Skip to main content
. Author manuscript; available in PMC: 2020 Jan 9.
Published in final edited form as: IEEE Access. 2019 Jan 9;7:11093–11104. doi: 10.1109/ACCESS.2019.2891970

Fig. 3.

Fig. 3.

Description of the densely connected 3D CNN architecture with 3 dense blocks used for 3D image segmentation. A clustering layer shown in Figure 1 was added to the top of the network. In this application the clustering layer was applied to every voxel instead of the whole image for the segmentation task. PReLu: parametric rectified linear unit.