From: Automatic detection of developmental stages of molar teeth with deep learning
Models | Precision | Recall | F1-Score | |||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
M1 | M2 | M3 | M4 | M1 | M2 | M3 | M4 | M1 | M2 | M3 | M4 | |
Cascade R-CNN | 0.72 | 0.86 | 0.83 | 0.89 | 1.00 | 0.69 | 0.74 | 0.99 | 0.84 | 0.77 | 0.78 | 0.94 |
YOLOv3 | 0.71 | 0.86 | 0.76 | 0.89 | 0.83 | 0.64 | 0.72 | 0.90 | 0.77 | 0.73 | 0.74 | 0.89 |
HTC | 0.76 | 0.79 | 0.83 | 0.90 | 0.97 | 0.70 | 0.72 | 0.99 | 0.85 | 0.77 | 0.77 | 0.94 |
DetectoRS | 0.71 | 0.84 | 0.80 | 0.87 | 0.96 | 0.65 | 0.73 | 0.98 | 0.82 | 0.73 | 0.76 | 0.92 |
SSD | 0.63 | 0.68 | 0.61 | 0.73 | 0.45 | 0.63 | 0.57 | 0.93 | 0.53 | 0.65 | 0.58 | 0.82 |
EfficientNet | 0.56 | 0.73 | 0.69 | 0.75 | 0.89 | 0.66 | 0.65 | 0.90 | 0.70 | 0.69 | 0.67 | 0.82 |
NAS-FPN | 0.60 | 0.74 | 0.76 | 0.90 | 0.94 | 0.69 | 0.60 | 0.90 | 0.73 | 0.71 | 0.67 | 0.90 |
Deformable DETR | 0.78 | 0.88 | 0.85 | 0.94 | 0.97 | 0.72 | 0.76 | 0.96 | 0.86 | 0.79 | 0.80 | 0.92 |
PAA | 0.51 | 0.75 | 0.72 | 0.75 | 0.90 | 0.65 | 0.69 | 0.93 | 0.65 | 0.69 | 0.70 | 0.83 |