Additional file 1 of Automated quantification of T1 and T2 relaxation times in liver mpMRI using deep learning: a sequence-adaptive approach

Additional file 1: Table e1. Comparison between mean segmental T1 and T2 relaxation times as quantified by the algorithm and the human reader in segmental testing datasets. Figure e1. Top-20 parameter configurations of the sequence-adaptive mpMRI quantification algorithm on the optimization dataset. The f-score represents the configuration performance according to the objective function f. The Mean ICC Value represents the mean ICC and standard deviation over all segments and all available mapping sequences per configuration. The Total ROI Measurements refer to the number of measurements the algorithm performed under the given configuration. The percentage represents the number of measurements performed by the algorithm compared to the human reader. The x-axis shows each configuration consisting of the proposed algorithm components, presented as follows: _____, where SS means NCC-based source slice subselection heuristic. Figure e2. Scatterplots show concordance between automated and manual parametric T1 and T2 relaxation time quantification for the internal testing dataset. Perfect concordance is represented by a 45-degree line (black line), and the observed concordance is represented by the Deming regression slope (red line). All pairwise comparisons show a significant Spearman correlation (p < 0.001). Best viewed in screen.