Confusion matrix of the classification results (in %) for the images of the testing set
| Predicted class | |||||||
| Lymphoid blasts | Pathological promyelocytes | Myeloid blasts | Reactive lymphocytes | Lymphocytes | Monocytes | ||
| True class | Lymphoid blasts | 78.9 | 1.5 | 16.5 | 2.1 | 1.0 | 0.0 |
| Pathological promyelocytes | 14.0 | 72.6 | 13.4 | 0.0 | 0.0 | 0.0 | |
| Myeloid blasts | 14.0 | 1.6 | 80.8 | 1.6 | 0.1 | 1.9 | |
| Reactive lymphocytes | 0.4 | 0.0 | 1.1 | 97.7 | 0.0 | 0.8 | |
| Lymphocytes | 0.0 | 0.0 | 0.0 | 2.0 | 97.6 | 0.4 | |
| Monocytes | 1.3 | 0.4 | 1.3 | 4.0 | 0.0 | 93.0 | |
Rows indicate the true class and columns represent the predicted class supplied by the classifier. Diagonal values are the true positive rates for each cell type. The overall classification accuracy was 85.8%.