Table 6 Summary of results using proposed custom CNN with GAP layer.
From: Computer-aided cholelithiasis diagnosis using explainable convolutional neural network
Optimizer | Batch size | Accuracy | Precision | Recall | Specificity | F1-score | AUC score | ||
|---|---|---|---|---|---|---|---|---|---|
Training | Validation | Testing | |||||||
SGD | 32 | 0.55 | 0.61 | 0.48 | 0.48 | 0.23 | 0.71 | 0.31 | 0.49 |
RMSPROP | 32 | 0.95 | 0.83 | 0.87 | 0.89 | 0.84 | 0.88 | 0.86 | 0.84 |
ADAM | 32 | 0.98 | 0.83 | 0.88 | 0.90 | 0.85 | 0.89 | 0.87 | 0.87 |
