Welcome to the nnU-Net Toolkit!

Instalation

• in conda terminal:
  • git clone https://github.com/Zeev1988/nnunet_toolkit.git
  • cd nnunet_toolkit
  • conda env create -f enviroment.yml

Running:

• in conda terminal - set up enviroment before running:
  • conda activate conda_nnunet_toolkit
  • export nnUNet_raw="/path/to/your/nnunet_raw"
  • export nnUNet_preprocessed="/path/to/your/nnunet_preprocessed"
  • export nnUNet_preprocessed="/path/to/your/nnunet_preprocessed"
  • export nnUNet_results="/path/to/your/nnunet_results"
  • export CUDA_VISIBLE_DEVICES=0 (or any other gpu you want)
• run:
  • streamlit run ./gui.py

Additional information:

• Learning from sparse annotations (scribbles, slices)
• Region-based training
• Manual data splits
• Pretraining and finetuning
• Intensity Normalization in nnU-Net
• Manually editing nnU-Net configurations
• Extending nnU-Net
• What is different in V2?

Acknowledgements

nnU-Net is developed and maintained by the Applied Computer Vision Lab (ACVL) of Helmholtz Imaging and the Division of Medical Image Computing at the German Cancer Research Center (DKFZ).