Documentation/Nightly/Modules/BasicBrainTissues - Revision history

Acsenrafilho at 16:02, 9 December 2016

2016-12-09T16:02:28Z

Acsenrafilho at 14:02, 27 November 2016

2016-11-27T14:02:33Z

Acsenrafilho: BasicBrainTissue wiki page created

2016-11-25T16:50:21Z

BasicBrainTissue wiki page created

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}}
Extension: [[Documentation/{{documentation/version}}/Extensions/BrainTissuesExtension|BrainTissuesExtension]]<br>
Webpage: http://dcm.ffclrp.usp.br/csim/<br>
Author: Antonio Carlos da S. Senra Filho, CSIM Laboratory (University of Sao Paulo, Department of Computing and Mathematics)<br>
Contact: Antonio Carlos da S. Senra Filho, <email>acsenrafilho@usp.br</email><br>
{{documentation/{{documentation/version}}/module-introduction-row}}
{{documentation/{{documentation/version}}/module-introduction-logo-gallery
|Image:CSIM-logo.png|CSIM Laboratory
|Image:USP-logo.png|University of Sao Paulo
|Image:CAPES-logo.png|CAPES Brazil
}}
{{documentation/{{documentation/version}}/module-introduction-end}}


{{documentation/{{documentation/version}}/module-section|Module Description}}
This module offer a...


{{documentation/{{documentation/version}}/module-section|Use Cases}}
* Use Case 1: a
**b
<gallery widths="200px" perrow="3">
Image:MRI_raw.png|Raw T1 weighted MRI Image
Image:MRI_AAD.png|T1 weighted MRI Image with AAD filter (q=1.2)
</gallery>


{{documentation/{{documentation/version}}/module-section|Panels and their use}}

[[Image:aad_scalar_gui.png|thumb|380px|User Interface]]
IO:
*Input Volume
**Select the input image
*Output Volume
**Set the output image file which the filters should place the final result

Diffusion Parameters:
*Conductance
**The conductance regulates the diffusion intensity in the neighbourhood area. Choose a higher conductance if the input image has strong noise seem in the whole image space.
*Number of Iteractions
**The number of iterations regulates the numerical simulation of the anomalous process over the image. This parameters is also related with the de-noising intensity, however it is more sensible to the noise intensity. Choose the higher number of iterations if the image presents high intensity noise which is not well treated by the conductance parameter.
*Time Step
**The time step is a normalization parameters for the numerical simulation. The maximum value, given as default, is set to 3D images. Lower time step restrict the numerical simulation of the anomalous process.
*Anomalous parameter
**The anomalous parameter (or q value) is the generalization parameters responsible to give the anomalous process approach on the diffusion equation. See the reference paper<ref>Da S Senra Filho, A. C., Garrido Salmon, C. E., & Murta Junior, L. O. (2015). Anomalous diffusion process applied to magnetic resonance image enhancement. Physics in Medicine and Biology, 60(6), 2355–2373. doi:10.1088/0031-9155/60/6/2355</ref> to choose the appropriate q value (at moment, only tested in MRI T1 and T2 weighted images).


{{documentation/{{documentation/version}}/module-section|Similar Modules}}
*[[Documentation/{{documentation/version}}/Modules/IADImageFilter|IAD Image Filter]]
*[[Documentation/{{documentation/version}}/Modules/GradientAnisotropicDiffusion|Gradient Anisotropic Image Filter]]


