Research Article
18F-FDG-PET/CT Whole-Body Imaging Lung Tumor Diagnostic Model: An Ensemble E-ResNet-NRC with Divided Sample Space
Table 5
Comparison of sensitivity results of different network models and classification algorithms.
| Network model | Classification algorithm | CT (%) | PET (%) | PET/CT (%) | Ensemble (%) |
| AlexNet | NNC | 99.00 | 100.00 | 99.60 | 99.87 | Softmax | 99.20 | 100.00 | 98.27 | 99.27 | NRC | 99.07 | 100.00 | 98.87 | 99.53 |
| ResNet-50 | NNC | 98.80 | 100.00 | 99.00 | 99.93 | Softmax | 98.73 | 100.00 | 98.80 | 99.87 | NRC | 99.40 | 100.00 | 99.33 | 99.73 |
|
|