Wall Motion Classification of Stress Echocardiography Based on Combined Rest-and-Stress Data

In this paper, we present a new framework that performs automated local wall motion analysis based on the combined information derived from a rest and stress sequence (a full stress echocardiography study). We introduce a Hidden Markov Model (HMM) approach for cardiac disease classification of stress echocardiography since the cardiac data inherits the time-varying and sequential properties. A wall segment model is developed for a normal and an abnormal heart and experiments are performed on rest, stress and rest-and-stress sequences. Combined rest-and-stress analysis shows an improvement in classification accuracy (84.17%) over individual rest (73.33%) and stress (68.33%) analysis.

• Type: Conference
• Year: 2008
• Where: MICCAI
• Authors: Sarina Mansor, Nicholas P. Hughes, J. Alison Noble
• Keywords: Cardiac Disease Classification, Medical Imaging, MICCAI 2008, Stress Echocardiography Study, Stress Sequence