NITRC: Welcome



AutoSeg 2.0 Documentation

Clement Vachet (cvachet@email.unc.edu)

Neuro Image Research and Analysis Laboratories

UNC Chapel Hill – April1st, 2011

Table of Contents

Introduction 4

1 Tutorial 4

1.1 Computation 4

1.1.1 Set the process data directory 4

1.1.2 Set data information 4

1.1.3 Set output data directory 4

1.1.4 Set the dataset 5

1.1.5 Computation option 6

1.1.6 Compute automatic segmentation 7

1.2 Parameters 7

1.2.1 Set the atlases 7

1.2.2 Set tissue atlas description 8

1.2.3 Set the structures to be segmented 8

1.2.4 Set advanced parameters 9

1.3 Regional histogram option 10

1.4 Menu options 12

1.5 Exit 13

1.6 AutoSeg outputs 13

1.6.1 Quality control: MRML Scene 13

1.6.2 Skull-stripped intensity rescaled image 13

1.6.3 Regions of interest 13

1.6.4 Volume analysis files 13

1.6.5 Regional histogram option: MRML Scenes 14

2 FAQ 15

2.1 How to improve the rigid registration step? 15

3 Automatic segmentation method 15

3.1 Atlas creation 15

3.1.1 Unbiased average image creation 16

3.1.2 Subcortical structures creation 16

3.2 AutoSeg pipeline 16

3.2.1 Bias field correction 16

3.2.2 Rigid registration to a common coordinate image 16

3.2.3 Tissue segmentation 17

3.2.4 Skull-stripping 18

3.2.5 Loop 18

3.2.6 Intensity rescaling 18

3.2.7 Atlas to case registration 19

3.2.8 Applying the transformations 19

4 Outputs location 20

4.1 Processing data directory 20

4.1.1 Files 20

4.1.2 AutoSeg_Volume 20

4.1.3 AutoSeg_MRML 20

4.2 Data directory 20

4.2.1 AutoSeg 20

4.2.2 AutoSeg/BiasFieldCorrected 21

4.2.3 AutoSeg/atlasIso 21

4.2.4 AutoSeg/ems{_N} 21

4.2.5 AutoSeg/Stripped 22

4.2.6 AutoSeg/WarpROI 22

4.2.7 AutoSeg/MRMLScene 24

5 Screenshots 25

6 Credits 29

Introduction

AutoSeg is a tool allowing the segmentation of probabilistic sub-cortical structures and label maps, such as generic ROI maps and parcellation maps. The approach is a fully automatic segmentation via a deformable registration of an unbiased diffeomorphic atlas with probabilistic spatial priors.

This software executes a BatchMake script and runs several tools as threads, with the possibility to process datasets locally or on a distributed environment using Condor.

Tutorial

This tutorial explains how to use AutoSeg through the FLTK graphic user interface.

1 Computation

This directory will contain BatchMake scripts, eventually quality control images and volume analysis files.

1 Set the process data directory

Type (T1-weighted, T2-weighted, PD) and orientation of the source images need to be set.

2 Set data information

Type (T1-weighted, T2-weighted, PD) of the source images need to be set.

3 Set output data directory

Under each data directory, a directory (named 'AutoSeg' by default) will be created to store the output files. One can change the name of this directory, if several studies are performed on the same dataset (e.g by playing with parameter settings).

4 Set the dataset

Dataset with several formats can be processed: GIPL format, meta format (.mhd), NRRD format, analyze format (.img).... As AutoSeg runs several programs which work best with NRRD images, output images will be saved in NRRD.

A browser displays data that are about to be processed, the user being able to delete selected lines ('Remove' button) or to clear entirely the browser. If the user works with multi-modal images, the browser will then display data separated by interactively resizable columns.

The data selection can be done automatically and/or manually:

Automatic data selection

One can edit the data automatically by setting a general data directory and a filter indicating what files are about to be processed (e.g T1/*T1.nrrd). Starting from the data directory, the tool will find recursively all files that match the first given expression, corresponding to the T1-weighted images. The other expressions, in order to find the T2-weighted and/or PD images, are expressions relative to the path of the T1-weighted images (e.g ../T2/*T2.nrrd). Clicking on the 'Refresh filelist' button will display the dataset in the browser.

