search

HealthML / active-segmentation

ActiveSegmentation: A Simulation Framework for Benchmarking Active Learning Strategies for 3D Medical Image Segmentation
GNU Affero General Public License v3.0
16 stars 1 forks source link

Implement normalised surface distance #66

Open josafatburmeister opened 2 years ago

josafatburmeister commented 2 years ago

Could be implemented in pytorch. Testing will be tedious.

Problems: They compare target and predicted surface if the distance between target predicted surface is above a certain threshold. This threshold value is specific per dataset. We would also need to know the voxel spacing for each dataset.