Table 4 Average precision (AP) results (mean and standard deviation) of the five-fold cross-validation evaluated on the consensus test set. The best metrics are highlighted in bold
From: AI-Dentify: deep learning for proximal caries detection on bitewing x-ray - HUNT4 Oral Health Study
Model | Enamel caries | Dentine caries | Secondary lesion | mAP |
|---|---|---|---|---|
YOLOv5 M | 0.597 ± 0.034 | 0.622 ± 0.029 | 0.681 ± 0.022 | 0.633 ± 0.025 |
RetinaNet | 0.371 ± 0.023 | 0.333 ± 0.024 | 0.412 ± 0.034 | 0.372 ± 0.017 |
EfficientDet D0 | 0.310 ± 0.048 | 0.278 ± 0.017 | 0.267 ± 0.017 | 0.285 ± 0.012 |
EfficientDet D1 | 0.340 ± 0.029 | 0.387 ± 0.032 | 0.377 ± 0.028 | 0.368 ± 0.027 |