Fig. 3
From: Context-guided segmentation for histopathologic cancer segmentation
(a) An example of an input detail patch. (b) The ground truth mask for the input patch with black representing non-cancer tissue and white representing cancer tissue. All these patches contain both cancer (white) and non-cancer (black). The segmentation maps are predicted by a single-input network (c) and by the dual-input network, CGS-Net (d).
