Fig. 5From: MSAL-Net: improve accurate segmentation of nuclei in histopathology images by multiscale attention learning networka Shows the diagram of the ECA module, where the GAP denotes the global average pooling, k represents the kernel size, C, H, and W represent the channel, height and width, denotes the sigmoid [38], and b displays the boundary refinement module, where 3 \(\times\) 3 represents the convolutional filter sizeBack to article page