Manual data selection

The user has also the possibility to add data manually by clicking on the 'Add' button. A pop up window will then appear, in which data location need to be set.

5 Computation option

3 options can be selected:

Compute volume analysis: this option allows the user to start a volume analysis of the computed subcortical structures and/or label maps.

Compute cortical thickness: this option will computed voxel-based regional cortical thickness measurements. If a parcellation map is provided, a lobar analysis will be performed.

Recompute all: this option will recompute the segmentation for the whole dataset, deleting previous results.

Use condor: this option allows the user to compute the dataset in a distributed environment via Condor, using several computational resources. BatchMake converts its script to a condor script ready to be sent to the Condor manager.

6 Compute automatic segmentation

Pressing the 'Compute AutoSeg' button runs a BatchMake script to process the dataset, which can eventually be stopped by pressing the 'Stop' button.

AutoSeg will check whether or not a study has already been performed in this directory (by considering the existence of the 'AutoSeg_Parameters.txt' file). One can process the dataset with the current parameter settings (if new subjects have been added) or cancel the execution. If one wants to perform a new study on the same dataset, by using different parameter settings, best would be to consider a new AutoSeg processing directory. Output files (parameter settings, volume analysis) would then be accurate.

When the automatic segmentation process starts, a pop up window appears, displaying the status of the current segmentation pipeline. This pop up window can be displayed ('Show process status') or hidden to the convenience of the user.

2 Parameters

Several parameters need to be set before starting the computation. A default parameter file is loaded when AutoSeg starts. However, these parameters can be set manually, in order to select the structures to be segmented, or eventually use a different atlas.

1 Set the atlases

Set the common coordinate image

The source images will be rigidly registered to this atlas and thus will be in the same reference coordinate space. The type of the common coordinate image has to be set.

The common coordinate image should have the same type than the region of interest atlas.

Set the tissue segmentation atlas directory

During the pipeline, a tissue segmentation step will be applied in order to get 3 labels from the brain: White Matter, Grey Matter, CSF. Depending on the source images, this segmentation will be a one-channel (using T1 image), two-channel (T1&T2 or T1&PD), or three-channel (T1&T2&PD). The type of the tissue segmentation image has to be set, the image should be called 'template.nrrd'.

Set the ROI atlas file

Set the T1-weighted ROI atlas, where the atlas probabilistic subcortical structures and label maps have been segmented.

2 Set tissue atlas description

Setting the tissue atlas description, either sharp or fuzzy, will set well-suited default parameters (concerning the warping for the tissue segmentation step), in order to improve the segmentation accuracy:

Sharp tissue atlas: B-Spline warping enabled by default for ABC

Fuzzy tissue atlas: B-Spline warping disabled by default for ABC

3 Set the structures to be segmented

Parcellation maps

The user can compute brain parcellations.

Probabilistic subcortical structures

Twelve subcortical structures can be set or selected (left and righ): amygdala, caudate, hippocampust, pallidus, putamen.

Generic ROI maps

One can also add ROI maps:

4 Set advanced parameters

Rigid Registration

By default, a rigid registration, which can be disabled, is performed to the input images, which includes re-griding. The grid template is by default the region of interest atlas. The grid template is only a template image to set size and spacing of the outputs images.

Using the default region of interest atlas, these parameters are:

size: 170x205x170

spacing: 0.9375*0.9375*0.9375

Depending on the input images, the user can directly set the grid template information, which is needed if the inputs images are larger (considering the spacing) than the region of interest atlas. Otherwise, the brain may be cut in the output images. It is also advised to use an isotropic spacing.

Tissue segmentation and warping parameters

These parameters may eventually be modified, but a non-expert user doesn't need to change them.

The first set of parameters is related to the tissue segmentation step. Depending on the tissue atlas description, different well-suited parameters will be used to improve the segmentation accuracy. One can use ABC, which performs a fluid registration.

The second set of parameters is related to the deformable registration step.

