Robust Brain Extraction (ROBEX) Releases

robex1.2-source ROBEX 1.2, source (all platforms)

jeiglesias@stage.nitrcce.org (Juan Eugenio Iglesias) — Thu, 14 Nov 2013 16:01:00 GMT

Robust Brain Extraction (ROBEX) v1.2
Author: Juan Eugenio Iglesias
Email: iglesias@nmr.mgh.harvard.edu
www: http://www.jeiglesias.com
--------------------------------------

Citation:
Iglesias JE, Liu CY, Thompson P, Tu Z: "Robust Brain Extraction Across
Datasets and Comparison with Publicly Available Methods", IEEE Transactions
on Medical Imaging, 30(9), 2011, 1617-1634.
Compilation instructions:
1. Download and install CMake from http://www.cmake.org
2. Download and compile ITK (www.itk.org). This version of ROBEX
was compiled with ITK-4.2, but any version on the ITK 4 family should
work (I have not tried, though).
3. Use Cmake to open CMakeLists.txt and generate a makefile or IDE
project file. Use the generated file to compile the project. In Linux,
make sure that you set CMAKE_EXE_LINKER_FLAGS to -lstdc++. Aso, make
sure that the executable ROBEX(.exe) ends up in this folder.
4. Enjoy!
------------------------
Usage:
WINDOWS:
runROBEX.bat inputFile strippedFile [outputMaskFile] [seed]
LINUX:
runROBEX.sh inputFile strippedFile [outputMaskFile] [seed]
Important details:
- As opposed to previous versions, any volume that is correctly
oriented in World coordinates should be correctly stripped. If
you get a completely wrong segmentation with the shape of a brain,
please let me know (iglesias@nmr.mgh.harvard.edu).
- Even though ROBEX will read/write any format supported by ITK,
use of Nifti format (.nii or .nii.gz), which can properly handle
the transforms that relate World and voxel coordinates, is *highly*
encouraged. If you have Analyze data, please convert it to Nifti
first and then make sure that the orientation is correct before
feeding the images to ROBEX.
- Some changes have been introduced in the registration, so you
might not be able to accurately reproduce the results from the
paper; to do so, please use an older version of ROBEX.
- The behavior of ROBEX is not deterministic. Therefore, you might
observe (very) slight differences between the outputs of different
runs on the same scan. If you need results that can be exactly
reproduced, you can provide ROBEX with a seed (which must be >=0).
- ROBEX is designed to be robust. If ROBEX doesn't produce decent
results for a given volume, I'd very much appreciate it if you let
me know by email (iglesias@nmr.mgh.harvard.edu).
- Please read license.txt!
------------------------
If you want to play with the code: this is version 1.2 of the software
and there are plenty of constants that are hard coded; sorry about that!
We'll try to make newer versions easier to read and modify.

robex1.2-linux64 ROBEX 1.2, linux 64 bits

jeiglesias@stage.nitrcce.org (Juan Eugenio Iglesias) — Thu, 14 Nov 2013 15:52:00 GMT

Robust Brain Extraction (ROBEX) v1.2
Author: Juan Eugenio Iglesias
Email: iglesias@nmr.mgh.harvard.edu
www: http://www.jeiglesias.com
--------------------------------------

Citation:
Iglesias JE, Liu CY, Thompson P, Tu Z: "Robust Brain Extraction Across
Datasets and Comparison with Publicly Available Methods", IEEE Transactions
on Medical Imaging, 30(9), 2011, 1617-1634.
Usage:
runROBEX.sh inputFile strippedFile [outputMaskFile] [seed]
Important details:
- As opposed to previous versions, any volume that is correctly
oriented in World coordinates should be correctly stripped. If
you get a completely wrong segmentation with the shape of a brain,
please let me know (iglesias@nmr.mgh.harvard.edu).
- Even though ROBEX will read/write any format supported by ITK,
use of Nifti format (.nii or .nii.gz), which can properly handle
the transforms that relate World and voxel coordinates, is *highly*
encouraged. If you have Analyze data, please convert it to Nifti
first and then make sure that the orientation is correct before
feeding the images to ROBEX.
- Some changes have been introduced in the registration, so you
might not be able to accurately reproduce the results from the
paper; to do so, please use an older version of ROBEX.
- The behavior of ROBEX is not deterministic. Therefore, you might
observe (very) slight differences between the outputs of different
runs on the same scan. If you need results that can be exactly
reproduced, you can provide ROBEX with a seed (which must be >=0).
- ROBEX is designed to be robust. If ROBEX doesn't produce decent
results for a given volume, I'd very much appreciate it if you let
me know by email (iglesias@nmr.mgh.harvard.edu).
- Please read license.txt!
------------------------
If you want to play with the code: this is version 1.2 of the software
and there are plenty of constants that are hard coded; sorry about that!
We'll try to make newer versions easier to read and modify.

