Skip to main content

Table 3 Evaluation metrics for caries classification according to the types of teeth (molar and premolar)

From: Tooth caries classification with quantitative light-induced fluorescence (QLF) images using convolutional neural network for permanent teeth in vivo

Evaluation metrics

Q-ray images

Molar

Premolar

True-positive case, n (%)

262 (60.5)

141 (41.1)

False-positive case, n (%)

38 (8.8)

29 (8.5)

True-negative case, n (%)

96 (22.2)

145 (42.3)

False-negative case, n (%)

37 (8.5)

28 (8.2)

Sensitivity

0.876

0.834

Specificity

0.716

0.829

Negative predictive value

0.722

0.834

f1-scores

0.875

0.832

Precision

0.873

0.829

Accuracy

0.827

0.834

AUC

0.881

0.905