Skull-stripping

One can add the option 'delete vessels' if necessary. T1 images with high intensities which correspond to vessels, may affect the atlas warping. Such voxels will be replaced by a gaussian smoothed values (size 2).

Intensity rescaling

Intensity rescaling needs to be performed prior to the atlas warping. One can use histogram quantile matching (default) or tissue mean matching.

3 Regional histogram option

The regional histogram option allows a histogram analysis by providing auxiliary datasets, such as DTI images.

To use this option, the user first has to select the type of the source images, in the second AutoSeg tab. These images have been processed in the main computation, so it can be a T1, T2 or a PD image and an atlas space, bias corrected or skull stripped-image (the T2 and PD skull-stripped images do not exist yet, so the user have to add them to the stripped directory if he wants to use it)

Then, the type of the transformation (rigid,affine or bspline) need to be selected. Only first auxiliary images are registered to source images

After that, the auxiliary data information has to be set. The user can use different types of auxiliary images (FA, MD, B0). He has to precise it by selecting the corresponding check button and writing the type in the text zone at the right of the check button. Thus, directories will be created for each type of auxiliary images with as a name the text in the text zones.

Next, the user needs to set the dataset. The data selection works as in the first tab. For the automatic auxiliary data selection, the user set the filters relative to the source images, files must be located in the data directory. Source images are automatically obtained from the data selection in the computation tab.

Finally, the user can set several parameters in the advanced parameters tab. The first one is quantiles (values by default are 1,5,33,50,66,95,99) and the second one is the point spacing, used only with a bspline registration (the default value is 10 mm).

4 Menu options

AutoSeg contains two default parameters files:

. AutoSeg_DefaultSharpAtlasParameters.txt: default parameter file for sharp tissue atlas

. AutoSeg_DefaultFuzzyAtlasParameters.txt: default parameter file for fuzzy tissue atlas

When AutoSeg starts, it loads the 'AutoSeg_DefaultSharpAtlasParameters.txt' file.

The menu helps to deal with parameter files and default ones. The available options are:

. Load Computation file: Load a computation file. In order to re-process a study, one can directly load this file instead of setting again all the computation information.

. Load Parameter file: Load a parameter file. In order to re-process a study, one can directly load this file instead of setting again all the parameters information.

. Save Computation file: Save a computation file

. Save Parameter file: Save a parameter file

. Use default sharp atlas parameters: Use default sharp atlas parameters as current parameters

. Use default fuzzy atlas parameters: Use default fuzzy atlas parameters as current parameters

. Set default sharp atlas parameters: Save current parameters as default sharp atlas parameters

. Set default fuzzy atlas parameters: Save current parameters as default fuzzy atlas parameters

. Reset default sharp atlas parameters: Reset default sharp atlas parameters

. Reset default fuzzy atlas parameters: Reset default fuzzy atlas parameters

5 Exit

If one wants to exit the tool while the process is still running, one has the possibility to stop the current process or to quit AutoSeg without stopping the pipeline, thus continuing the automatic segmentation in the background.

6 AutoSeg outputs

1 Quality control: MRML Scene

Quality control is provided via 3D Slicer MRML Scenes. A MRML scene is created per subject, containing a snapshot for each step of the pipeline. Upon completion of the pipeline, clicking on the 'Show MRML Scene' button generates a pop up window giving the choice of starting Slicer3 and automatically loading the MRML Scene of the first case. This allows the user to quickly check the quality of the segmentation pipeline, and see immediately if there has been a problem on one or several cases during the process.

2 Skull-stripped intensity rescaled image

For each data, a skull-stripped intensity rescaled image is computed. This is the image the atlas is registered to. Using other tools, such as itkSNAP (), one can display this image.

3 Regions of interest

If several subcortical structures have been selected, a file gathering all the ROIs is computed. Not only this file but also label maps, such as parcellation maps and generic ROI maps can be overlayed to the skull-stripped intensity rescaled image to check the accuracy of the automatic segmentation.

4 Volume analysis files

If the 'Compute volume' option is selected the tool computes a volume analysis. A subdirectory 'AutoSeg_Volume' with related result files is created in the Process Data directory.

