Left Ventricle Cavity Segmentation from Cardiac Cine MRI

Automatic left ventricle segmentation plays an important role in the evaluation of cardiac function. In this paper, we proposed a method for segmenting the left ventricle cavity by applying pixel classification method. In this method, we used different features (i.e. the output of median filter, the gradient magnitude, the largest eigenvalues, and the gray value), and the principal component analysis (PCA) in building the feature vectors used with the KNN classifier in the segmentation of the LV cavity. We evaluated our method by sensitivity, and specificity, and we achieved good results in the segmentation process reached to 95.61% sensitivity, and 98.9% specificity.