Table 2 Average predictive performance of each CNN for malignant multi-class classification model
From: Recognizing pathology of renal tumor from macroscopic cross-section image by deep learning
CNN models | mi-AUC | ma-Sn | ma-Sp | mi-Acc |
|---|---|---|---|---|
EfficientNet-B4 | 0.9091 | 0.5781 | 0.9120 | 0.8194 |
ResNet-18 | 0.9002 | 0.5249 | 0.8760 | 0.7361 |
VGG-16 | 0.9398 | 0.5774 | 0.8660 | 0.7917 |