Table 4.

Mean metrics for comparing our method to expert annotators, displayed separately for each slice.

	Automated vs expert annotation			Agreement of three experts (interobserver)
	Basal	Midventricular	Apical	Basal	Midventricular	Apical
IoU - Jaccard index $\Uparrow$ ($\mathrm{\%}$)	84.06${}^{\mathrm{a}}$	81.83${}^{\alpha }$	73.13${}^{\mathcal{A}}$	87.5${}^{\mathrm{b}}$	85.49${}^{\beta }$	81.78${}^{\mathcal{B}}$
Dice score$\Uparrow$ ($\mathrm{\%}$)	90.09${}^{\mathrm{a}}$	88.24${}^{\alpha }$	79.86${}^{\mathcal{A}}$	92.62${}^{\mathrm{b}}$	90.98${}^{\beta }$	88.12${}^{\mathcal{B}}$
Hausdorff distance $\Downarrow$ (mm)	3.59${}^{\mathrm{a}}$	3.52${}^{\alpha }$	7.41${}^{\mathcal{A}}$	2.51${}^{\mathrm{b}}$	2.6${}^{\beta }$	2.91${}^{\mathcal{B}}$
Mean surface distance $\Downarrow$ (mm)	1.57${}^{\mathrm{a}}$	1.59${}^{\alpha }$	3.37${}^{\mathcal{A}}$	1.05${}^{\mathrm{b}}$	1.12${}^{\beta }$	1.39${}^{\mathcal{B}}$

For each metric and each slice, differences are statistically significant ($p<0.001$, also denoted with different lettering in superscripts). $\Uparrow$ indicates higher-the-better metrics, while metrics $\Downarrow$ are lower-the-better.