Skip to main content
Fig. 7 | BMC Bioinformatics

Fig. 7

From: Large scale tissue histopathology image classification, segmentation, and visualization via deep convolutional activation features

Fig. 7

Sample discriminative patches selected with individual components (neurons) of the CNN activation features. Each row of patches causes a high response in one of the 4096 neurons from all colon training images in binary classification task. 6 top-weight features for each classifier are selected and top patches triggering these 6 neurons are selected to represent the characteristics of the corresponding feature. The purpose of this figure is to show the characteristics of individual components of CNN features which are thought be important by the binary classifier. These visualized characteristics convey some clinical insights

Back to article page