurons 1. The connectivity patterns across different brain regions could convey evidences for advancing and supporting the understanding of cognitive and behavioral functions 2-5. In the past decades, many research studies have been devoted to discovering the process and mechanisms that govern the communication between neurons; in particular, how and why neuronal networks are formed for various neurological disorders. Epilepsy is one of the most common central nervous system disorders, following Alzheimer's disease and stroke. According to recent statistics 6 , nearly 4% of people across different ages are diagnosed with epilepsy and suffer from epileptic seizure occurrence and recurrence during their lifetimes. Epileptic seizures develop with a sudden abnormal surge of electrical activities of pathological, synchronous neuronal firing in all brain regions or some parts. Seizures can be controlled with medications and/or invasive surgeries in 70% of diagnosed patients 7. However, prompt detection or even prediction of seizure onsets remains a critical and challenging task to date because of its high variation patterns of occurrence and manifestation from one individual to another. To this end, a lot of efforts have been given to developing subject-specific, data-driven methodologies aiming at ultimately improving individualized seizure onset detection and prediction 8. Electroencephalography (EEG) recordings in high temporal resolution, regardless of arguable evidence of poor spatial resolution and low signal-to-noise ratio (SNR), are useful amongst neuroimaging techniques allowing clinicians to collect and monitor global neuronal activity information in the brain of epileptic patients. Epilepti...

No abstract

No abstract

No abstract

No abstract