Research Article
18F-FDG-PET/CT Whole-Body Imaging Lung Tumor Diagnostic Model: An Ensemble E-ResNet-NRC with Divided Sample Space
Table 7
Comparison of
-value results of different network models and classification algorithms.
| Network model | Classification algorithm | CT (%) | PET (%) | PET/CT (%) | Ensemble (%) |
| AlexNet | NNC | 96.46 | 99.57 | 96.70 | 99.11 | Softmax | 98.22 | 99.50 | 97.65 | 98.87 | NRC | 98.80 | 99.83 | 97.98 | 99.43 |
| ResNet-50 | NNC | 97.05 | 99.50 | 97.57 | 99.24 | Softmax | 98.14 | 99.63 | 97.92 | 99.34 | NRC | 99.07 | 99.80 | 98.35 | 99.57 |
|
|