Table 3 Evaluation with different numbers of involved CNN models
From: A novel fusion algorithm for benign-malignant lung nodule classification on CT images
N | Accuracy | Sensitivity | Specificity | Precision | F1 Score | AUC | Size | Time |
|---|---|---|---|---|---|---|---|---|
4 | 92.49% | 87.94% | 95.39% | 92.70% | 0.9016 | 0.9559 | 14.897743M | 1.7ms |
5 | 93.25% | 89.22% | 95.82% | 92.46% | 0.9114 | 0.9629 | 14.897747M | 1.7ms |
6 | 92.31% | 87.10% | 95.74% | 93.10% | 0.9000 | 0.9499 | 14.897751M | 1.7ms |
7 | 92.12% | 87.95% | 94.77% | 91.85% | 0.8971 | 0.9478 | 14.897755M | 1.7ms |