mach-beamform 0.0.2

Ultrafast GPU-accelerated beamforming kernel for ultrasound imaging

mach

An ultrafast GPU-accelerated ultrasound beamformer, written in CUDA, accessible from Python.

Beamforming PyMUST's rotating-disk Doppler dataset at 0.86 trillion points per second (5x the speed of sound)

Highlights

• ⚡ Ultra-fast beamforming: ~10x faster than prior state-of-the-art
• 🚀 GPU-accelerated: Leverages CUDA for maximum performance on NVIDIA GPUs
• 🎯 Optimized for research: Designed for functional ultrasound imaging (fUSI) and other ultrafast, high-channel-count, or volumetric-ensemble imaging
• 🐍 Python bindings: Zero-copy integration with CuPy, and JAX arrays via nanobind. NumPy support included.`
• 🔬 Validated: Matches vbeam and PyMUST outputs

Installation

Install from PyPI:

pip install mach-beamform

Wheel prerequisites:

• Linux
• CUDA-enabled GPU with driver >= 12.3, compute-capability >= 7.5

Or, to build from source:

make compile

Build prerequisites:

• Linux
• make
• uv >= 0.6.10
• gcc >= 8
• nvcc >= 11.0

Examples

Try our examples:

• 📊 Plane Wave Imaging with PICMUS Dataset
• 🩸 Doppler Imaging

If you don't have a CUDA-enabled GPU, you can download the notebook from the docs and open in Google Colab (select a GPU instance).

Contributing

We welcome contributions! Please see CONTRIBUTING.md for guidelines.

Roadmap

Alpha release (v0.0.Z)

• ✅ Single-wave transmissions (plane wave, focused, diverging)
• ✅ Linear interpolation beamforming
• ✅ Allow NumPy/CuPy/JAX/PyTorch inputs through Array API
• ✅ Comprehensive error handling
• ✅ PyPI packaging and distribution

Experimental features

• Coherent compounding

Tentative Future Plans

• Additional interpolation methods (spline, sinc)
• Additional apodization windows

See the project page for our up-to-date roadmap. We welcome feature requests!

Acknowledgments

mach builds upon the excellent work of the ultrasound imaging community:

• vbeam - For educational examples and validation benchmarks
• PyMUST - For MUST simulator integration and testing
• PICMUS - For standardized evaluation datasets
• Community contributors - Gev and Qi for CUDA optimization guidance

Citation

If you use mach in your research, please cite:

@software{mach,
  title={mach: Ultra-fast GPU-accelerated ultrasound beamforming},
  author={Guan, Charles and Rockhill, Alex and Pinton, Gianmarco},
  organization={Forest Neurotech},
  year={2025},
  url={https://github.com/Forest-Neurotech/mach}
}