4 volumes analyses can be computed depending on the selected options:

Tissue Segmentation volume analysis: Volumes of the White Matter, Grey Matter, CSF.

Subcortical structures volume analysis: Volumes of the selected subcortical structures

Generic ROI Map volume analysis: WM,GM,CSF volumes for each label

Parcellation Map volume analysis: WM,GM,CSF volumes for each label

5 Regional histogram option: MRML Scenes

To allow the user to perform a quality control, four MRML scenes are created. They are stored in the MRML directory, in the process data directory. The BatchMake scripts used to create these MRML scenes are stored in the process data directory.

-Source_MRMLScene.mrml

This MRML scene contains one snapshot for each source case. The snapshot displays two images, the background image which is the registered source, and the foreground, the first auxiliary image. The user can control with that scene the success of the affine, rigid or bspline registration.

-Parcellation_MRMLScene.mrml

This MRML scene contains one snapshot with two images by couple source case/auxiliary image. The background image is the registered source and the label image is the registered parcellation.

-Struct_MRMLScene.mrml

This MRML scene contains one snapshot by triplet source case/auxiliary image/subcortical structure. The background image is the registered source and we have also the registered subcortical structure as a label image.

-AllROI_MRMLScene.mrml

The AllROI MRML scene contains one snapshot by couple source case/auxiliary image. The background image is still the registered source and the label is the registered AllROI image.

FAQ

1 How to improve the rigid registration step?

If the rigid registration to a common coordinate image is not correct, or the related image is empty, first check the orientation of the input images. If the orientation is correct, a manual registration can be computed to initialize the automatic one.

In this case, the user needs to run Slicer3 and load the common coordinate image (atlas), as well as the bias field corrected image and the transform output in the alasISO folder (T1Image_out.txt).

Apply the transform to the bias field corrected image and use the module Transforms to give manually to the result the same orientation as the atlas.

The transformation file should be saved in the 'atlasIso' directory as follow: T1Image_init.txt

Then the user needs to remove all the other files in the 'atlasIso' directory and the other directories (BiasFieldCorrected, ems{_N}, Stripped, WarpROI, MRMLScene), and run AutoSeg again: AutoSeg will then recognize the previously saved transformation file and will use it as an initialization for the rigid registration step.

Automatic segmentation method

Our approach is a fully automatic segmentation via a deformable registration of an unbiased atlas with probabilistic spatial priors.

The following pages will describe the atlas creation (the package already containing the atlas) and the automatic segmentation pipeline itself: this is what is computed each time a user runs the software.

1 Atlas creation

1 Unbiased average image creation

The current atlas, used by default in AutoSeg has been build from a dataset of 20 T1 images, on which subcortical structures have been manually segmented. The atlas building consists in computing an average image along with transformation fields mapping each training case to the average image (Step 1).

2 Subcortical structures creation

These transformation fields are then applied to the manually segmented structures of each case in order to obtain a probabilistic map on the atlas (Step 2).

2 AutoSeg pipeline

Input images:

1 Bias field correction

Tool: N4BiasFiledCorrection

2 Rigid registration to a common coordinate image

All cases are rigidly registered (6 parameters: translation and rotation) to a common coordinate image, in order to be in the same coordinate space. If the dataset is composed of multi-modality images, all images are aligned.

Tools used: BRAINSFit and ResampleVolume2

3 Tissue segmentation

Depending on the source images, a 1, 2, 3-channel expectation-maximization tissue segmentation is computed for each case. The outputs are:

a filter, intensity inhomogeneity corrected image

a label image: white matter (WM), grey matter (GM), cortical spinal fluid (CSF)

the probabilistic maps of WM, GM, CSF.

4 Skull-stripping

Using the label image from the previous step, our registered image is skull stripped.

5 Loop

If 'Do Loop' is selected with N iterations, there will be N more “Tissue segmentation followed by Skull-stripping”.

6 Intensity rescaling

The stripped image is then intensity rescaled to match the atlas.

7 Atlas to case registration

The atlas needs now to be registered to each case, mapping the gray level intensities. This is done through two steps.

