OASIS Prediction

This function creates the OASIS probability map from a single MRI study with FLAIR, T1, T2, and PD volumes.

oasis_predict(flair, t1, t2, pd = NULL, brain_mask = NULL, model = NULL,
  return_preproc = FALSE, binary = FALSE, threshold = 0.16,
  verbose = TRUE, ...)

Arguments

flair	flair volume of class nifti
t1	t1 volume of class nifti
t2	t2 volume of class nifti
pd	pd volume of class nifti
brain_mask	brain mask of class nifti, if NULL a brain mask will be created using fslbet. Note that provided brain masks should be in the same space as the T1 volume if preproc = TRUE, as all volumes will be registered to this space
model	an object of class glm used to make the OASIS predictions
return_preproc	is a logical value that indicates whether the preprocessed images should be returned, if NULL then the model from the OASIS paper will be used
binary	logical indicating whether a binary map should be returned by thresholding the probability map
threshold	numeric indicating the threshold value for the probability map, with default of 0.16 for the OASIS paper
verbose	print diagnostic messages
...	options passed to oasis_train_dataframe

Value

A list of volumes: the OASIS probability map, the preprocessed volumes (if return_preproc = TRUE), the brain mask for the subject, the voxel selection mask, and a thresholded, binary mask (if binary = TRUE) .

Examples

library(ROCR)
p = predict( oasis::oasis_model,
    newdata = example_oasis_df,
    type = 'response')
nopd_p = predict( oasis::nopd_oasis_model,
    newdata = example_oasis_df,
    type = 'response')    
y =  example_oasis_df$GOLD_Lesions
pred = ROCR::prediction(p, y)
perf = ROCR::performance(pred, "tpr", "fpr")
plot(perf)



library(neurobase)
dl_file = function(url) {
   tfile = tempfile(fileext = ".nii.gz")
   req <- httr::GET(url,
   httr::write_disk(path = tfile))
   httr::stop_for_status(req)
   tfile
}
in_ci <- function() {
 nzchar(Sys.getenv("CI"))
}
on_cran = function() {
 identical(Sys.getenv("NOT_CRAN"), "false")
} 
if (in_ci() || on_cran()) {
  if (fslr::have.fsl() && require(httr)) {
    mods = c("FLAIR", "T1W", "T2W", "consensus_gt", "brainmask")
    base_url = file.path(
      "https://raw.githubusercontent.com/muschellij2/open_ms_data", 
      "master/cross_sectional/coregistered/patient01/")
    files = paste0(base_url, mods, ".nii.gz")
    files = sapply(files, dl_file)
    names(files) = mods

    flair <- readnii(files["FLAIR"])
    t1 <- readnii(files["T1W"])
    t2 <- readnii(files["T2W"])
    brain_mask <- readnii(files["brainmask"])
    gold_standard = readnii(files["consensus_gt"])
    oasis_preprocessed_data <- oasis_predict(flair, t1, t2, 
      brain_mask = brain_mask, preproc = TRUE)
  } 
}