Table 4 Comparison of MD width, CCH, and segmentation time among three segmentation groups.

From: Accuracy and efficiency of automatic tooth segmentation in digital dental models using deep learning

 

LS

DS

AS

REF

pa value

Post hoc test

MD width (mm)

8.28 (8.15, 8.41)

8.63 (8.49, 8.76)

8.51 (8.37, 8.65)

8.52 (8.40, 8.63)

 < 0.001*

DS > REF, AS > LS

CCH (mm)

7.65 (7.52, 7.78)

7.52 (7.39, 7.65)

7.58 (7.45, 7.70)

7.62 (7.50, 7.74)

 < 0.001*

LS, REF > DS, AS

Time (sec)

424.17 (404.28, 444.05)

150.73 (140.70, 160.77)

57.73 (54.43, 61.04)

 

 < 0.001*

LS > DS > AS

  1. MD width and CCH showed statistically significant differences, depending on segmentation method. The segmentation time also showed statistically significant differences in the three groups, with the AS having the least manual intervention being the shortest.
  2. Data are given as the mean (95% confidence interval).
  3. ap values were derived from Friedman test; Shapiro–Wilk’s test was employed to test the normality assumption; *p < 0.05.
Back to article page