Table 15 Best model performance on original dataset (24 classes).

From: Exploring vision transformers and XGBoost as deep learning ensembles for transforming carcinoma recognition

Model combination

Testing accuracy (%)

AUC (%)

ADaDR-22

87.3

95.5

ADaDR-22 + Vision Transformer

89.1

97

ADaDR-22 + XGBoost

88.3

96.5

Back to article page