Fig. 6.

Performance evaluation of custom CNN model for dental condition classification using 5-fold cross-validation. a Training history displaying loss and accuracy curves for both training and validation sets across 30 epochs, with separate lines for each fold. b Performance metrics including precision, recall, and F1-score for four dental conditions (fillings, cavity, implant, and impacted tooth) with error bars representing standard deviation across folds. c Confusion matrix aggregated from all test samples across the 5-fold cross-validation, showing the distribution of true labels versus predicted labels for the four dental condition classes