Figure 7 | Scientific Reports

Figure 7

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

Figure 7

Three-dimensional reconstruction results. (a) Clear maxillary sinus, (b) hazy maxillary sinus. Red: the ground truth (manual labels); green: the results of artificial intelligence (AI) prediction; yellow: the results after post-processing of AI prediction. The average segmentation time per maxillary sinus was 48.7 min for the manual method and 46.2 s for the AI method, and the post-processing process took an average of 16 s.

Back to article page