GaussianNoisePerturbation

Note

This page is a reference documentation. It only explains the class signature, and not how to use it. Please refer to the Habitat Guide and Python API guide (v2.0) for usage.

class GaussianNoisePerturbation(sigma: float | None = None, noise_method: str = 'chang', roi: str | None = None, round_to_int: bool = False)

Bases: object

Add zero-mean Gaussian noise to every image of a subject.

Parameters:

• sigma – Noise standard deviation in intensity units; None estimates it per subject with noise_method (the paper’s choice, MIRP’s behaviour when no level is configured).

• noise_method – "chang" (wavelet estimator) or "roi_std" (standard deviation inside the ROI).

• roi – Mask key for roi_std estimation; None uses the subject’s single mask.

• round_to_int – Round the noisy image to whole numbers, mirroring MIRP’s handling of integer-valued CT (HU) data.

__init__(sigma: float | None = None, noise_method: str = 'chang', roi: str | None = None, round_to_int: bool = False) → None

property spec: Spec

Return the algorithm specification used for provenance.

__call__(subject: Subject, *, rng: Generator) → Subject

Return a copy of subject with Gaussian noise added to all images.

Parameters:

• subject – Subject providing the images (and the ROI when the noise level is estimated with roi_std).

• rng – Random generator supplying the noise field.

Returns:

The perturbed subject copy.