Table 7. Performance evaluation metrics for WBC classification.
The performance accuracy percentages and the evaluation parameters such as accuracy, precision, recall, sensitivity, specificity, and F-measures used to assess the effectiveness of various classification algorithms for WBCs.
| Author | Classification | Performance accuracy % | Evaluation parameter |
|---|---|---|---|
| Hegde et al. (2019) | TissueQuant algorithm | 96.5 | Accuracy, precision and recall |
| Liang et al. (2018) | CNN-RNN | 90.79 | Accuracy |
| Hegde et al. (2018) | Hybrid-classifier (SVM & NN) | 86 and 95 | Sensitivity and accuracy |
| Di Ruberto, Loddo & Putzu (2016) | SVM | 99.73 | Accuracy |
| Liu & Long (2019) | Augmented enhanced bagging ensemble | 84, 85 and 84 | Precision, recall and F1 score |
| Vogado et al. (2018) | SVM | 99 | Precision, recall, accuracy and kappa index |
| Othman, Mohammed & Ali (2017) | MLP-BP neural network | 96 | Accuracy |
| Zhao et al. (2017) | Granularity feature and SVM | 85.3 and 97.1 | Sensitivity and precision |
| Agaian, Madhukar & Chronopoulos (2018) | SVM | 98.5, 97.8, 95.7 and 97.1 | Precision, specificity, sensitivity and F-measures |