Table 4 Performance of WideResNet model
From: Application of entire dental panorama image data in artificial intelligence model for age estimation
WideResNet | |||||||
|---|---|---|---|---|---|---|---|
Number of images | train:13,220, val:1653, test:1653 | ||||||
parameters | batch8, epoch40, resize256 | ||||||
performance | Loss | Acc | Precision | Recall | F1-score | ||
Type 1 grouping | Basic prediction | 0.5683 | 0.1041 | 0.0598 | 0.0608 | 0.0599 | |
with ± 3 years deviation | 0.5686 | 0.2716 | 0.1707 | 0.1718 | 0.1709 | ||
Type 2 grouping (heuristics) | Basic prediction | 0.4098 | 0.3182 | 0.2098 | 0.2147 | 0.2071 | |
with ± 3 years deviation | 0.4091 | 0.7623 | 0.6476 | 0.649 | 0.6437 | ||