Trained U-Net on the LITS dataset is automatically downloaded when running the inference script and can be used as you wish, ENJOY! :)
The figure shows a predicted liver mask with the corresponding patient CT in 3DSlicer. It is the Volume-10 from the LITS17 dataset.
The LITS dataset can be accessible from here, and the corresponding paper for the challenge from here. If trained model is used, please consider citing this paper.
- Clone repo:
git clone https://github.com/andreped/livermask.git
cd livermask
- Create virtual environment and intall dependencies:
virtualenv -ppython3 venv
source venv/bin/activate
pip install -r /path/to/requirements.txt
- Run livermask method:
cd livermask
python livermask.py "path_to_ct_nifti.nii" "output_name.nii"
If you lack any modules after, try installing them through setup.py (could be done instead of using requirements.txt):
pip install wheel
python setup.py bdist_wheel
Pipeline assumes input is in the NIfTI format, and output a binary volume in the same format (.nii). DICOM can be converted to NIfTI using the CLI dcm2niix, as such:
dcm2niix -s y -m y -d 1 "path_to_CT_folder" "output_name"
Note that "-d 1" assumed that "path_to_CT_folder" is the folder just before the set of DICOM scans you want to import and convert. This can be removed if you want to convert multiple ones at the same time. It is possible to set "." for "output_name", which in theory should output a file with the same name as the DICOM folder, but that doesn't seem to happen...
You might have issues downloading the model when using VPN. If any issues are observed, try to disable VPN and try again.
Made with ❤️ and python