Table 5. Consolidated results of Kruskal–Wallis H and post-hoc tests.
Metric | Kruskal-Wallis H summary | Mean ranks | Post-hoc | |
---|---|---|---|---|
Accuracy | χ2(5) = 15.508, p = 0.008 | AlexNet | 11.20 | Xception & ResNet-50 (p = 0.005) Xception & VGG-16 (p = 0.007) Customized & ResNet-50 (p = 0.017) |
VGG-16 | 22.30 | |||
ResNet-50 | 23.00 | |||
Xception | 7.20 | |||
DenseNet-121 | 19.60 | |||
Customized | 9.70 | |||
AUC | χ2(5) = 18.958, p = 0.002 | AlexNet | 13.00 | Xception & ResNet-50 (p = 0.034) Xception & VGG-16 (p = 0.030) Xception & DenseNet-121 (p = 0.014) |
VGG-16 | 21.70 | |||
ResNet-50 | 21.50 | |||
Xception | 4.50 | |||
DenseNet-121 | 22.90 | |||
Customized | 9.40 | |||
Sensitivity | χ2(5) = 5.518, p = 0.356 | AlexNet | 16.20 | – |
VGG-16 | 17.30 | |||
ResNet-50 | 15.80 | |||
Xception | 11.40 | |||
DenseNet-121 | 21.80 | |||
Customized | 10.50 | |||
Specificity | χ2(5) = 6.639, p = 0.249 | AlexNet | 9.80 | – |
VGG-16 | 20.70 | |||
ResNet-50 | 21.30 | |||
Xception | 13.30 | |||
DenseNet-121 | 14.10 | |||
Customized | 13.80 | |||
F1-score | χ2(5) = 14.798, p = 0.011 | AlexNet | 11.70 | Xception & ResNet-50 (p = 0.005) Xception & VGG-16 (p = 0.006) Xception & DenseNet-121 (p = 0.023) |
VGG-16 | 22.20 | |||
ResNet-50 | 22.60 | |||
Xception | 6.90 | |||
DenseNet-121 | 19.50 | |||
Customized | 10.10 | |||
MCC | χ2(5) = 14.487, p = 0.013 | AlexNet | 11.30 | Xception & ResNet-50 (p = 0.007) Xception & VGG-16 (p = 0.008) Xception & DenseNet-121 (p = 0.034) Customized & ResNet-50 (p = 0.021) |
VGG-16 | 22.30 | |||
ResNet-50 | 22.60 | |||
Xception | 7.60 | |||
DenseNet-121 | 19.40 | |||
Customized | 9.80 |
Notes.
Bold text indicate the performance measures of the best-performing model/s.