Simulate complex three-dimensional tissue domains — simulate_volumetric

Generates volumetric spatial-label benchmarks with curved interfaces, disconnected components, thin structures, class imbalance, irregular z-plane acquisition, and spatially structured label corruption.

Usage

simulate_volumetric_domains(
  n = 50000L,
  shape = c("concentric_shells", "warped_ellipsoids", "toroidal_compartments",
    "folded_layers", "thin_folded_sheets", "branching_tubes", "disconnected_volumes",
    "helical_channels"),
  acquisition = c("uniform", "class_imbalanced", "irregular_z"),
  noise_type = c("random", "boundary", "patch", "region"),
  noise = 0.25,
  k = 5L,
  samples = 1L,
  seed = 1L
)

Arguments

n: Number of observations.
shape: Three-dimensional domain geometry.
acquisition: Sampling design: `"uniform"`, `"class_imbalanced"`, or `"irregular_z"`.
noise_type: Corruption mechanism: `"random"`, `"boundary"`, `"patch"`, or `"region"`.
noise: Fraction of labels to corrupt within each sample. Each true class present in a specimen retains one correct exemplar; a rate that makes this impossible is rejected.
k: Number of domains.
samples: Number of independent tissue volumes.
seed: Random seed.

Value

A `spatial_refinement_benchmark` with three coordinate columns.

Examples

sim <- simulate_volumetric_domains(
  n = 1000, shape = "folded_layers", noise_type = "boundary", seed = 8
)
dim(sim$xy)
#> [1] 1000    3