The Neuroconductor Project (https://neuroconductor.org/) is a large repository of R packages for imaging. All the packages we use in this course should be represented there. One of the instructors (John) is a main developer on the project.
All the PDF slides are located in a zip file here.
| title | slides | pdf_slides | rcode | source |
|---|---|---|---|---|
| Introduction and R | Slides | PDF Slides | R Code | Source |
| General R (not covered at ENAR) | Slides | PDF Slides | R Code | Source |
| Imaging Packages in R | Slides | PDF Slides | R Code | Source |
| Visualization of Images | Slides | PDF Slides | R Code | Source |
| Inhomogeneity Correction | Slides | PDF Slides | R Code | Source |
| Brain Extraction/Segmentation | Slides | PDF Slides | R Code | Source |
| Image Registration | Slides | PDF Slides | R Code | Source |
| Tissue-Class Segmentation | Slides | PDF Slides | R Code | Source |
| Intensity Normalization | Slides | PDF Slides | R Code | Source |
| Segmentation of MS Lesions | Slides | PDF Slides | R Code | Source |
| Image Harmonization | Slides | PDF Slides | R Code | Source |
| Starting with Raw (DICOM) Data (not covered) | Slides | PDF Slides | R Code | Source |
All materials for this course are located at: https://github.com/muschellij2/imaging_in_r
You can download by clicking “Clone or download” (in green), then Download as Zip. We will also have USB drives loaded with the code.
We have created a function cheatsheet for all the functions we will call during the course.
The server is located at: http://johnmuschelli.com/rstudio_server.html and you will be given a username and a password.
The code to make the server is located at: https://github.com/muschellij2/rneuro/blob/master/ms_rstudio_droplet.sh
We have provided a set of instructions to install all the requirements on your local system after the tutorial at: http://johnmuschelli.com/imaging_in_r/installing_everything_locally/.
This script should install the packages locally for Mac OSX/Linux/Windows:
if (!"devtools" %in% installed.packages()[, "Package"]) {
install.packages("devtools")
}
if (!"ms.lesion" %in% installed.packages()[, "Package"]) {
devtools::install_github("muschellij2/ms.lesion")
}
source("https://neuroconductor.org/neurocLite.R")
pkgs = c("neurobase", "fslr", "dcm2niir","divest",
"RNifti", "oro.dicom",
"oro.nifti", "WhiteStripe", "neurohcp", "papayar",
"papayaWidget", "oasis", "kirby21.t1")
neuro_install(pkgs)
# data for whitestripe
library(dcm2niir); install_dcm2nii()
library(WhiteStripe); download_img_data()In order to use fslr with FSL (availabel for Mac OSX and Linux only), you must install FSL.
These packages only work for Mac OSX and Linux:
neuro_install(c("ITKR", "ANTsRCore", "ANTsR", "extrantsr"),
upgrade_dependencies = FALSE)This is a package for MALF (multi-atlas label fusion), but is a very large package, so only download it if you are going to do MALF:
neuro_install("malf.templates")In this tutorial, we will provide tutorials on how to use R for structural magnetic resonance imaging (MRI) analysis. We will show how to perform entire image analysis in R, from the scans in raw image format to the statistical analysis after image preprocessing, with an emphasis on reproducibility by using a single programming language. This course will use a real multiple sclerosis dataset and will show the steps of going from the raw image files to performing multiple sclerosis lesion classification with a number of classifiers entirely in R. In this hands-on tutorial, attendees will be given instructions for setup and data before the course, so that they are able to follow along and perform the analysis during the tutorial. The topics to be cover in the course are as follows:
This page was last updated on 2020-09-03 16:24:15 Eastern Time.