Hippocampal/Enthorhinal segmentation using "Deep Flash"

Source: R/deepFlash.R

Perform hippocampal/entorhinal segmentation in T1 images using labels from Mike Yassa's lab

deepFlashDeprecated(
  t1,
  doPreprocessing = TRUE,
  doPerHemisphere = TRUE,
  whichHemisphereModels = "new",
  antsxnetCacheDirectory = NULL,
  verbose = FALSE
)

Arguments

t1

raw or preprocessed 3-D T1-weighted brain image.
doPreprocessing

perform preprocessing. See description above.
doPerHemisphere

If TRUE, do prediction based on separate networks per hemisphere. Otherwise, use the single network trained for both hemispheres.
whichHemisphereModels

"old" or "new".
antsxnetCacheDirectory

destination directory for storing the downloaded template and model weights. Since these can be resused, if is.null(antsxnetCacheDirectory), these data will be downloaded to the inst/extdata/ subfolder of the ANTsRNet package.
verbose

print progress.

Value

list consisting of the segmentation image and probability images for each label.

Details

https://faculty.sites.uci.edu/myassa/

The labeling is as follows:

  • Label 0 :background

  • Label 5 :left aLEC

  • Label 6 :right aLEC

  • Label 7 :left pMEC

  • Label 8 :right pMEC

  • Label 9 :left perirhinal

  • Label 10:right perirhinal

  • Label 11:left parahippocampal

  • Label 12:right parahippocampal

  • Label 13:left DG/CA3

  • Label 14:right DG/CA3

  • Label 15:left CA1

  • Label 16:right CA1

  • Label 17:left subiculum

  • Label 18:right subiculum

Preprocessing on the training data consisted of:

  • n4 bias correction,

  • denoising,

  • brain extraction, and

  • affine registration to MNI. The input T1 should undergo the same steps. If the input T1 is the raw T1, these steps can be performed by the internal preprocessing, i.e. set doPreprocessing = TRUE

Author

Tustison NJ

Examples

if (FALSE) {
library( ANTsRNet )
library( keras )

image <- antsImageRead( "t1.nii.gz" )
results <- deepFlash( image )
}