[hal-01077143] Improved estimation of the left ventricular ejection fraction using a combination of independent automated segmentation results in cardiovascular magnetic resonance imaging

This work aimed at combining different segmenta-tion approaches to produce a robust and accurate segmentation result Three to five segmentation results of the left ventricle were combined using the STAPLE algorithm and the reliability of the resulting segmentation was evaluated in comparison with the result of each individual segmentation method This comparison was performed using a supervised approach based on a reference method Then we used an unsupervised statistical evaluation the extended Regression Without Truth eRWT that ranks different methods according to their accuracy in estimating a specific biomarker in a population The segmentation accuracy was evaluated by focusing on the left ventricular ejection fraction LVEF estimate resulting from the LV contour delineation using a public cardiac cine MRI database Eight different segmentation methods including three expert delineations were studied and sixteen combinations of the five automated methods were investigated The supervised and unsupervised evaluations demonstrated that in most cases STAPLE results provided better estimates of the LVEF than individual automated segmentation methods In addition LVEF obtained with STAPLE were within inter-expert variability Overall combining different automated segmentation methods improved the reliability of the segmenta-tion result compared to that obtained using an individual method



from HAL : Dernières publications http://ift.tt/1sWztBO