Table 4 Classification performance comparison
From: Vi-GeN 1.0: GAN-Augmented Vision Transformer Pipeline for Diversified Pneumonia Classification
Model | Accuracy | Sensitivity | Specificity | F1-score | AUC-ROC |
|---|---|---|---|---|---|
ViT (without augmentation) | 92.1% | 91.5% | 92.8% | 92.0% | 0.944 |
ViT + Vi-GeN 1.0 (augmented) | 97.3% | 98.1% | 96.5% | 97.5% | 0.985 |