The Lecture is held by:
Prof. Dr.-Ing. Jörg Lohscheller
Fachhochschule Trier, Fachbereich Informatik - Medizininformatik
D-54208 Trier, Germany.

Abstract

For the diagnosis of pathological voices it is of particular importance to examine the dynamic properties of the underlying vocal fold (VF) movements occurring at a fundamental frequency of 100 - (300 Hz). To this end, a patient's laryngeal oscillation patterns are captured with state-of-the-art endoscopic high-speed (HS) camera systems capable of recording 4000 frames/second. Clinical analysis of these HS videos is commonly performed in a subjective manner via slow-motion playback. Hence, the resulting diagnoses are inherently error-prone, exhibiting high inter-rater variability. In this talk an objective method is presented to overcome this drawback. It employs a quantitative description and classification approach based on a novel image analysis strategy called Phonovibrography. By extracting the relevant VF movement information from HS videos the spatio-temporal patterns of vocal fold dynamics are displayed within a single image the so called Phonovibrogram (PVG). It will be shown that PVG analysis in combination with machine learning (ML) algorithms can be used to obtain clinically meaningful classification of voice disorders.

Registration not necesseary but for further information please contact: Pia Holm, , Phone: 4480 5130