Table 5

Statistical table

Data typeCompared groupsTestResultsdf
F1-score (%); Fig. 2Final vs no refin., no
cluster, no size thr.
Repeated-measures
ANOVA
F = 40.333
Data typeCompared groupsTestConfidence leveldf
95%Bonferroni corr.
F1-score (%); Fig. 2Final vs no refin.Paired t test10.44% to 19.36%9.18% to 20.62%10
F1-score (%); Fig. 2Final vs no clusterPaired t test0.60% to 1.90%0.41% to 2.08%10
F1-score (%); Fig. 2Final vs no size thr.Paired t test2.34% to 4.15%2.08% to 4.41%10
F1-score (%), acute
slices; Fig. 3
Algorithm vs humansPaired t test−5.67% to −2.25%-10
F1-score (%), Cry. fix.
n.c.; Fig. 3
Algorithm vs humansPaired t test−16.89% to −4.15%-6
F1-score (%), Che. fix.
n.c.; Fig. 3
Algorithm vs humansPaired t test−8.10% to −3.45%-8
F1-score (%), acute slicesAlgorithm vs ilastikPaired t test16.20% to 29.27%-10
F1-score (%), Cry. fix. n.c.Algorithm vs ilastikPaired t test12.42% to 24.89%-6
F1-score (%), Che. fix. n.c.Algorithm vs ilastikPaired t test6.46% to 27.01%-8
Vesicle count; Fig. 6Algorithm vs humansPearson corr.0.7288 to 0.9494-42
Vesicle nnd; Fig. 6Algorithm vs humansPearson corr.0.2838 to 0.8309-42
Vesicle area; Fig. 6Algorithm vs humansPearson corr.0.4979 to 0.8949-42