Authors	Project	Build Status
D. Dall'Olio N. Curti	3DFemurSegmentation	Linux/MacOS : Windows :

Make sure to install conda before going further.

Clone the repository:

username@local:~$ git clone https://github.com/eDIMESLab/3DFemurSegmentation.git

Next, in order to create 3DFemurSegmentation custom environment, type:

username@local:~/3DFemurSegmentation$ conda env create -f itk.yaml

Then, activate the environment and build Cython libraries:

username@local:~/3DFemurSegmentation$ conda activate itk
username@local:~/3DFemurSegmentation$ python setup.py develop --user

Make sure to add ~/3DFemurSegmentation/lib/ to your Python library path before running. On Ubuntu OS, type:

username@local:~/3DFemurSegmentation$ export PYTHONPATH=$PYTHONPATH:~/3DFemurSegmentation/lib/

Now, run the unsupervised segmentation by supplying input DICOMs directory and output DICOMs directory:

username@local:~/3DFemurSegmentation$ python runFemurSegmentation.py --indir ./indir_example  --outdir ./outdir_example

• Daniele Dall'Olio git, unibo
• Nico Curti git, unibo

Thanks goes to all contributors of this project.

[1] Krčah, M., Székely, G., Blanc, R. Fully automatic and fast segmentation of the femur bone from 3D-CT images with no shape prior 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Chicago, IL, 2011, pp. 2087-2090. doi