Left ventricle segmentation from cardiac cine MRI to detect cardiac abnormalities

Abstract

Ma g netic Resonance Ima g in g (MRI) has become one of the most promising technolo g ies for the treatment of cardiac abnormalities. Nowadays, Image processing techniques are widely used in medical field to detect cardiac disorders. In this paper we present a simple and novel algorithm to automatically se g ment the Left Ventricle (LV) in short axis cardiac cine MRI. The frames of the cine MRI of a patholo g ical and five normal patients are processed using enhancement, thresholdin g and morpholo g ical operations. The variation in the area of the left ventricle is calculated for the entire cardiac cycle for normal and diseased conditions. The pattern of variation in area for abnormal is si g nificantly different from that of normal and hence could be used as a tool for detecting abnormal cardiac motion.Index Terms-Cine MRI, cardiac abnormalities, histo g ram equalization, morpholo g ical operations, thresholdin g .