Automatic computation of left ventricle ejection fraction from dynamic ultrasound images

Barcaro U., Moroni D., Salvetti O.

Image Processing  Computer Vision and Pattern Recognition  Computer Graphics and Computer-Aided Design 

Left Ventricle (LV) Ejection Fraction (EF) is a fundamental parameter for heart function assessment. Being based on border tracing, however, manual computation of EF is time-consuming and extremely prone to inter- and intra-observer variability. In this paper we present an automatic method for EF computation which provides results in agreement with those provided by expert observers. The segmentation strategy consists of two stages: first, the region of interest is identified by means of mimetic criteria; then, the identified region is used for initialization of an active contour based on a variational formulation of level set methods, which provides accurate segmentation of the LV cavity. Volume calculation is then performed according to the conventional Simpson's rule and, finally, the EF is computed.

Source: Pattern recognition and image analysis 18 (2008): 351–358. doi:10.1134/S1054661808020247

Publisher: Distributed by Allen Press,, Lawrence, KS , Stati Uniti d'America

Metrics