priorBasedSegmentation.Rd
markov random field regularized, prior-based image segmentation that is a wrapper around atropos (see ANTs and related publications).
priorBasedSegmentation(
img,
priors,
mask,
priorWeight = 0.25,
mrf = 0.1,
iterations = 25,
verbose = FALSE
)
input image or image list for multivariate segmentation
list of priors that cover the number of classes
segment inside this mask
usually 0 (priors used for initialization only), 0.25 or 0.5.
regularization, higher is smoother, a numerical value in range 0.0 to 0.2
maximum number of iterations. could be a large value eg 25.
maximum number of iterations. could be a large value eg 25.
segmentation and probability images
fi <- antsImageRead(getANTsRData("r16"))
seg <- kmeansSegmentation(fi, 3)
msk <- thresholdImage(seg$segmentation, 1, Inf)
pseg <- priorBasedSegmentation(fi, seg$probabilityimages, msk, 0.25, 0.1, 3)