Table 5 Type identification models with PGGAN Augmentation.

From: Vision transformer and deep learning based weighted ensemble model for automated spine fracture type identification with GAN generated CT images

Ensemble Models with PGGAN Augmentation

Accuracy (%)

Recall

F1-Score

Resnet-DenseNet-Ensemble Model

59.96

0.60

0.57

VGG16-DenseNet-Ensemble Model

72.49

0.72

0.64

VGG16-Resnet-DenseNet-Ensemble Model

80.42

0.80

0.75

VGG16-Resnet-Ensemble Model

87.13

0.87

0.82

ViT

91.28

0.89

0.85

VGG16-ResNet50-ViT-Proposed Ensemble Model

93.68

0.90

0.94

Back to article page