Research Article
Automatic Semicircular Canal Segmentation of CT Volumes Using Improved 3D U-Net with Attention Mechanism
Figure 8
CT slices of our dataset. (a1), (a2), and (a3) represent the 37th, 39th, and 41st slices of a sample in our dataset. (b1), (b2), and (b3) are the corresponding labels; the areas where the semicircular canals are located are marked in blue. (a2ā) and (b2ā) are enlarged pictures of (a2) and (b2).