mimosa_training: Train MIMoSA model on full training set

In neuroconductor-devel/mimosa: 'MIMoSA': A Method for Inter-Modal Segmentation Analysis

Description

This function trains the MIMoSA model from the data frames produced by mimosa_data on all subjects and determines optimal threshold based on training data

Usage

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

Arguments

brain_mask	vector of full path to brain mask
FLAIR	vector of full path to FLAIR
T1	vector of full path to T1
T2	vector of full path to T2 if available. If not use NULL.
PD	vector of full path to PD if available. If not 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	vector of full path to Gold standard segmentations. Typically manually segmented images.
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
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	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
outdir	vector of paths/IDs to be pasted to objects that will be saved. NULL if objects are not to be saved
optimal_threshold	NULL. To run algorithm provide vector of thresholds

Value

GLM objects fit in the MIMoSA procedure and optimal threshold evaluated for full training set

neuroconductor-devel/mimosa documentation built on Sept. 21, 2019, 6:24 p.m.