deepmr.linops.SenseOp

deepmr.linops.SenseOp#

class deepmr.linops.SenseOp(*args: Any, **kwargs: Any)[source]#

Multiply input image by coil sensitivity profile.

Coil sensitivity profiles are expected to have the following dimensions:

  • 2D MRI: (nsets, nslices, ncoils, ny, nx)

  • 3D Cartesian MRI: (nsets, nx, ncoils, nz, ny)

  • 3D NonCartesian MRI: (nsets, ncoils, nz, ny, nx)

where nsets represents multiple sets of coil sensitivity estimation for soft-SENSE implementations (e.g., ESPIRIT), equal to 1 for conventional SENSE and ncoils represents the number of receiver channels in the coil array.

__init__(ndim, sensmap, device=None, multicontrast=True)[source]#

Initiate the linear operator.

Methods

__init__(ndim, sensmap[, device, multicontrast])

Initiate the linear operator.

forward(x)

Forward coil operator.

to(*args, **kwargs)

Copy to different devices

Attributes

H

Return adjoint linear operator.