bartorch.tools.rtnlinv

Contents

bartorch.tools.rtnlinv#

bartorch.tools.rtnlinv(kspace, *, i=None, R=None, M=None, d=None, c=False, N=False, m=None, U=False, f=None, p=None, t=None, I=None, C=None, g=False, S=False, a=None, b=None, T=None, w=None, x=None, A=False, s=False, **extra)#

Jointly estimate a time-series of images and sensitivities with nonlinear inversion using {iter} iteration steps. Optionally outputs the sensitivities.

Runs bart rtnlinv.

Parameters:

  • kspace (torch.Tensor) – Input array.

  • i (int | None) – Number of Newton steps (-i)

  • R (float | None) – (reduction factor) (-R)

  • M (float | None) – (minimum for regularization) (-M)

  • d (int | None) – Debug level (-d)

  • c (bool) – Real-value constraint (-c)

  • N (bool) – Do not normalize image with coil sensitivities (-N)

  • m (int | None) – Number of ENLIVE maps to use in reconstruction (-m)

  • U (bool) – Do not combine ENLIVE maps in output (-U)

  • f (float | None) – restrict FOV (-f)

  • p (torch.Tensor | None) – pattern / transfer function (-p)

  • t (torch.Tensor | None) – kspace trajectory (-t)

  • I (torch.Tensor | None) – File for initialization (-I)

  • C (torch.Tensor | None) – (File for initialization with image space sensitivities) (-C)

  • g (bool) – use gpu (-g)

  • S (bool) – Re-scale image after reconstruction (-S)

  • a (float | None) – (a in 1 + a * Laplace^-b/2) (-a)

  • b (float | None) – (b in 1 + a * Laplace^-b/2) (-b)

  • T (float | None) – temporal damping [default: 0.9] (-T)

  • w (float | None) – (inverse scaling of the data) (-w)

  • x (tuple[int, int, int] | None) – Explicitly specify image dimensions (-x)

  • A (bool) – (Alternative scaling) (-A)

  • s (bool) – (Simultaneous Multi-Slice reconstruction) (-s)

  • **extra (Any) – Further BART flags, passed through by name.

Returns:

output, sensitivities

Return type:

tuple of torch.Tensor

Contents