Fig. 5: Illustration of the Residual U-Net (ResU-Net) architecture used in this work. | npj Breast Cancer

Fig. 5: Illustration of the Residual U-Net (ResU-Net) architecture used in this work.

From: Supporting intraoperative margin assessment using deep learning for automatic tumour segmentation in breast lumpectomy micro-PET-CT

Fig. 5

The composition of the residual downsampling, bottleneck, and upsampling units is shown. The number of layers shown in this figure is only indicative, as a suited number of layers is defined using a grid search. The number of channels (n) is doubled for every downsampling unit and halved for every upsampling unit. We used the MONAI30 implementation of the architecture introduced by Kerfoot et al.31.

Back to article page