This repo is the official implementation of 'Narrowing the semantic gaps in U-Net with learnable skip connections: The case of medical image segmentation' which is an improved journal version of UCTransNet.
I'm sorry to bother you again. I found that the mask in the train npz dataset of Synapse is a pure black image. To verify this idea, I printed out an array of 512 * 512 labels and found that they are all 0. I don't understand why the corresponding mask image is not a binary image, that is, the area to be segmented is white, and other areas are black. I hope to receive your reply. Thank you very much.
I'm sorry to bother you again. I found that the mask in the train npz dataset of Synapse is a pure black image. To verify this idea, I printed out an array of 512 * 512 labels and found that they are all 0. I don't understand why the corresponding mask image is not a binary image, that is, the area to be segmented is white, and other areas are black. I hope to receive your reply. Thank you very much.