Affine registration

An affine registration TA(15 parameters: translation, rotation, scaling, skews) is computed from the atlas to the skull stripped image. The registration is computed with a conjugate gradient descent optimization and a cubic spline interpolation.

Tool used: RView

Deformable registration

A fluid registration TW, with a linear interpolation, is computed from the previous affinely registered image to the skull stripped image.

Tool used: WarpTool

8 Applying the transformations

Tool used: RView, WarpTool

Subcortical structures

Probabilistic maps creation

The affine transformation is applied using a cubic spline interpolation, whereas the warping is done with a linear interpolation.

ROI thresholding

In order to get hard segmentations, all probabilistic maps are thresholded to half of their maximum intensities.

Lateral ventricles

As lateral ventricles have a wide shape distribution across subjects, a correct probability map is hard to obtain. Large binary masks are used instead, on which the previously computed affine transformation is applied using a nearest neighbor interpolation, then the warping. As their segmentation is not precise enough, the CSF probability map (obtained during the tissue segmentation step) is masked by these ventricle binary images, which creates a probabilistic map for each ventricle.

ROI gathering

Subcortical structures and lateral ventricles are gathered into a single file, allowing an easier quality control.

Label maps

The affine and fluid deformations are applied to the label maps defined in the atlas, such as generic ROI maps and parcellation maps.

Outputs location

1 Processing data directory

1 Files

If the automatic data selection is computed:

-AutoSeg_Data.bms: BatchMake script to compute data automatically

-AutoSeg_Data.txt: Text file containing all the data to be computed

-AutoSeg.bms: BatchMake script

-AutoSeg.log Log File

-AutoSeg_Computation.txt: Computation file

-AutoSeg_Parameters.txt: Parameter file

2 AutoSeg_Volume

In this directory are stored files related to the volume analysis:

-AutoSeg_GenericROIMapVolume.csv: Generic ROI map volume analysis file

-AutoSeg_ParcellationMapVolume.csv: Parcellation map volume analysis file

-AutoSeg_SubcorticalStructureVolume.csv: Subcortical structures volume analysis file

-AutoSeg_TissueSegmentationVolume.csv: Tissue segmentation volume analysis file

3 AutoSeg_MRML

In this directory are stored MRML Scenes:

-Image_MRMLScene.mrml MRML Scene

2 Data directory

Considering your input images are called: T1image, T2image and PDImage

-{T1,T2,PD}Image.nrrd NRRD images

1 AutoSeg

-AutoSeg_Computation.txt: Computation file

-AutoSeg_Parameters.txt: Parameter file

2 AutoSeg/BiasFieldCorrected

-{T1,T2,PD}Image_BiasFieldCorrected.nrrd : bias field corrected image

3 AutoSeg/atlasIso

-{T1,T2,PD}Image_BiasFieldCorrected_out.txt: Log files related to the rigid registration step

-T1Image_BiasFieldCorrected_regAtlas.nrrd: T1 images registered to the common coordinate image

-{T2,PD}Image_regT1_BiasFieldCorrected._regAtlasnrrd: T2 or PD image registered to the T1- registered image

4 AutoSeg/ems{_N}

-ABCparam.xml: XML parameter file

- EMS{_N}.log: Log file

-EMS{_N}.xml : XML file

- {T1,T2,PD}Image_regAtlas_corrected_EMS{_N}.nrrd Images filtered and intensity inhomogeneity corrected

-T1Image_regAtlas_labels_EMS{_N}.nrrd : Label Image (WM+GM+CSF)

-T1Image_regAtlas_posterior0_EMS{_N}.nrrd : White matter probabilistic map

-T1Image_regAtlas_posterior1_EMS{_N}.nrrd : Grey matter probabilistic map

-T1Image_regAtlas_posterior2_EMS{_N}.nrrd : CSF probabilistic map

-T1Image_regAtlas_template_affine_EMS{_N}.nrrd: Template registered image

-{T1,T2,PD}Image_regAtlas_registered_EMS{_N}.nrrd: Registered images

-T1Image_regAtlas_to_template_EMS{_N}.affine: Transformation files

-{T1,T2}Image_regAtlas_to_{T1,T2}Image_regAtlas_registered_EMS{_N}.affine: Transformation files

