This project is a Python implementation of most of the MATLAB toolbox k-Wave as well as an interface to the pre-compiled v1.3 of k-Wave simulation binaries which support NVIDIA sm 3.0 to sm 7.5.
With this project, we hope to increase accessibility and reproducablitiy of k-Wave simulations for medical imaging, algorithmic prototyping and testing. Many tools and methods of k-Wave can be found here, but this project has and will continue to diverge from the original k-Wave APIs in order to leverage pythonic practices.
The documentation for k-wave-python can be found here
pip install k-wave-pythonCurrently, we are looking for beta testers on Windows.
After installation, run the B-mode reconstruction example in the examples directory of the repository:
git clone https://github.com/waltsims/k-wave-python
cd k-wave-python
pip install -r ./requirements/example.txt
python3 examples/bmode_reconstruction_example.pyThis example file steps through the process of:
- Generating a simulation medium
- Configuring a transducer
- Running the simulation
- Reconstructing the simulation
This example expects an NVIDIA GPU by default to simulate with k-Wave.
To test the reconstruction on a machine without a GPU, set RUN_SIMULATION on line 14 of bmode_reconstruction_example.py to False and the exmaple will run with pre-computed data.
If you're enjoying k-Wave-python and want to contribute, development instructions can be found here.
j-wave: Differentiable acoustic simulations in JAXADSeismic.jl: a finite difference acoustic simulator with support for AD and JIT compilation in Julia.stride: a general optimisation framework for medical ultrasound tomography.
e-mail walter.simson@tum.de.