Fig. 2
From: Deep learning for histopathological segmentation of smooth muscle in the urinary bladder
Flow diagram of the patch-based approach for classification and semantic segmentation of MP and non-MP regions from bladder H&E-stained histopathological images. In the model training step, the annotated images are stain normalized and split into patches with labels as either MP or non-MP. The CNN architecture is trained on that dataset to classify each patch as MP or non-MP region. In the patch-based inference step, the test image is stain normalized and split into patches. Each patch is passed through the trained CNN architecture and the patch probability is assigned to the center pixel of the patch. All the patch probabilities are merged together to form a segmented test image. Thus, the predicted output image contains either white pixels (MP) or black pixels (non-MP). This output image is further post-processed to obtain a binary image with smooth edges and minimal noisy pixels