If 'Compute volume' option is selected:

-T1Image_regAtlas_WM.nrrd: White matter label map

-T1Image_regAtlas_GM.nrrd: Grey matter label map

-T1Image_regAtlas_CSF.nrrd: CSF label map

-T1Image_regAtlas_WM_vol.txt: White matter volume information text file

-T1Image_regAtlas_GM_vol.txt: Grey matter volume information text file

-T1Image_regAtlas_CSF_vol.txt: CSF volume information text file

5 AutoSeg/Stripped

-T1Image_labels_EMS_mask.nrrd Binary Mask (WM+GM+CSF)

-{T1,T2,PD}Image_corrected_EMS-stripped.nrrd Skull Stripped image

-T1Image_corrected_EMS-stripped-irescaled.nrrd Intensity rescaled skull-stripped image

6 AutoSeg/WarpROI

Affine registration step

- AtlasAffReg-T1Image_regAtlas_corrected_EMS-stripped-irescaled_initializetransform.txt

Log file

- AtlasAffReg-T1Image_regAtlas_corrected_EMS-stripped-irescaled.nrrd

Atlas image affinely registered to the skull-stripped intensity rescaled image

Deformable registration step

- AtlasWarpReg-T1Image_regAtlas_corrected_EMS-stripped-irescaled_transformation.nrrd

Deformation field

- AtlasWarpReg-T1Image_regAtlas_corrected_EMS-stripped-irescaled.nrrd

Atlas image warped to the skull-stripped intensity rescaled image

Applying the transformations

Subcortical structures

10 probabilistic maps have been defined in our atlas: amygdalaLeft, amygdalaRight, caudateLeft, caudateRight, hippocampusLeft, hippocampusRight, pallidusLeft, pallidusRight, putamenLeft and putamenRight.

For each structure:

- T1Image_regAtlas_corrected_EMS--${Structure}-AffReg.nrrd

Probability map affinely registered to the skull-stripped intensity rescaled image

- T1Image_regAtlas_corrected_EMS--${Structure}-WarpReg.nrrd

Probability map warped to the skull-stripped intensity rescaled image

- T1Image_regAtlas_corrected_EMS--${Structure}-WarpReg-HardSeg.nrrd

Binary image (hard segmentation of the probabilistic map)

If the 'Compute volume' option has been selected:

- T1Image_regAtlas_corrected_EMS--${Structure}-WarpReg_vol.txt

Volume information text file

Lateral ventricles

For each lateral ventricle:

- T1Image_regAtlas_corrected_EMS—latVentricleMask-AffReg-BinMask.nrrd

Binary mask affinely registered to the skull-stripped intensity rescaled image

- T1Image_regAtlas_corrected_EMS—latVentricleMask-WarpReg-BinMask.nrrd

Binary mask warped to the skull-stripped intensity rescaled image

- T1Image_regAtlas_corrected_EMS—latVentricleMask-WarpReg.nrrd

Probabilistic map, obtained by masking the CSF probabilistic map with the binary mask

- T1Image_regAtlas_corrected_EMS—latVentricleMask-WarpReg-HardSeg.nrrd

Binary image (hard segmentation of the probabilistic map)

If the 'Compute volume' option has been selected:

- T1Image_regAtlas_corrected_EMS—latVentricleMask-WarpReg-HardSeg_vol.txt

Volume information text file

Generic ROI maps

- T1Image_regAtlas_corrected_EMS--GenericROIMap-AffReg.nrrd

Generic ROI Map affinely registered to the skull-stripped intensity rescaled image

- T1Image_regAtlas_corrected_EMS--GenericROIMap-WarpReg.nrrd

Binary image (hard segmentation of the probabilistic map)

If the 'Compute volume' option has been selected:

- T1Image_regAtlas_corrected_EMS—GenericROIMap-WarpReg_volumeSummary.csv

Volume information file

Parcellation maps

- T1Image_regAtlas_corrected_EMS--ParcellationMap-AffReg.nrrd

Generic ROI Map affinely registered to the skull-stripped intensity rescaled image

