Skip to main content

Table 3 Detailed Summary and distribution of the dataset used for the training and testing of the CNN

From: Influence of growth structures and fixed appliances on automated cephalometric landmark recognition with a customized convolutional neural network

Subgroup characteristics

Train Dataset

Test Dataset

No fixed orthodontic appliances

Permanent Dentition

Group I/1

175

40%

141

31%

No fixed orthodontic appliances

Mixed Dentition

Group I/2

110

26%

164

36%

Orthodontic brackets and/or bands and other fixed orthodontic appliances

Permanent Dentition

Group II

134

31%

135

29%

Orthodontic brackets and/or bands and other fixed orthodontic appliances

Mixed Dentition

Not included in the comparative analysis

11

3%

20

4%

Total Number of images (n)

430

460