Table 4 Type identification models with DCGAN 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 DCGAN Augmentation

Accuracy (%)

Recall

F1-Score

Resnet-DenseNet-Ensemble Model

59.08

0.59

0.54

VGG16-DenseNet-Ensemble Model

68.49

0.69

0.63

VGG16-Resnet-DenseNet-Ensemble Model

78.13

0.78

0.72

VGG16-Resnet-Ensemble Model

84.66

0.85

0.81

ViT

89.28

0.85

0.80

VGG16-ResNet50-ViT-Proposed Ensemble Model

90.28

0.85

0.89

Back to article page