Choice of loss function for semantic segmentation

Question

I am training a U-Net for semantic segmentation of large medical images (4096x4096px). The two classes are "too" unbalanced. The white pixels are just about 0.1% (or less) of the whole image. The Dice Coeff loss function seems to not be working since it predicts always black pixels.

• Is there any specialized loss function for such unbalanced data? I can not find anything that works.
• Is the U-Net arcitecture suitable for such segmentation tasks?

I have tried to train with the following setup:

    Epochs:          50
    Batch size:      4
    Learning rate:   1e-05
    Training size:   451
    Validation size: 23
    Checkpoints:     True
    Device:          cuda
    Images scaling:  0.25

and also with batch size of 1 and learning rate of 10^4. I would appreciate some help.

Cheers