deepFlash: Hippocampal/Enthorhinal segmentation using "Deep Flash"

In ANTsX/ANTsRNet: Neural Networks for Medical Image Processing

Hippocampal/Enthorhinal segmentation using "Deep Flash"

Description

Perform hippocampal/entorhinal segmentation in T1 and T1/T2 images using labels from Mike Yassa's lab—https://faculty.sites.uci.edu/myassa/

Usage

deepFlash(
  t1,
  t2 = NULL,
  doPreprocessing = TRUE,
  antsxnetCacheDirectory = NULL,
  useRankIntensity = TRUE,
  verbose = FALSE
)

Arguments

t1	raw or preprocessed 3-D T1-weighted brain image.
t2	optional raw or preprocessed 3-D T2-weighted brain image.
doPreprocessing	perform preprocessing. See description above.
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.
useRankIntensity	If false, use histogram matching with cropped template ROI. Otherwise, use a rank intensity transform on the cropped ROI.
verbose	print progress.

Details

https://www.nature.com/articles/s41598-024-59440-6

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/CA2/CA3/CA4

• Label 14:right DG/CA2/CA3/CA4

• 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,

• affine registration to deep flash template. which is performed on the input images if doPreprocessing = TRUE.

Value

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

Author(s)

Tustison NJ

Examples

## Not run: 
library( ANTsRNet )
library( keras )

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

## End(Not run)

ANTsX/ANTsRNet documentation built on April 28, 2024, 12:16 p.m.