UpdateBot: Nightly -> 4.10

2018-10-19T00:47:17Z

Nightly -> 4.10

New page

<noinclude>{{documentation/versioncheck}}</noinclude>

{{documentation/{{documentation/version}}/module-header}}



{{documentation/{{documentation/version}}/module-section|Introduction and Acknowledgements}}
{{documentation/{{documentation/version}}/module-introduction-start|{{documentation/modulename}}}}
{{documentation/{{documentation/version}}/module-introduction-row}}
This work is part of the National Alliance for Medical Image Computing (NA-MIC), funded by the National Institutes of Health through the NIH Roadmap for Medical Research, Grant U54 EB005149. Information on NA-MIC can be obtained from the [http://www.na-mic.org/ NA-MIC website]. 
Author: Yi Gao, UAB 
Contributor: Ron Kikinis, BWH 
Contributor: Marc Niethammer, UNC 
Contributor: Sylvain Bouix, BWH 
Contributor: Martha Shenton, BWH 
Contributor: Allen Tannenbaum, SBU 
Contact: Yi Gao, <email> gaoyi@gatech.edu</email> 
{{documentation/{{documentation/version}}/module-introduction-row}}
{{documentation/{{documentation/version}}/module-introduction-logo-gallery
|{{collaborator|logo|namic}}|{{collaborator|longname|namic}}
|{{collaborator|logo|uab}}|{{collaborator|longname|uab}}
|{{collaborator|logo|spl}}|{{collaborator|longname|spl}}
}}
{{documentation/{{documentation/version}}/module-introduction-end}}

{{documentation/{{documentation/version}}/module-section|Module Description}}
{{documentation/{{documentation/version}}/module-description}}
This module is a general purpose segmenter. The target object is initialized by a label map. An active contour model then evolves to extract the desired boundary of the object.



{{documentation/{{documentation/version}}/module-section|Use Cases}}
Most frequently used for these scenarios:

* '''Use Case 1, Meningioma segmentation from MRI''':
** Data Set http://www.spl.harvard.edu/publications/item/view/1180 Tumorbase.zip at page bottom, in the zip file, case1/grayscale.nrrd
** Steps to get the segmentation:
<center>
<gallery widths="400px" heights="400px" perrow="3">
Image:MeningiomaCase1RSSLabel.png|Drawn some seeds in the editor module
Image:MeningiomaRSSPanel.png|Set up in RSS module panel, Change target volume limit to 100cc. And run
Image:MeningiomaCase1.png|RSS results for extracting meningioma
</gallery>
</center>

* '''Use Case 2, Right kidney segmentation from CT image''':
** Test case file [[File:CT_liver_segmentation_case.tgz]]
** parameters:
*** Intensity homogeneity: 0.7
*** Boundary smoothness: 0.4
<center>
<gallery widths="700px" heights="400px">
Image:KidneyRightCTRSS.png| RSS segments right kidney from CT image
</gallery>
</center>
* '''Use Case 3, Left kidney segmentation from CT image''':
** Test case file [[File:CT_liver_segmentation_case.tgz]]
** parameters:
*** Intensity homogeneity: 0.7
*** Boundary smoothness: 0.4
<center>
<gallery widths="700px" heights="400px">
Image:KidneyLeftCTRSS.png| RSS segments left kidney from CT image
</gallery>
</center>
* '''Use Case 4, Lung segmentation from CT image''':
** Test case file http://pubimage.hcuge.ch:8080/ LUNGIX data set
** parameters:
*** Intensity homogeneity: 0.7
*** Boundary smoothness: 0.4
<center>
<gallery widths="700px" heights="400px">
Image:LUNGIXRSSSegmentation.png| RSS segments lung from CT image
</gallery>
</center>
* '''Use Case 5, Left caudate segmentation from MR image''':
** Data Set http://www.spl.harvard.edu/publications/item/view/1180 Tumorbase.zip
** parameters:
*** Intensity homogeneity: 0.1
*** Boundary smoothness: 0.2
<center>
<gallery widths="400px" heights="250px" perrow="3">
Image:RSSLeftCaudateLeakage.png| RSS segments left caudate, but have leakage pointed out by the crosses
Image:RSSLeftCaudateRejectionLabel.png| Edit the seed label image and put label-2 at the leakage spot (yellow), keep the targe seed (green) un-changed, run again
Image:RSSLeftCaudateRejectionLabelNoLeakage.png| No leakage.
</gallery>
</center>

{{documentation/{{documentation/version}}/module-section|Tutorials}}

* First run:
# Give a rough estimate of the object volume and use the editing module to paint several non-zero labels, called seeds in the following, in the object.
# Run the module using the default parameters.

* Note:
# The Approximate volume is just a rough upper limit for the volume. It should be at least the size of the object. This is because when the volume reaches that, the program must stop. However, other criteria may stop the algorithm before the volume reaches this value.
# The positions of the seeds have to be in the object, preferably close to center.

* Troubleshooting
** '''Surface is too rough.''' Try:
*** Increase "Boundary smoothness"
** '''Leakage into thin/narrow regions'''. Try:
*** Increase "Boundary smoothness"
** '''leakage into similar (but still different) intensity regions (which is not necessarily thin)''', Try:
*** Increase "Intensity homogeneity"
** '''Some regions are missed''': Try (either one):
*** Increase "Max volume"
*** Decrease"Intensity homogeneity"
*** Decrease "Boundary smoothness"
** '''Some regions are missed, at the same time leakages to some other regions'''. Try (either one)
*** Increase "Intensity homogeneity"
*** Add some other seeds


{{documentation/{{documentation/version}}/module-section|Panels and their use}}
{|
|
* '''Parameters panel:'''
** '''Approximate volume:''' The estimated upper limit of the target volume. The resulting volume will be less or equal than this value.
** '''Intensity homogeneity:''' If the target contains homogeneous intensity, then give a close-to-1 value here.
** '''Boundary smoothness:''' Larger value will result in smoother boundary and a more spherical looking result.
** '''Output Label Value:''' Defined the label value of the output. Also refer to the "Multiple-value label map handling" above.
** '''Max running time:''' The upper limit for program running time.
* '''IO panel:'''
** '''Input Image:''' The image to be segmented.
** '''Label Image:''' The label map providing initial seeds.
* '''Output Volume:''' The output volumetric image.
|[[Image:RSSPanelSlicer4.png|thumb|280px|User Interface]]
|}


{{documentation/{{documentation/version}}/module-section|Similar Modules}}
*[[Documentation/4.0/Modules/SimpleRegionGrowingSegmentation|Simple Region Growing Segmentation]]
* GrowCut in the editor module


{{documentation/{{documentation/version}}/module-section|References}}
Yi Gao, Ron Kikinis, Sylvain Bouix, Martha Shenton, Allen Tannenbaum, ''A 3D Interactive Multi-object Segmentation Tool using Local Robust Statistics Driven Active Contours'', Medical Image Analysis, 2012, http://dx.doi.org/10.1016/j.media.2012.06.002


{{documentation/{{documentation/version}}/module-section|Information for Developers}}
{{documentation/{{documentation/version}}/module-developerinfo}}


{{documentation/{{documentation/version}}/module-footer}}

Documentation/4.10/Modules/RobustStatisticsSegmenter - Revision history

UpdateBot: Nightly -> 4.10