Research Article
18F-FDG-PET/CT Whole-Body Imaging Lung Tumor Diagnostic Model: An Ensemble E-ResNet-NRC with Divided Sample Space
Table 6
Comparison of specificity results of different network models and classification algorithms.
| Network model | Classification algorithm | CT (%) | PET (%) | PET/CT (%) | Ensemble (%) |
| AlexNet | NNC | 93.73 | 99.13 | 93.60 | 98.33 | Softmax | 97.20 | 99.00 | 97.00 | 98.47 | NRC | 98.53 | 99.67 | 97.07 | 99.33 |
| ResNet-50 | NNC | 95.20 | 99.00 | 96.07 | 98.53 | Softmax | 97.53 | 99.27 | 97.00 | 98.80 | NRC | 98.73 | 99.60 | 97.33 | 99.40 |
|
|