bartorch 0.0.4

bartorch embeds BART, the Berkeley Advanced Reconstruction Toolbox, in the Python process and calls it on PyTorch tensors in host or CUDA device memory. BART's commands are Python functions; its linear and nonlinear operators are composable Python objects; its iterative algorithms are solver classes and iteration blocks. Applying an operator or a solver to a tensor that requires a gradient records it for PyTorch autograd. The arithmetic is BART's except where bartorch substitutes a component: FINUFFT and cuFINUFFT compute every non-uniform Fourier transform, the FFT and BLAS/LAPACK routines come from MKL, PyTorch's linked library or SciPy, and the MRI encoding operators run on bartorch's own executor built from BART's operators.

Features

• BART commands (pics, ecalib, nlinv, moba, ...) as functions of tensors, and the bartorch command line, which accepts the arguments of bart.
• MRI encoding operators — Cartesian, non-Cartesian and wave-encoded SENSE, off-resonance correction — composed with @ and + into single BART operators.
• BART's regularization terms and its CG, IST, FISTA, ADMM and primal-dual iterations, as solvers and as differentiable iteration blocks.
• Nonlinear operators, iteratively regularized Gauss-Newton, and quantitative signal models from TorchSim.
• Adapters for unrolled networks, plug-and-play denoisers and DeepInverse.

Quick start

pip install bartorch

import bartorch.tools as bt
from bartorch import priors

kspace = bt.phantom(128, coils=8, kspace=True)  # (coils, z, y, x)
maps = bt.ecalib(kspace, maps=1)
image = bt.pics(kspace, maps, regularizers=priors.Wavelet((-1, -2), 0.005), solver="fista")

The same reconstruction can be assembled from an encoding operator and a solver; Interfaces and execution describes which interface fits which task.

Documentation

https://pulserver.github.io/bartorch/ has the user guide (installation, supported platforms, data layout), the developer guide, conceptual explanations, executed examples and the API reference, with a version switcher between the development version and the releases.

Citation

bartorch has no publication or archival DOI. Work that uses it should cite BART and the methods it applied (ESPIRiT, compressed sensing, nonlinear inversion, ...), and report the bartorch version or commit and the pinned BART revision; Contributors and citation gives the references and what else a reproducible report records.

License

bartorch is MIT-licensed. The embedded BART (BSD-3-Clause) and the vendored pocketfft (BSD-3-Clause) and BlocksRuntime (MIT or NCSA) keep their own licenses; see License and third-party notices. bartorch is an independent project, not affiliated with or endorsed by the BART developers, the PyTorch Foundation or The Linux Foundation. The logo combines BART's mark with the PyTorch logo's flame; PyTorch, the PyTorch logo and any related marks are trademarks of The Linux Foundation.