Skip to main content
. Author manuscript; available in PMC: 2019 Dec 1.
Published in final edited form as: IEEE Trans Med Imaging. 2018 Jun 27;37(12):2718–2728. doi: 10.1109/TMI.2018.2851150

Fig. 3.

Fig. 3.

Data path for computation of sclerosed glomeruli fraction. Both patch-based and fully convolutional models utilize pretrained VGG16 architecture with frozen weights, truncated before bottleneck. Input patch sizes were 448×448 pixels for patch-based model, and 1024×1024 pixels for fully convolutional model.