We recently published a method on deep learning methods for unsupervised segmentation that makes use of voxelmorph infrastructure. We provide the atlases used during training.
It might be useful to have each folder inside the ext folder on your python path.
assuming voxelmorph is setup at /path/to/voxelmorph/:
export PYTHONPATH=$PYTHONPATH:/path/to/voxelmorph/ext/neuron/:/path/to/voxelmorph/ext/pynd-lib/:/path/to/voxelmorph/ext/pytools-lib/
If you would like to train/test your own model, you will likely need to write some of the data loading code in 'datagenerator.py' for your own datasets and data formats. There are several hard-coded elements related to data preprocessing and format.
python train_unsupervised_segmentation.py /path/to/your/volume/data/
python test_unsupervised_segmentation.py input_file.nii output_seg_filename.nii
If you use the code, please cite (see bibtex):
- Unsupervised deep learning for Bayesian brain MRI segmentation
Adrian V. Dalca, Evan Yu, Polina Golland, Bruce Fischl, Mert R. Sabuncu, Juan E. Iglesias
Under Review. eprint arXiv:1904.11319
For any problems or questions please open an issue in github (preferred).
Alternatively, please contact us at [email protected], but our response might be slower through this route.