Am Freitag, dem 29.05.2015, findet ab 13.15 Uhr das Medizintechnik-Kolloquium statt.
Vortragender: Dr. Julien Oster, University of Oxford, Institute of Biomedical Engineering
Ort: G29-301
Thema: "Cardiovascular Signal Processing for arrhythmia detection and mHealth"
Abstract: Analysis of the ECG signal implies the recognition of abnormal rhythms. Such abnormal rhythms can be induced either in the atria or the ventricles, and they will have different properties. For example, Atrial Fibrillation (AF) is the most common cardiac arrhythmia. AF is associated with irregular and unpredictable RR intervals, due to a chaotic firing of the Atrioventricular node. We have developed a machine-learning approach, combining several features of RR unpredictability, to detect short episodes of AF on RR interval time-series. A Bayesian filtering approach has also recently been suggested for the detection of Ventricular beats. This technique is based on a model of the ECG morphology, which is estimated for both normal and ventricular beats. A Switching Kalman filter is applied on the data for simultaneous signal denoising and beat detection. The introduction of an additional “X-Factor” mode allows for the exclusion of noisy or unknown heartbeats. Finally, a system allowing to acquire ECG signal on a mobile phone will be presented. The ECG signal is automatically analysed on the phone. This analysis includes heartbeat detection, Signal Quality Index estimation, and AF detection. The data can be uploaded on a Medical record system, which can be accessed by clinicians for manual annotations, which are then aggregated.
Short Bio:Julien Oster received a Master’s degree in electrical engineering in 2006, a Master’s degree in fundamental and applied mathematics in 2007, both from the Ecole Supérieure d’Electricité (Supélec), France, and a Ph.D. degree from the Université Henri Poincaré, Nancy, France, in 2009. From 2006 to 2009, he was with the Interventional and Diagnostic Adaptive Imaging Laboratory (IADI), Inserm U947, Nancy Université, Nancy, France, and worked in collaboration with Schiller Médical, Wissembourg, France. During this period, he was engaged in research on the real-time processing of electrophysiological signals acquired during Magnetic Resonance Imaging (MRI) acquisitions. In 2010, he worked at the Centre Suisse d’Electronique et de Microtechnique (CSEM), Neuchâtel, Switzerland, an independent, private, non-profit Swiss company for applied research, where he was involved in the development of biomedical signal processing algorithms for wearable technology. He was awarded a Newton International Fellowship by the Royal Society in 2010. Since 2011 he has been pursuing his research at the Institute of Biomedical Engineering (IBME), Department of Engineering of Science, University of Oxford, United-Kingdom. In 2012, Julien was awarded the J.A. Lodge award from the Institute of Engineering and Technology (IET) in recognition for a promising early-career in Biomedical Engineering. His research activities include the development of techniques for the suppression of the MagnetoHydroDynamic effect on Electrocardiogram in MRI, arrhythmia detection and classification, and mHealth applications.
Alle Interessenten sind herzlich eingeladen.
Eröffnung
