pyBOLD is a Python module for semi-blind deconvolution of the fMRI signal (BOLD). This package reproduces the results of the Cherkaoui et al., ICASSP 2019, paper :
[1] Hamza Cherkaoui, Thomas Moreau, Abderrahim Halimi, Philippe Ciuciu, "Sparsity-based blind deconvolution of neural activation signal in fMRI", 2019 IEEE International Conference on Acoustic Speech and Signal Processing, May 2019, Brighton, United Kingdom.
- Official source code repo: https://github.com/CherkaouiHamza/pybold
- Cherkaoui et al., ICASSP 2019, paper
The required dependencies to use the software are:
- Numba
- Joblib
- Numpy
- Scipy
- PyWavelets
- Matplotlib (for examples)
All material is Free Software: BSD license (3 clause).
In order to perform the installation, run the following command from the pybold directory:
python setup.py install --user
To run all the tests, run the following command from the pybold directory:
python -m unittest discover pybold/tests
To run the synthetic examples, go to the directories examples/synth_data and run a script, e.g.:
python deconv.py
To reproduce the ICASSP 2019 plots, go to the directories examples/icassp_2019 and run the scripts, e.g.:
python validation.py python simulation.py
You can check the latest sources with the command:
git clone git://github.com/CherkaouiHamza/pybold
or if you have write privileges:
git clone git@github.com:CherkaouiHamza/pybold