Research Article
18F-FDG-PET/CT Whole-Body Imaging Lung Tumor Diagnostic Model: An Ensemble E-ResNet-NRC with Divided Sample Space
Table 4
Accuracies of different network models and classification algorithms.
| Network model | Classification algorithm | CT (%) | PET (%) | PET/CT (%) | Ensemble (%) |
| AlexNet | NNC | 96.37 | 99.57 | 96.60 | 99.10 | Softmax | 98.20 | 99.50 | 97.63 | 98.87 | NRC | 98.80 | 99.83 | 97.97 | 99.43 |
| ResNet-50 | NNC | 97.00 | 99.50 | 97.53 | 99.23 | Softmax | 98.13 | 99.63 | 97.90 | 99.33 | NRC | 99.07 | 99.80 | 98.33 | 99.57 |
|
|