Skip to content

RandomGhosting

MRI k-space ghosting artifacts

RandomGhosting

Bases: RandomTransform, IntensityTransform

Add random MRI ghosting artifact.

Discrete "ghost" artifacts may occur along the phase-encode direction whenever the position or signal intensity of imaged structures within the field-of-view vary or move in a regular (periodic) fashion. Pulsatile flow of blood or CSF, cardiac motion, and respiratory motion are the most important patient-related causes of ghost artifacts in clinical MR imaging (from mriquestions.com).

Parameters:

Name Type Description Default
num_ghosts int | tuple[int, int]

Number of 'ghosts' \(n\) in the image. If num_ghosts is a tuple \((a, b)\), then \(n \sim \mathcal{U}(a, b) \cap \mathbb{N}\). If only one value \(d\) is provided, \(n \sim \mathcal{U}(0, d) \cap \mathbb{N}\).

 (4, 10)
axes int | tuple[int, ...]

Axis along which the ghosts will be created. If axes is a tuple, the axis will be randomly chosen from the passed values. Anatomical labels may also be used (see [RandomFlip][torchio.transforms.augmentation.RandomFlip]).

 (0, 1, 2)
intensity float | tuple[float, float]

Positive number representing the artifact strength \(s\) with respect to the maximum of the \(k\)-space. If 0, the ghosts will not be visible. If a tuple \((a, b)\) is provided then \(s \sim \mathcal{U}(a, b)\). If only one value \(d\) is provided, \(s \sim \mathcal{U}(0, d)\).

 (0.5, 1)
restore float | None

Number between 0 and 1 indicating how much of the \(k\)-space center should be restored after removing the planes that generate the artifact. If None, only the central slice will be restored. If a tuple \((a, b)\) is provided then \(r \sim \mathcal{U}(a, b)\). If only one value \(d\) is provided, \(r \sim \mathcal{U}(0, d)\).

 None
**kwargs

See Transform for additional keyword arguments.

 {}
Note

The execution time of this transform does not depend on the number of ghosts.

__call__(data)

Transform data and return a result of the same type.

Parameters:

Name Type Description Default
data InputType

Instance of torchio.Subject, 4D torch.Tensor or numpy.ndarray with dimensions \((C, W, H, D)\), where \(C\) is the number of channels and \(W, H, D\) are the spatial dimensions. If the input is a tensor, the affine matrix will be set to identity. Other valid input types are a SimpleITK image, a torchio.Image, a NiBabel Nifti1 image or a dict. The output type is the same as the input type.

 required

get_base_args()

Provides easy access to the arguments used to instantiate the base class (Transform) of any transform.

This method is particularly useful when a new transform can be represented as a variant of an existing transform (e.g. all random transforms), allowing for seamless instantiation of the existing transform with the same arguments as the new transform during apply_transform.

Note

The p argument (probability of applying the transform) is excluded to avoid multiplying the probability of both existing and new transform.

add_base_args(arguments, overwrite_on_existing=False)

Add the init args to existing arguments

validate_keys_sequence(keys, name) staticmethod

Ensure that the input is not a string but a sequence of strings.

to_hydra_config()

Return a dictionary representation of the transform for Hydra instantiation.

arguments_are_dict()

Check if main arguments are dict.

Return True if the type of all attributes specified in the args_names have dict type.