Table 3 Image-level NSCLC classification results on test instances. Mean values and 95% confidence intervals are provided
Partition | Method | Accuracy | Sensitivity | Specificity | AUC |
|---|---|---|---|---|---|
Validation | DenseNet | 0.86 [0.84–0.88] | 0.83 [0.8–0.86] | 0.89 [0.86–0.92] | 0.94 [0.93–0.96] |
Validation | WSUnet | 0.87 [0.85–0.89] | 0.86 [0.83–0.88] | 0.88 [0.86–0.9] | 0.95 [0.93–0.96] |
Validation | sCNN | 0.88 [0.86–0.89] | 0.9 [0.87–0.92] | 0.85 [0.82–0.88] | 0.95 [0.93–0.96] |
Test | DenseNet | 0.87 [0.86–0.88] | 0.86 [0.85–0.87] | 0.88 [0.87–0.89] | 0.94 [0.94–0.95] |
Test | WSUnet | 0.86 [0.85–0.87] | 0.87 [0.86–0.89] | 0.85 [0.84–0.86] | 0.94 [0.94–0.95] |
Test | sCNN | 0.88 [0.87–0.89] | 0.84 [0.83–0.85] | 0.93 [0.92–0.94] | 0.96 [0.95–0.96] |