Extended Data Fig. 4: Neural network architectures and detailed processes of various modes.
From: Deep learning supported discovery of biomarkers for clinical prognosis of liver cancer
a, The process of obtaining probability heatmaps, segmentation maps, and tumor patches based on PaSegNet. b, c, d, Neural network architectures and detailed processes of MacroNet (b), MicroNet (c) and M2MNet (d), respectively. e, The detailed architecture of each neural network module in the model.
