Automatic Left Ventricular cavity detection using Fuzzy Isodata and connected-components labeling algorithms

Extraction of the Left Ventricle (LV) contours is essential in the quantitative analysis of cardiac function. We present a new method that employs Fuzzy Isodata (FI) and conne nents Labeling algorithms to automatically detect the LV contours. The FI algorithm is applied to each cardiac image to generate a given number of fuzzy subsets. Each heart´s substructure (aorta. is considered as fuzzy cluster. To achieve the extraction process, a labeling algorithm is used. The method is tested by application of 32 sets of 30 images each. A comparison between the ejection fractions obtained by the proposed technique and a standard method is included.