Table 3 The difference in mean T₁ between automated segmentation and manual segmentation, as well as between measurements by different human observers. The first two columns show the difference between automated and manual segmentations on a test set of 100 subjects for the proposed PHiSeg and U-Net networks. The third to fifth columns show the inter-observer variability, which is evaluated on a randomly selected set of 30 subjects, each being analysed by three different human observers (O1, O2, O3) independently. The mean and standard deviation (in parentheses) of the absolute difference and relative difference are reported

From: Automated quantification of myocardial tissue characteristics from native T₁ mapping using neural networks with uncertainty-based quality-control