Clean a noisy categorical mask — clean_categorical

Applies FiberMargin to a 2D pixel mask or 3D voxel mask using only coordinates and categorical assignments.

Usage

clean_categorical_mask(mask, samples = NULL, workers = NULL)

Arguments

mask: A categorical matrix or three-dimensional array. Missing cells are treated as void locations.
samples: Optional matrix or array with the same dimensions as mask. Different samples are cleaned independently.
workers: Optional CPU budget used across samples and independent spatial charts. NULL uses up to two physical cores when possible.

Value

A cleaned mask with the representation of mask. Pointwise attributes are candidate, margin_score, required, repair_margin, atlas_dispersion, isolation, and changed. margin_score is a local support contrast on the mask lattice; repair_margin is the gap to the local acceptance threshold.

Examples

mask <- matrix(c(rep("A", 50), rep("B", 50)), nrow = 10)
mask[5, 5] <- "B"
cleaned <- clean_categorical_mask(mask, workers = 1)