Skip to main content
. 2022 Feb;33(2):420–430. doi: 10.1681/ASN.2021030404

Figure 1.

Figure 1.

Schematic illustration of the 3D U-Net architecture utilized in this study. The U-Net architecture consists of two pathways. The first combined downsampling with convolutional layers to encode the input. The second recombined these representations with shallower features transferred via skip connections to generate the final segmentation mask.