Influence of Intraoral Scanners, Operators, and Data Processing on Dimensional Accuracy of Dental Casts for Unsupervised Clinical Machine Learning: An In Vitro Comparative Study
Table 2
3-Factor ANOVA to evaluate the relationship between scanners, operators, and processing workflow and subsequent RMSE outcomes.
List of independent factors
3D scanner
F = 2.23,
IOS1 = mean ± SD = 34.25 ± 5.89
IOS2 = mean ± SD = 33.02 ± 4.93
Augmentation
F = 4.90,
Native dataset = mean ± SD = 34.54 ± 5.80
Augmented dataset = mean ± SD = 32.73 ± 4.94
Clinical operator
F = 0.24,
Operator 1 = mean ± SD = 33.43 ± 5.63
Operator 2 = mean ± SD = 33.83 ± 5.30
Native dataset
Operator 1 (mean ± SD)
Operator 2 (mean ± SD)
IOS1
35.01 ± 7.21
35.18 ± 5.66
IOS2
33.63 ± 5.21
34.35 ± 5.17
Augmented dataset
Operator 1 (mean ± SD)
Operator 2 (mean ± SD)
IOS1
33.10 ± 5.66
33.70 ± 4.95
IOS2
31.99 ± 3.89
32.12 ± 5.25
Interaction effect
(1) 1. 3D scanner vs. augmentation: F = .021, (2) 2. 3D scanner vs. clinical operator: F <.001, (3) 3. Augmentation vs. clinical operator: F = .003, (4) 4. 3D scanner vs. augmentation vs. clinical operator: F = .097,
