Table 18 Final comparison of the most effective models from both datasets.

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

Model combination

Dataset

Testing accuracy (%)

AUC (%)

ADaDR-22 + XGBoost

Modified (14 Classes)

92.2

97.8

ADaDR-22 + Vision Transformer

Modified (14 Classes)

93.4

98.8

Back to article page