geoSeg.Rd
uses topological constraints to enhance accuracy of brain segmentation
geoSeg(
img,
brainmask,
priors,
seginit,
vesselopt = "none",
vesselk = 2,
gradStep = 1.25,
mrfval = 0.1,
atroposits = 10,
jacw = NULL,
beta = 0.9
)
input image or list of images (multiple features) where 1st image would typically be the primary constrast
binary image
spatial priors, assume first is csf, second is gm, third is wm
a previously computed segmentation which should have the structure of atropos
or kmeansSegmentation
output
one of bright, dark or none
integer for kmeans vessel-based processing
scalar for registration
e.g. 0.05 or 0.1
e.g. 5 iterations
precomputed diffeo jacobian
for sigma transformation ( thksig output variable )
list of segmentation result images
if (FALSE) { # \dontrun{
img <- antsImageRead(getANTsRData("simple"), 2)
img <- n3BiasFieldCorrection(img, 4)
img <- n3BiasFieldCorrection(img, 2)
bmk <- getMask(img)
segs <- kmeansSegmentation(img, 3, bmk)
priors <- segs$probabilityimages
seg <- geoSeg(img, bmk, priors)
} # }