robex1.2-win ROBEX 1.2, Windows

jeiglesias@stage.nitrcce.org (Juan Eugenio Iglesias) — Thu, 14 Nov 2013 15:41:00 GMT

Citation:

Iglesias JE, Liu CY, Thompson P, Tu Z: "Robust Brain Extraction Across
Datasets and Comparison with Publicly Available Methods", IEEE Transactions
on Medical Imaging, 30(9), 2011, 1617-1634.
------------------------
Usage:
runROBEX.bat inputFile strippedFile [outputMaskFile] [seed]
Important details:
- As opposed to previous versions, any volume that is correctly
oriented in World coordinates should be correctly stripped. If
you get a completely wrong segmentation with the shape of a brain,
please let me know (iglesias@nmr.mgh.harvard.edu).
- Even though ROBEX will read/write any format supported by ITK,
use of Nifti format (.nii or .nii.gz), which can properly handle
the transforms that relate World and voxel coordinates, is *highly*
encouraged. If you have Analyze data, please convert it to Nifti
first and then make sure that the orientation is correct before
feeding the images to ROBEX.
- Some changes have been introduced in the registration, so you
might not be able to accurately reproduce the results from the
paper; to do so, please use an older version of ROBEX.
- The behavior of ROBEX is not deterministic. Therefore, you might
observe (very) slight differences between the outputs of different
runs on the same scan. If you need results that can be exactly
reproduced, you can provide ROBEX with a seed (which must be >=0).
- ROBEX is designed to be robust. If ROBEX doesn't produce decent
results for a given volume, I'd very much appreciate it if you let
me know by email (iglesias@nmr.mgh.harvard.edu).
- Please read license.txt!
------------------------
If you want to play with the code: this is version 1.2 of the software
and there are plenty of constants that are hard coded; sorry about that!
We'll try to make newer versions easier to read and modify.

robex1.1-source ROBEX 1.1, source (all platforms)

jeiglesias@stage.nitrcce.org (Juan Eugenio Iglesias) — Tue, 21 May 2013 13:19:00 GMT

Citation:

Iglesias JE, Liu CY, Thompson P, Tu Z: "Robust Brain Extraction Across
Datasets and Comparison with Publicly Available Methods", IEEE Transactions
on Medical Imaging, 30(9), 2011, 1617-1634.

Usage:

WINDOWS:

runROBEX.bat inputFile strippedFile [outputMaskFile] [seed]

LINUX:

runROBEX.sh inputFile strippedFile [outputMaskFile] [seed]

Important details:

- The input file is supposed to be oriented as the volume "atlas"
in the folder "ref_vols": x = left->right, y = posterior->anterior,
z=inferior->superior. If you get a completely wrong segmentation
with the shape of a brain, try changing the orientation of the
input scan.

- The behavior of ROBEX is not deterministic. Therefore, you might
observe (very) slight differences between the outputs of different
runs on the same scan. If you need results that can be exactly
reproduced, you can provide ROBEX with a seed (which must be >=0).

- ROBEX has been tested with images in Analyze format (.hdr/.img),
but any ITK-supported format should work.

- ROBEX is designed to be robust. If ROBEX doesn't produce decent
results for a given volume, I'd very much appreciate it if you let
me know by email (iglesias@nmr.mgh.harvard.edu).

- Please read license.txt!

