Use of matched filters for extraction of left ventricular features in two-dimensional short-axis echocardiographic images

ABSTRACTAn automatic method for identification of the center point of the left ventricle of the myocardium during systole is described for 2-dimensional short—axis echocardiographic im-ages. This method, based on the use of large matched filters, identifies a single fixed centerpoint during systole, by locating the three features: the epicardial boundary along the pos-tenor wall, the epicardial boundary along the anterior wall, and the endocardial boundary along the anterior wall. Thus, it provides a first step towards the long term goal of auto- matic recognition of the endocardial and epicardial boundaries. An index associated withthe filter used to approximate the epicardial boundary along the posterior wall provides anindication of the quality of the image and a reliability measurement of the estimate. Whentested on 207 image sequences, 18 images were identified by this index (applied to the enddiastolic frame) as unsuitable for processing. In the remaining 189 image sequences, 16 ofthe automatically defined center points were judged poor when compared with estimatesmade on the end diastolic frame by an independent expert observer.