prior-based-losses-for-medical-image-segmentation

Repository for papers:

Benchmark: Effect of Prior-based Losses on Segmentation Performance: A Benchmark

Midl: A Surprisingly Effective Perimeter-based Loss for Medical Image Segmentation (https://openreview.net/forum?id=NDEmtyb4cXu)

In the .py script losses you can find all the losses used in the benchmark as well as the Contour-based loss.

You can just plugin the name of the loss in the losses argument in the main script and run the program.

TO DO \

• Code should be cleaned and divided into project compartements . \
• Functions should be documented
• Documentation should be provided !!!