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

Progress in Orthodontics

Table 8 Comparison of the difference of estimated and actual tooth models in arch width between manual and deep learning methods (unit: mm)

Difference of estimated and actual tooth models	Manual method	Deep learning method	P value*
Difference of estimated and actual tooth models	Mean ± SD	Mean ± SD	P value*
Maxilla
Inter-incisor width U1	− 0.32 ± 0.73	− 0.06 ± 0.84	0.238
Inter-incisor width U2	− 0.84 ± 1.13	− 0.84 ± 1.13	0.184
Inter-canine width	0.34 ± 0.54	0.36 ± 0.73	0.966
Inter-premolar width	− 1.12 ± 0.60	− 0.06 ± 1.05	0.079
Inter-molar width	− 0.90 ± 1.11	0.20 ± 0.95	0.077
Mandible
Inter-incisor width L1	0.02 ± 0.62	0.02 ± 0.29	0.088
Inter-incisor width L2	− 0.44 ± 0.64	− 0.32 ± 0.63	0.695
Inter-canine width	− 0.04 ± 1.02	− 0.76 ± 1.10	0.208
Inter-premolar width	− 1.72 ± 0.90	− 0.80 ± 0.89	0.172
Inter-molar width	− 1.10 ± 1.61	− 1.04 ± 2.03	0.920

SD, Standard deviation
*The results of paired t test. U1, maxillary central incisors; U2, maxillary lateral incisors; L1, mandibular central incisors; L2, mandibular lateral incisors