Package stapler details

Simultaneous Truth and Performance Level Estimation

An implementation of Simultaneous Truth and Performance Level Estimation (STAPLE) . This method is used when there are multiple raters for an object, typically an image, and this method fuses these ratings into one rating. It uses an expectation-maximization method to estimate this rating and the individual specificity/sensitivity for each rater.

Maintainer: John Muschelli < muschellij2 at gmail.com >

From within R, enter citation(stapler)

Warfield SK, Zou KH, Wells WM (2004). "Simultaneous truth and
performance level estimation (STAPLE): an algorithm for the validation
of image segmentation." _IEEE transactions on medical imaging_,
*23*(7), 903-921.

A BibTeX entry for LaTeX users is

@Article{warfield2004simultaneous,
title = {Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation},
author = {Simon K Warfield and Kelly H Zou and William M Wells},
journal = {IEEE transactions on medical imaging},
volume = {23},
number = {7},
pages = {903--921},
year = {2004},
publisher = {IEEE},
}

If you have any problems with this package you can open a new issue or check the already existing ones here.

To install this package, start R and enter:

source("https://neuroconductor.org/neurocLite.R")

# Default Install
neuro_install('stapler')

# From the Binary Repo in NeuroC
neuro_install('stapler', release = "stable", release_repo = binary_release_repo(release = "stable"))
neuro_install('stapler', release = "current", release_repo = binary_release_repo(release = "current"))

# from GitHub
neuro_install('stapler', release = "stable", release_repo = "github")
neuro_install('stapler', release = "current", release_repo = "github")

More detailed installation instructions can be found here.