Unsupervised Learning with CNNs for Image Registration
We incorporate several variants, presented at CVPR2018 (initial unsupervised learning) and MICCAI2018 (probabilistic & diffeomorphic)
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/
These instructions are for the MICCAI2018 paper. If you'd like the CVPR version (no diffeomorphism or uncertainty measures and using CC) use train.py
- Change the top parameters in
train_miccai2018.py
to the location of your image files. - Run
train_miccai2018.py
with options described in the main function. Example:
train_miccai2018.py --gpu 0 --model_dir /my/path/to/models
- Put test filenames in data/test_examples.txt, and anatomical labels in data/test_labels.mat.
- Run
test_miccai2018.py
[gpu-id] [model_dir] [iter-num]
-
We provide a T1 atlas used in our papers at data/atlas_norm.npz.
-
The spatial transform code, found at
neuron.layers.SpatialTransform
, accepts N-dimensional affine and dense transforms, including linear and nearest neighbor interpolation options. Note that original development of VoxelMorph usedxy
indexing, whereas we are now emphasizingij
indexing. -
For the MICCAI2018 version, we integrate the velocity field using
neuron.layers.VecInt
. By default we integrate using scaling and squaring, which we found efficient. -
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.
If you use voxelmorph or some part of the code, please cite:
Unsupervised Learning for Fast Probabilistic Diffeomorphic Registration
Adrian V. Dalca, Guha Balakrishnan, John Guttag, Mert R. Sabuncu
MICCAI 2018. eprint arXiv:1805.04605
An Unsupervised Learning Model for Deformable Medical Image Registration
Guha Balakrishnan, Amy Zhao, Mert R. Sabuncu, John Guttag, Adrian V. Dalca
CVPR 2018. eprint arXiv:1802.02604
For and problems or questions please open an issue in github or email us at voxelmorph@mit.edu