Implementing Multiclass Dice Loss Function

I am doing multi class segmentation using UNet. My input to the model is HxWxC and my output is, outputs = layers.Conv2D(n_classes, (1, 1), activation='sigmoid')(decoder0) Using S

Solution 1:

The problem is that your dice loss doesn't address the number of classes you have but rather assumes binary case, so it might explain the increase in your loss.

You should implement generalized dice loss that accounts for all the classes and return the value for all of them.

Something like the following:

defdice_coef_9cat(y_true, y_pred, smooth=1e-7):
    '''
    Dice coefficient for 10 categories. Ignores background pixel label 0
    Pass to model as metric during compile statement
    '''
    y_true_f = K.flatten(K.one_hot(K.cast(y_true, 'int32'), num_classes=10)[...,1:])
    y_pred_f = K.flatten(y_pred[...,1:])
    intersect = K.sum(y_true_f * y_pred_f, axis=-1)
    denom = K.sum(y_true_f + y_pred_f, axis=-1)
    return K.mean((2. * intersect / (denom + smooth)))

defdice_coef_9cat_loss(y_true, y_pred):
    '''
    Dice loss to minimize. Pass to model as loss during compile statement
    '''return1 - dice_coef_9cat(y_true, y_pred)

This snippet is taken from https://github.com/keras-team/keras/issues/9395#issuecomment-370971561

This is for 9 categories, while you should adjust to the number of categories you have.

Solution 2:

If you are doing multi-class segmentation, the 'softmax' activation function should be used.

I would recommend using one-hot encoded ground-truth masks. This needs to be done outside of the loss calculation code.

The generalized dice loss and others were implemented in the following link:

https://github.com/NifTK/NiftyNet/blob/dev/niftynet/layer/loss_segmentation.py

Solution 3:

Not sure why but the last layer has "sigmoid" as activation function. For Multiclass segmentation it has to be "softmax" not "sigmoid".

Also, the loss you are considering is SparseCategoricalCrossentropy along with a multichannel output. If the last layer would have just 1 channel (when doing multi class segmentation), then using SparseCategoricalCrossentropy makes sense but when you have multiple channels as your output the loss which is to be considered is "CategoricalCrossentropy".

Your loss is increasing as the activation and output channels aren't matching (as mentioned above).

change

outputs = layers.Conv2D(n_classes, (1, 1), activation='sigmoid')(decoder0)

to

outputs = layers.Conv2D(n_classes, (1, 1), activation='softmax')(decoder0)