ANTsR is an R package which wraps the well-established C++ biomedical image processing library ANTs. It includes efficient reading and writing of medical images, algorithms for registration, segmentation, and statistical learning, as well as functions to create publication-ready visualizations.
If you are looking to train deep learning models on your medical images in R, you might be interested in ANTsRNet which provides pre-trained models and utilities for training deep learning models on medical images.
The ANTsR package can be installed the pre-compiled binaries (fast) or from source. We are actively working on getting ANTsR onto a host like CRAN or BioConductor.
The fastest way to install ANTsR is from pre-compiled binaries made available on the Releases Page. However, you must first install the ANTsRCore package, whose pre-compiled binaries are available on its own Releases Page. Download the relevant versions for both pacakges and run this from the command-line:
R CMD INSTALL ANTsRCore_*.tgz
R CMD INSTALL ANTsR_*.tgz
To install ANTsR from source, you can use devtools to install the latest version of the code directly form GitHub. This should also automatically install the main dependencies like the ANTsRCore package.
devtools::install_github('ANTsX/ANTsR')
Alternatively, you can clone and install ANTsR and its two main dependencies (ANTsRCore, ITKR) and then install them as you would traditional R source packages.
First, clone the repositories:
$ git clone https://github.com/stnava/ITKR.git
$ git clone https://github.com/ANTsX/ANTsRCore.git
$ git clone https://github.com/ANTsX/ANTsR.git
Install the package as follows:
Brian B. Avants (maintainer), Benjamin M. Kandel, Jeff T. Duda, Philip A. Cook, Nicholas J. Tustison
Reference manual: ANTsR
Wiki: Notes and work in progress examples
Package source: from github
Binaries: here
Windows installation option here
Suggested packages https://github.com/stnava/ANTsRDocker/blob/master/install.R
Inter-modality inference yet to be added RIPMMARC
Eigenanatomy for multiple modality population studies function sparseDecom
Tumor segmentation function mrvnrfs
(not exactly the same but close)
Multiple modality pediatric template and population study employs several aspects of ANTsR
Structural networks from subject-level data function makeGraph
plus yet to be added RIPMMARC
SCCAN relating neuroimaging and cognitive batteries function sparseDecom2
Sparse regression with manifold smoothness constraints function sparseRegression
Prior-based eigenanatomy function sparseDecom
Corrective learning for segmentation functions segmentationRefinement.train
and segmentationRefinement.predict
.
LINDA: automated segmentation of stroke lesions function mrvnrfs
.
LESYMAP: lesion to symptom mapping function sparseDecom2
.
ANTsRNet A growing collection of well-known deep learning architectures ported to the R language. _ Image segmentation _ U-Net (2-D) _ V-Net (3-D) _ Image classification _ AlexNet (2-D, 3-D) _ Vgg16/Vgg19 (2-D, 3-D) _ ResNet/ResNeXt (2-D, 3-D) _ GoogLeNet (2-D) _ DenseNet (2-D, 3-D) _ Object detection * Single Shot MultiBox Detector (2-D, 3-D)