Skip to main content

Table 10 Comparison of the difference of estimated and actual tooth models in root axis angle to occlusal plane between manual and deep learning methods (unit: degree)

From: Accuracy of deep learning-based integrated tooth models by merging intraoral scans and CBCT scans for 3D evaluation of root position during orthodontic treatment

Difference of estimated and actual tooth models

Manual method

Deep learning method

P value*

Mean ± SD

Mean ± SD

Maxilla

 Incisors

− 0.44 ± 2.61

− 0.43 ± 2.55

0.992

 Canine

− 0.27 ± 2.75

0.39 ± 1.85

0.533

 Second premolar

0.06 ± 2.89

0.68 ± 2.57

0.554

 First molar

− 0.45 ± 4.18

2.41 ± 2.74

0.088

Mandible

 Incisors

− 0.19 ± 1.83

− 2.81 ± 2.76

0.002*

 Canine

0.64 ± 1.81

− 1.09 ± 2.59

0.090

 Second premolar

0.82 ± 3.42

1.70 ± 4.01

0.200

 First molar

− 0.92 ± 2.87

− 1.50 ± 5.02

0.714

  1. SD, Standard deviation
  2. *The results of paired t test