Electrocardiographic Imaging (ECGI) is a promising tool to non-invasively map the electrical activity of the heart using body surface potentials (BSPs) and the patient specific anatomical data. One of the first steps of ECGI is the segmentation of heart and torso. However, the inter-operator variation in cardiac segmentations may influence the ECGI solution. This effect reamains however unquantified. In this work, we study the effect of segmentation uncertainty on the ECGI estimation of the cardiac activity with 262 shape models generated from fifteen different segmentations. Our results confirm that this variation in cardiac segmentation induces an additional error in the ECGI solution. Moreover, these results also indicate that septal stimulation is more sensitive to segmetation variability than LV, RV and apical stimulation.