Research Article
18F-FDG-PET/CT Whole-Body Imaging Lung Tumor Diagnostic Model: An Ensemble E-ResNet-NRC with Divided Sample Space
Table 8
Comparison of MCC results of different network models and classification algorithms.
| Network model | Classification algorithm | CT (%) | PET (%) | PET/CT (%) | Ensemble (%) |
| AlexNet | NNC | 92.86 | 99.14 | 93.37 | 98.21 | Softmax | 96.42 | 99.00 | 95.27 | 97.74 | NRC | 97.66 | 99.67 | 95.95 | 98.87 |
| ResNet-50 | NNC | 94.06 | 99.00 | 95.11 | 98.48 | Softmax | 96.27 | 99.27 | 95.82 | 98.67 | NRC | 98.14 | 99.60 | 96.69 | 99.13 |
|
|