------------------------

If you want to play with the code: this is version 1.1 of the software
and there are plenty of constants that are hard coded; sorry about that!
We'll try to make newer versions easier to read and modify.

robex1.1-win ROBEX 1.1, Windows

jeiglesias@stage.nitrcce.org (Juan Eugenio Iglesias) — Tue, 21 May 2013 13:14:00 GMT

Iglesias JE, Liu CY, Thompson P, Tu Z: "Robust Brain Extraction Across
Datasets and Comparison with Publicly Available Methods", IEEE Transactions
on Medical Imaging, 30(9), 2011, 1617-1634. 

Usage:

runROBEX.bat inputFile strippedFile [outputMaskFile] [seed]

Important details:

- The input file is supposed to be oriented as the volume "atlas"
in the folder "ref_vols": x = left->right, y = posterior->anterior,
z=inferior->superior. If you get a completely wrong segmentation
with the shape of a brain, try changing the orientation of the
input scan.

- The behavior of ROBEX is not deterministic. Therefore, you might
observe (very) slight differences between the outputs of different
runs on the same scan. If you need results that can be exactly
reproduced, you can provide ROBEX with a seed (which must be >=0).

- ROBEX has been tested with images in Analyze format (.hdr/.img),
but any ITK-supported format should work.

- ROBEX is designed to be robust. If ROBEX doesn't produce decent
results for a given volume, I'd very much appreciate it if you let
me know by email (iglesias@nmr.mgh.harvard.edu).

- Please read license.txt!

robex1.1-linux64 ROBEX 1.1, linux 64 bits

jeiglesias@stage.nitrcce.org (Juan Eugenio Iglesias) — Tue, 21 May 2013 12:50:00 GMT

robex1.0-win32 Robex 1.0, windows 32 bits

jeiglesias@stage.nitrcce.org (Juan Eugenio Iglesias) — Thu, 12 Jul 2012 16:04:00 GMT

Robust Brain Extraction (ROBEX) v1.0
Author: Juan Eugenio Iglesias
Email: jeiglesias@ucla.edu
www: http://www.jeiglesias.com
--------------------------------------

Usage: ROBEX inputFile strippedFile [outputMaskFile]

Important details:

- The input file is supposed to be oriented as the volume "atlas"
in the folder "ref_vols": x = left->right, y = posterior->anterior,
z=inferior->superior. If you get a completely wrong segmentation
with the shape of a brain, try changing the orientation of the
input scan.

- ROBEX has been tested with images in Analyze format (.hdr/.img),
but any ITK-supported format should work.

- ROBEX is designed to be robust. If ROBEX doesn't produce decent
results for a given volume, I'd very much appreciate it if you let
me know by email.

- Please read license.txt!

robex1.0-linux64 ROBEX 1.0, linux 64 bits

jeiglesias@stage.nitrcce.org (Juan Eugenio Iglesias) — Thu, 12 Jul 2012 16:00:00 GMT

robex1.0-source ROBEX 1.0, source code

jeiglesias@stage.nitrcce.org (Juan Eugenio Iglesias) — Thu, 12 Jul 2012 15:54:00 GMT

robex1.0-linux32 ROBEX 1.0, linux 32 bits

jeiglesias@stage.nitrcce.org (Juan Eugenio Iglesias) — Thu, 12 Jul 2012 16:02:00 GMT

Robust Brain Extraction (ROBEX) v1.0

Author: Juan Eugenio Iglesias

Email: [url=mailto:jeiglesias@ucla.edu]jeiglesias@ucla.edu[/url]

www: [url=http://www.jeiglesias.com/]http://www.jeiglesias.com[/url]

--------------------------------------

Usage: ROBEX inputFile strippedFile
[outputMaskFile]

Important details:

- The input file is supposed to be oriented as the volume "atlas"

in the folder "ref_vols": x = left->right, y =
posterior->anterior,

z=inferior->superior. If you get a completely wrong segmentation

with the shape of a brain, try changing the orientation of the

input scan.

- ROBEX has been tested with images in Analyze format
(.hdr/.img),

but any ITK-supported format should work.

- ROBEX is designed to be robust. If ROBEX doesn't produce
decent

results for a given volume, I'd very much appreciate it if you let

me know by email.

- Please read license.txt!