ichseg / Git / Diff of /README.md

Models:

SCallahan/

ichseg

Downloads: 3

Diff of /README.md [242173] .. [42a64b]

Switch to unified view


---
output: github_document
---

<!-- README.md is generated from README.Rmd. Please edit that file -->

```{r setup, include = FALSE}
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "",
  fig.path = "man/figures/README-"
)
```


<!-- badges: start -->

[![Travis build status](https://travis-ci.com/muschellij2/ichseg.svg?branch=master)](https://travis-ci.com/muschellij2/ichseg)

[![AppVeyor build status](https://ci.appveyor.com/api/projects/status/github/muschellij2/ichseg?branch=master&svg=true)](https://ci.appveyor.com/project/muschellij2/ichseg)

<!-- badges: end -->
  
The goal of `ichseg` is to perform preprocessing on computed tomography (CT) scans, including skull stripping. Computes predictors of intracerebral hemorrhage (ICH) and uses these to predict a binary hemorrhage mask from the data.

## Citing





To cite `ichseg`, you can run:

```{r}
citation("ichseg")
```

## Installation

You can install `ichseg` from github with:

```{r gh-installation, eval = FALSE}
# install.packages("devtools")















devtools::install_github("muschellij2/ichseg")
```


## Requirements

These functions require a working installation of FSL (https://fsl.fmrib.ox.ac.uk/fsl/fslwiki/FslInstallation), which can be installed via Neurodebian as well: http://neuro.debian.net/pkgs/fsl-complete.html.  

## Prediction





In order to segment ICH from an image, use the `ich_segment` function:

```{r, eval = FALSE}
ichseg::ich_segment(img = "/path/to/ct/scan")
```


	a/README.md		b/README.md
1		1	---
		2	output: github_document
		3	---
		4
2	<!-- README.md is generated from README.Rmd. Please edit that file -->	5	<!-- README.md is generated from README.Rmd. Please edit that file -->
3		6
4	ichseg <img src="man/figures/logo.png" align="right" height="139" />	7	```{r setup, include = FALSE}
5	====================================================================	8	knitr::opts_chunk$set(
6		9	collapse = TRUE,
		10	comment = "",
		11	fig.path = "man/figures/README-"
		12	)
		13	```
		14
		15
7	<!-- badges: start -->	16	<!-- badges: start -->
8
9	[![Travis build	17	[![Travis build status](https://travis-ci.com/muschellij2/ichseg.svg?branch=master)](https://travis-ci.com/muschellij2/ichseg)
10	status](https://travis-ci.com/muschellij2/ichseg.svg?branch=master)](https://travis-ci.com/muschellij2/ichseg)
11	[![AppVeyor build	18	[![AppVeyor build status](https://ci.appveyor.com/api/projects/status/github/muschellij2/ichseg?branch=master&svg=true)](https://ci.appveyor.com/project/muschellij2/ichseg)
12	status](https://ci.appveyor.com/api/projects/status/github/muschellij2/ichseg?branch=master&svg=true)](https://ci.appveyor.com/project/muschellij2/ichseg)
13	<!-- badges: end -->	19	<!-- badges: end -->
14		20
15	The goal of `ichseg` is to perform preprocessing on computed tomography	21	The goal of `ichseg` is to perform preprocessing on computed tomography (CT) scans, including skull stripping. Computes predictors of intracerebral hemorrhage (ICH) and uses these to predict a binary hemorrhage mask from the data.
16	(CT) scans, including skull stripping. Computes predictors of	22
17	intracerebral hemorrhage (ICH) and uses these to predict a binary	23	## Citing
18	hemorrhage mask from the data.	24
19
20	Citing
21	------
22
23	To cite `ichseg`, you can run:	25	To cite `ichseg`, you can run:
24		26
25	citation("ichseg")	27	```{r}
26		28	citation("ichseg")
27	Muschelli J, Sweeney EM, Ullman NL, Vespa P, Hanley DF, Crainiceanu CM	29	```
28	(2017). "PItcHPERFeCT: Primary Intracranial Hemorrhage Probability	30
29	Estimation using Random Forests on CT." _NeuroImage: Clinical_, 14,	31	## Installation
30	379-390.	32
31		33	You can install `ichseg` from github with:
32	A BibTeX entry for LaTeX users is	34
33		35	```{r gh-installation, eval = FALSE}
34	@Article{muschelli2017pitchperfect,	36	# install.packages("devtools")
35	title = {{PItcHPERFeCT}: Primary Intracranial Hemorrhage Probability Estimation using Random Forests on {CT}},
36	author = {John Muschelli and Elizabeth M Sweeney and Natalie L Ullman and Paul Vespa and Daniel F Hanley and Ciprian M Crainiceanu},
37	journal = {NeuroImage: Clinical},
38	volume = {14},
39	pages = {379--390},
40	year = {2017},
41	publisher = {Elsevier},
42	}
43
44	Installation
45	------------
46
47	You can install `ichseg` from github with:
48
49	# install.packages("devtools")
50	devtools::install_github("muschellij2/ichseg")	37	devtools::install_github("muschellij2/ichseg")
51		38	```
52	Requirements	39
53	------------	40
54		41	## Requirements
		42
55	These functions require a working installation of FSL	43	These functions require a working installation of FSL (https://fsl.fmrib.ox.ac.uk/fsl/fslwiki/FslInstallation), which can be installed via Neurodebian as well: http://neuro.debian.net/pkgs/fsl-complete.html.
56	(<a href="https://fsl.fmrib.ox.ac.uk/fsl/fslwiki/FslInstallation" class="uri">https://fsl.fmrib.ox.ac.uk/fsl/fslwiki/FslInstallation</a>),	44
57	which can be installed via Neurodebian as well:	45	## Prediction
58	<a href="http://neuro.debian.net/pkgs/fsl-complete.html" class="uri">http://neuro.debian.net/pkgs/fsl-complete.html</a>.	46
59
60	Prediction
61	----------
62
63	In order to segment ICH from an image, use the `ich_segment` function:	47	In order to segment ICH from an image, use the `ich_segment` function:
64		48
65	ichseg::ich_segment(img = "/path/to/ct/scan")	49	```{r, eval = FALSE}
		50	ichseg::ich_segment(img = "/path/to/ct/scan")
		51	```
		52