Table 2.

Performance metrics of the general, reperfused and non-reperfused models among (a) reperfused and (c) non-reperfused patients (average values ± standard deviation). Bold values correspond to the best value of the respective evaluation metric (column-wise). P-values from two-sided wilcoxon signed-rank tests comparing the general, reperfused and non-reperfused models among (b) reperfused and (d) non-reperfused patients. Bold values correspond to significant differences, with (*) indicating P < 0.05, (**) indicating P < 0.01 and (***) indicating P < 0.001. Note that tests were not corrected for multiple comparisons, and correspond to independent two-by-two comparisons.

(a) Performance metrics among reperfused patients
Model	DSC	VS	Precision	Recall	HD
General	0.43 ± 0.24	0.69 ± 0.27	0.55 ± 0.28	0.43 ± 0.25	33.23 ± 15.6
Reperfused	0.44 ± 0.25	0.70 ± 0.27	0.50 ± 0.27	0.50 ± 0.26	38.58 ± 18.1
Non-reperfused	0.35 ± 0.21	0.57 ± 0.28	0.60 ± 0.25	0.31 ± 0.24	40.05 ± 15.6

(b) Model comparisons among reperfused patients
Two-sided Test	DSC P-value	VS P-value	Precision P-value	Recall P-value	HD P-value
General vs Reperfused	0.43	0.53	3.7e-6 (***)	1.4e-6 (***)	0.048 (*)
General vs Non-Reperfused	1.4e-8 (***)	4.3e-6 (***)	0.0069 (**)	1.0e-10 (***)	0.0041 (**)
Reperfused vs Non-Reperfused	2.3e-8 (***)	1.6e-5 (***)	2.9e-7 (***)	2.7e-11 (***)	0.65

(c) Model performance among non-reperfused patients
Model	DSC	VS	Precision	Recall	HD
General	0.44 ± 0.21	0.66 ± 0.26	0.39 ± 0.25	0.63 ± 0.21	30.61 ± 16.1
Reperfused	0.44 ± 0.22	0.63 ± 0.25	0.36 ± 0.23	0.69 ± 0.22	44.53 ± 16.7
Non-reperfused	0.47 ± 0.17	0.74 ± 0.13	0.49 ± 0.22	0. 52 ± 0.21	37.70 ± 17.7

(d) Model comparisons among non-reperfused patients
Two-sided Test	DSC P-value	VS P-value	Precision P-value	Recall P-value	HD P-value
General vs Reperfused	0.93	0.55	0.13	0.021 (*)	0.0023 (**)
General vs Non-Reperfused	0.17	0.21	0.0016 (**)	0.00084 (***)	0.11
Reperfused vs Non-Reperfused	0.13	0.034 (*)	0.00067 (***)	5.3e-5 (***)	0.12