- T1Image_regAtlas_corrected_EMS--ParcellationMap-WarpReg.nrrd

Binary image (hard segmentation of the probabilistic map)

If the 'Compute volume' option has been selected:

- T1Image_regAtlas_corrected_EMS--ParcellationMap-WarpReg_volumeSummary.csv

Volume information file

ROI gathering

For all the subcortical structures:

- AtlasWarpReg-T1Image_regAtlas_corrected_EMS-stripped-irescaled-AllROI.nrrd

Label map gathering all the regions of interest

7 AutoSeg/MRMLScene

-Image_MRMLScene/Image_MRMLScene.mrml MRML Scene

-Image_MRMLScene/Model_N.vtk Nth model

Screenshots

Credits

. Sylvain Gouttard for the original pipeline

References:

Gouttard S, Styner M, Joshi S, Smith RG, Hazlett HC, Gerig G, Subcortical Structure Segmentation using Probabilistic Atlas Priors, Medical Image Computing and Computer Assisted Intervention, 3D Segmentation in the Clinic: A grand Challenge, October 2007, p 37-46.

. Kitware Inc. :

BatchMake is a crossplatform tool for batch processing of large amount of data. It can process datasets locally or on distributive systems using Condor.

. Condor:

Condor allows users to run High Throughput Computing on large collections of distributively owned computing resources.

. RView package (Daniel Rueckert):

The Image Registration Toolkit was used under Licence from Ixico Ltd.

References:

D. Rueckert, L. I. Sonoda, C. Hayes, D. L. G. Hill, M. O. Leach, and D. J. Hawkes. Non- rigid registration using free-form deformations: Application to breast MR images. IEEE Transactions on Medical Imaging, 18(8):712-721, 1999.

J. A. Schnabel, D. Rueckert, M. Quist, J. M. Blackall, A. D. Castellano Smith, T. Hartkens, G. P. Penney, W. A. Hall, H. Liu, C. L. Truwit, F. A. Gerritsen, D. L. G. Hill, and D. J. Hawkes. A generic framework for non-rigid registration based on non-uniform multi-level free-form deformations. In Fourth Int. Conf. on Medical Image Computing and Computer- Assisted Intervention (MICCAI '01), pages 573-581, Utrecht, NL, October 2001.

C. Studholme, D.L.G.Hill, D.J. Hawkes, An Overlap Invariant Entropy Measure of 3D Medical Image Alignment, Pattern Recognition, Vol. 32(1), Jan 1999, pp 71-86.

. itkEMS (Marcel Prastawa):

References for the original method:

Van Leemput K, Maes F, Vandermeulen D, Suetens P. Automated model based tissue classification of MR images of the brain. IEEE TMI 1999;18:897–908.

Van Leemput K, Maes F, Vandermeulen D, Suetens P. Automated model based bias field correction of MR images of the brain. IEEE TMI 1999;18:885–896.

. ABC (Marcel Prastawa): Atlas Based Classification -

ABC (Atlas Based Classification) is a full segmentation pipeline developed and used at University of North Carolina and University of Utah for brain MRIs. The processing pipeline includes image registration, filtering, and inhomogeneity correction. The tool is cross-platform and can be run within 3D Slicer or as a stand-alone program.

This software is based on itkEMS.

. WarpTool, fWarp, txApply: Sarang Joshi, Brad Davis

References:

Sarang Joshi, Brad Davis, Matthieu Jomier, and Guido Gerig, "Unbiased Diffeomorphic Atlas Construction for Computational Anatomy," NeuroImage; Supplement issue on Mathematics in Brain Imaging, (PM Thompson, MI Miller, T Ratnanather, RA Poldrack, and TE Nichols, eds.), vol. 23, no. Supplement1, pp. S151-S160, Elsevier, Inc, 2004

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

T3

T2

T1

T5

T4

Step 2

T1

T2

T3

Step 1

T5

T4

Label image

WM

GM

CSF

Atlas

TA

TW

................
................

In order to avoid copyright disputes, this page is only a partial summary.

Google Online Preview   Download