Year: 2025
Type: article
Abstract: MRI-NUFFT is a python package that provides a universal interface to various Non-Uniform Fast Fourier Transform libraries running on CPU or GPU (gpuNUFFT, finufft, cufinufft, pyNFFT), adding compatibility with standard array library (NumPy, CuPy, PyTorch, TensorFlow, etc.) On top of these libraries it extends the existing NUFFT operations to provide a physical model of the MRI acquisition process (e.g.multi-coil acquisition and static-field inhomogeneities).It also provides a wide variety of customizable implementations of non-Cartesian sampling trajectories, as well as density compensation methods.Finally, it proposes optimized auto-differentiation with respect to the data and sampling locations for machine learning.With MRI-NUFFT one can experiment with non-Cartesian sampling in MRI, get access to the latest advances in the field and state-of-the-art sampling patterns.
DOI: 10.21105/joss.07743
Institutions: Institut national de recherche en sciences et technologies du numérique, Commissariat à l'Énergie Atomique et aux Énergies Alternatives, Université Paris-Saclay, CEA Paris-Saclay - Etablissement de Saclay, Siemens Healthcare (United States), Istituto Nazionale di Fisica Nucleare, Sezione di Pisa
Language: English
Subfield: Radiology, Nuclear Medicine and Imaging
Field: Medicine
Domain: Health Sciences
Open Access status: diamond
OpenAlex ID: W4405351926