ANTsR (version 0.3.1)

jointIntensityFusion3D: jointIntensityFusion3D

Description

Estimates an image/labelset from another set of 3D images

Usage

jointIntensityFusion3D(targetI, targetIMask, atlasList, beta = 4, rad = NA,
  labelList = NA, doscale = TRUE, doNormalize = TRUE,
  maxAtlasAtVoxel = c(1, Inf), rho = 0.01, useSaferComputation = FALSE,
  usecor = FALSE, rSearch = 0, slices = NA, includezero = FALSE,
  computeProbs = FALSE)

Arguments

targetI

antsImage to be approximated

targetIMask

mask with value 1

atlasList

list containing antsImages

beta

weight sharpness, default to 2

rad

neighborhood radius, default to 4

labelList

list containing antsImages

doscale

scale neighborhood intensities

doNormalize

normalize each image range to 0, 1

maxAtlasAtVoxel

min/max n atlases to use at each voxel

rho

ridge penalty increases robustness to outliers but also makes image converge to average

useSaferComputation

slower but more error checking

usecor

employ correlation as local similarity

rSearch

radius of search, default is 2

slices

vector defining slices to use (speeds parameter selection)

includezero

boolean - try to predict the zero label

computeProbs

boolean - requires more memory

Value

approximated image, segmentation and probabilities (latter are WIP, might be done by the time your read this ) ...

Details

intensity generalization of joint label fusion, still supports segmentation. this version is more efficient, memory-wise, for 3D images. it is a thin wrapper that goes slice-by-slice but produces the same results.

Examples

# NOT RUN {
# see jointIntensityFusion for a detailed example
# defaults for this function are current recommended parameters
# }