Local wall motion classification of stress echocardiography using a Hidden Markov Model approach

In this paper, we present a new approach to regional heart functional analysis employing a Hidden Markov Model (HMM) approach for cardiac disease classification. We examine the use of an HMM for local wall motion classification based on stress echocardiography. A wall segment model is developed for a normal and an abnormal heart and the experiments are performed on rest and stress sequences. We achieve a good accuracy of classification, particularly for the normal data but with also promising results for the abnormal case.