{{documentation/{{documentation/version}}/module-section|References}}
* paper


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


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

@@ Line 22: / Line 22: @@
 <!-- ---------------------------- -->
 {{documentation/{{documentation/version}}/module-section|Module Description}}
-This module offer a simple and robust brain tissue segmentation focused on white matter, gray matter and CSF brain tissues. The method applied here is based on K-Means clustering segmentation, which presents best results with high quality T1 weighted MRI images.
+This module offer a simple and robust brain tissue segmentation focused on white matter, gray matter and CSF brain tissues. The method applied here is based on naive Bayesian segmentation, which presents good results with high quality T1 weighted MRI images.
-'''NOTE''': This module can be used alone (only apply the K-Means segmentation method on the input data), but the [[Documentation/{{documentation/version}}/Modules/BrainStructuresSegmenter|Brain Structures Segmenter]] module already use it internally, which control a image processing pipeline for a better brain tissue segmentation result.
+'''NOTE''': This module can be used alone (only apply the naive Bayesian segmentation method on the input data), but the [[Documentation/{{documentation/version}}/Modules/BrainStructuresSegmenter|Brain Structures Segmenter]] module already use it internally, which control a image processing pipeline for a better brain tissue segmentation result.
 <!-- ---------------------------- -->
@@ Line 30: / Line 30: @@
 * Use Case 1: Separate White Matter, Gray Matter and CSF brain tissues from a strucutral MRI image.
 **There are some image processing strategies that may need a specific brain tissue mask and this module could facilitate this task. For instance, a Multiple Sclerosis lesion detection algorithm may need a White Matter mask in order to define a localized brain region where the lesion are more probable to appear.
-<gallery widths="200px" perrow="3">
+<gallery widths="300px" heights="300px" perrow="3">
 Image:T1_tissues.png|White matter, gray matter and CSF tissues segmented from the previous MRI image
 Image:WM_3DReconstruction.png|A white matter mask 3D reconstruction

@@ Line 22: / Line 22: @@
 <!-- ---------------------------- -->
 {{documentation/{{documentation/version}}/module-section|Module Description}}
-This module offer a...
+This module offer a simple and robust brain tissue segmentation focused on white matter, gray matter and CSF brain tissues. The method applied here is based on K-Means clustering segmentation, which presents best results with high quality T1 weighted MRI images.
 <!-- ---------------------------- -->
 {{documentation/{{documentation/version}}/module-section|Use Cases}}
-* Use Case 1: a
+* Use Case 1: Separate White Matter, Gray Matter and CSF brain tissues from a strucutral MRI image.
-**b
+**There are some image processing strategies that may need a specific brain tissue mask and this module could facilitate this task. For instance, a Multiple Sclerosis lesion detection algorithm may need a White Matter mask in order to define a localized brain region where the lesion are more probable to appear.
 <gallery widths="200px" perrow="3">
-Image:MRI_raw.png|Raw T1 weighted MRI Image
+Image:T1_tissues.png|White matter, gray matter and CSF tissues segmented from the previous MRI image
-Image:MRI_AAD.png|T1 weighted MRI Image with AAD filter (q=1.2)
+Image:WM_3DReconstruction.png|A white matter mask 3D reconstruction
 </gallery>
@@ Line 37: / Line 40: @@
 {{documentation/{{documentation/version}}/module-section|Panels and their use}}
-[[Image:aad_scalar_gui.png|thumb|380px|User Interface]]
+[[Image:basicbraintissues_gui.png|thumb|500px|User Interface]]
 IO:
 *Input Volume
-**Select the input image
+**Input volume. The algorithm works better with high resolution T1 MRI images alread brain extract and inhomogeneity corrected
-*Output Volume
+*Image Modality
-**Set the output image file which the filters should place the final result
+**Select the image modality inserted as a input volume
-Diffusion Parameters:
+Tissue Type Output:
-*Conductance
+*Separate one tissue class
-**The conductance regulates the diffusion intensity in the neighbourhood area. Choose a higher conductance if the input image has strong noise seem in the whole image space.
+**Choose if you want all the tissues classes or only one class segmented
-*Number of Iteractions
+*Tissue
-**The number of iterations regulates the numerical simulation of the anomalous process over the image. This parameters is also related with the de-noising intensity, however it is more sensible to the noise intensity. Choose the higher number of iterations if the image presents high intensity noise which is not well treated by the conductance parameter.
+**Choose what is the brain tissue label that you want as the output label
 <!-- ---------------------------- -->
 {{documentation/{{documentation/version}}/module-section|Similar Modules}}
-*[[Documentation/{{documentation/version}}/Modules/IADImageFilter|IAD Image Filter]]
+*[https://www.slicer.org/wiki/Modules:EMSegmenter-3.6 EM Segmenter]
 <!-- ---------------------------- -->
 {{documentation/{{documentation/version}}/module-section|References}}
-* paper
+N/A
 <!-- ---------------------------- -->