Research Article
Improved Classification of White Blood Cells with the Generative Adversarial Network and Deep Convolutional Neural Network
Table 11
10-fold cross-validation results comparison with other works.
| Model | Train: test setting | Dataset | Acc. (%) |
| ResNet-50 (Tran_aug3 + GAN_aug3) | 10-Fold CV | LISC | 97.4 | DenseNet-121 (Tran_aug3 + GAN_aug3) | 10-Fold CV | LISC | 98.3 | DenseNet-169 (Tran_aug3 + GAN_aug3) | 10-Fold CV | LISC | 98.8 | Linear discriminant analysis (LDA) [46] | 10-Fold CV | Private | 93.9 | Neural network + PCA [47] | 75%: 25% | Kanbilim | 95.0 | W-net [48] | 10-Fold CV | Private | 97.0 | W-net [48] | 10-Fold CV | LISC + private | 96.0 | Linear SVM [49] | 10-Fold CV | CellaVision | 85.0 |
|
|