Semi-automatic segmentation of the left ventricle in CINE MR datasets by linked radial active model (LRAM)

Abstract

Heart failures (cardiac infarction) are of increasing importance due to increasing life expectation. For clinical diagnosis parameters for the condition of hearts are needed and can be derived automatically by imaging processing. In this work we present an efficient method to segment the left ventricle (LV) in heart MR data from rats using two linked active contour models working in a spherical coordinate system. The initial model used for the active contour scheme is generated from user given points by a radial interpolation algorithm. The model was developed on healthy heart data and was tested on 15 different data sets and the results are presented.