Fig. 6From: Automatic classification of 3D positional relationship between mandibular third molar and inferior alveolar canal using a distance-aware networkSegmentation results for the M3 and the MC by SegNet, simple U-Net, Attention U-Net, and Dense121 U-Net. The predicted segmentation masks of the M3 and the MC were superimposed on the ground truth in CBCT images. The yellow, green, and red regions represent true positive, false negative, and false positive, respectivelyBack to article page