mirtorch.linear.mri.Sense

class mirtorch.linear.mri.Sense(smaps: Tensor, masks: Tensor, norm: str = 'ortho', batchmode: bool = True)

Cartesian sense operator, following “SENSE: Sensitivity encoding for fast MRI”. The input/ourput size depends on the sensitivity maps. If we use the batch dimension, the input dimension is [nbatch, 1, nx, ny, (nz)], and the output is [nbatch, ncoil, nx, ny, (nz)]. Otherwise, the input dimension is [nx, ny, (nz)], and the output is [ncoil, nx, ny, (nz)].

masks

tensor with dimension [(batch), nx, ny, (nz)]

sensitivity maps

tensor with dimension [(batch), ncoil, nx, ny, (nz)]. On the same device as masks

batchmode

bool, determining if there exist batch and channel dimension (should always be 1).

norm

normalization of the fft (‘ortho’, ‘forward’ or ‘backward’)

__init__(smaps: Tensor, masks: Tensor, norm: str = 'ortho', batchmode: bool = True)

Initiate the linear operator.

Methods

__init__(smaps, masks[, norm, batchmode])	Initiate the linear operator.
adjoint(x)	Apply the adjoint operator
apply(x)	Apply the forward operator
to(*args, **kwargs)	Copy to different devices

Attributes

H	Apply the (Hermitian) transpose