This function creates the training vectors from a single MRI study that has FLAIR, T1, T2, and PD volumes as well as binary masks of lesions. The function can create a tissue mask for the data (or the user can supply a brain mask), the candidate voxels for lesion segmentation, smoothed volumes, and coupling maps. The user may supply already normalized data if they wish to use an alternative normalization method.

mimosa_data(
  brain_mask,
  FLAIR,
  T1,
  T2 = NULL,
  PD = NULL,
  tissue = FALSE,
  gold_standard = NULL,
  normalize = "no",
  cand_mask = NULL,
  slices = NULL,
  orientation = c("axial", "coronal", "sagittal"),
  cores = 1,
  verbose = TRUE
)

Arguments

brain_mask

brain or tissue mask of class nifti

FLAIR

volume of class nifti

T1

volume of class nifti

T2

volume of class nifti. If not available use NULL.

PD

volume of class nifti. If not available use NULL.

tissue

is a logical value that determines whether the brain mask is a full brain mask or tissue mask (excludes CSF), should be FALSE unless you provide the tissue mask as the brain_mask object

gold_standard

gold standard lesion segmentation mask of class nifti

normalize

is 'no' by default and will not perform any normalization on data. To normalize data specify 'Z' for z-score normalization or 'WS' for WhiteStripe normalization

cand_mask

is NULL to use candidate mask procedure proposed with method or a nifti object to be used as the candidate mask

slices

vector of desired slices to train on, if NULL then train over the entire brain mask

orientation

string value telling which orientation the training slices are specified in, can take the values of "axial", "sagittal", or "coronal"

cores

1 numeric indicating the number of cores to be used (no more than 4 is useful for this software implementation)

verbose

logical indicating printing diagnostic output

Value

List of objects