Standard data preparation techniques for MRI datasets

While our dataset is provided to us post-registration and in the NIfTI format, we still have to do some minor pre-processing before feeding the data to our model.

Metrics and loss functions for segmentation

• Dice Similarity Coefficient

Aside from the architecture, one of the most important elements of any deep learning method is the choice of our loss function.

A natural choice that you may be familiar with is the cross-entropy loss function.

However, this loss function is not ideal for segmentation tasks due to heavy class imbalance (there are typically not many positive regions). A much more common loss for segmentation tasks is the Dice similarity coefficient, which is a measure of how well two contours overlap.

The Dice index ranges from 0 (complete mismatch) To 1 (perfect match).

Visualizing and evaluating segmentation models