Table 3 Final AI prediction results after post-processing according to sinus condition.

From: Deep learning-based fully automatic segmentation of the maxillary sinus on cone-beam computed tomographic images

 

Clear sinus (mean ± SD)

Hazy sinus (mean ± SD)

DSC

0.9072 ± 0.1842

0.9123 ± 0.1977

Precision

0.8852 ± 0.1784

0.9131 ± 0.1917

Recall

0.9404 ± 0.1935

0.9173 ± 0.2060

HD (mm)

2.4057 ± 2.4496

1.9158 ± 2.0887

  1. AI artificial intelligence, DSC dice similarity coefficient, HD Hausdorff distance, SD standard deviation.
Back to article page