Difference between revisions of "Documentation/Nightly/Extensions/BabyBrain"

From Slicer Wiki
Jump to: navigation, search
(First commit to Baby Brain extension)
 
Line 9: Line 9:
 
{{documentation/{{documentation/version}}/module-introduction-row}}
 
{{documentation/{{documentation/version}}/module-introduction-row}}
 
This work was partially funded by CAPES and CNPq, a Brazillian Agencies. Information on CAPES can be obtained on the [http://www.capes.gov.br/ CAPES website] and [http://www.cnpq.br/ CNPq website].<br>
 
This work was partially funded by CAPES and CNPq, a Brazillian Agencies. Information on CAPES can be obtained on the [http://www.capes.gov.br/ CAPES website] and [http://www.cnpq.br/ CNPq website].<br>
Author: Antonio Carlos da S. Senra Filho, CSIM Laboratory (University of Sao Paulo, Department of Computing and Mathematics)<br>
+
Author: Antonio Carlos da S. Senra Filho, CSIM Laboratory (University of Sao Paulo, Department of Computing and Mathematics) and '''Sara...'''<br>
 
Contact: Antonio Carlos da S. Senra Filho <email>acsenrafilho@usp.br</email><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-row}}
Line 27: Line 27:
 
[[Image:BabyBrainExtension-logo.png|left]]
 
[[Image:BabyBrainExtension-logo.png|left]]
  
This module offers a set of algorithms to biomedical image data preparation, which is focused for the neonate and fetal MRI analysis. The methods used here are
+
This module offers a set of algorithms to biomedical image data preparation, which is focused on the neonate and fetal MRI analysis. The methods used are optimized to structural MRI images, namely T2 and T1. Further improvements are under development stage in order to address new imaging modalities (e.g. diffusion-weighted images). The general procedure assumes that the MRI image was already reconstructed in a volume representation and also brain extracted.
optimized to structural MRI images, namely T2 and T1, however, any kind of digital 3D images can be processed here (assuming a different set of parameters).  
 
The general procedure assumes that the MRI image was already reconstructed in a volume representation and also brain extracted
 
  
 
+
Basically, there are two different modules: '''BabyBrainPreparation''' and '''BabyBrainSegmentation''', which each of them are optimized for a specific set of image processing. More details are elucidated below.
Basically, there are two different filters ...
 
  
 
<!-- ---------------------------- -->
 
<!-- ---------------------------- -->
 
{{documentation/{{documentation/version}}/extension-section|Modules}}
 
{{documentation/{{documentation/version}}/extension-section|Modules}}
* '''Structural image denoising with tissues border preservation function''': [[Documentation/{{documentation/version}}/Modules/AADImageFilter|AAD Image Filter]]
+
* '''General image enhancement procedure''': [[Documentation/{{documentation/version}}/Modules/BabyBrainPreparation|Baby Brain Preparation]]
* '''Structural image denoising without tissues border preservation function''': [[Documentation/{{documentation/version}}/Modules/IADImageFilter|IAD Image Filter]]
+
* '''Brain tissue segmentation''': [[Documentation/{{documentation/version}}/Modules/BabyBrainSegmentation|Baby Brain Segmentation]]
* '''Diffusion-weighted MR image denoising with tissues border preservation''': [[Documentation/{{documentation/version}}/Modules/AADDiffusionWeightedData|AAD on DWI Image]]
 
* '''Echo-planar imaging denoising with tissues border preservation (fMRI and ASL)''': [[Documentation/{{documentation/version}}/Modules/AADEPIData|AAD on EPI Image]]
 
  
 
<!-- ---------------------------- -->
 
<!-- ---------------------------- -->
 
{{documentation/{{documentation/version}}/module-section|Use Cases}}
 
{{documentation/{{documentation/version}}/module-section|Use Cases}}
Most frequently used for these scenarios:
+
'''Baby Brain Preparation:'''
* Use Case 1: Noise reduction as a pre-processing step for tissue segmentation
+
* Use Case 1: Image preparation to further tissue segmentation
**When dealing with single voxel classification schemes, a noise reduction pre-processing step is usually helpful to reduce data fluctuation due to acquisition artifacts (e.g. reducing the number of misclassified voxels).
+
**The structural MRI images (fetal or neonate) often have a strong level of image artefacts (e.g. noise and grey level inhomogeneity), hence a previous data preparation is needed for further segmentation process.
 
* Use Case 2: Volume rendering
 
* Use Case 2: Volume rendering
**Noise reduction will result in nicer looking volume renderings
+
**Image preprocessing frequently increases the quality of volume renderings
* Use Case 3: Noise reduction as part of image processing pipeline
+
 
**Could offer a better segmentation and classification on specific brain image analysis such as in Multiple Sclerosis lesion segmentation
+
'''Baby Brain Segmentation:'''
<gallery widths="200px" perrow="3">
+
* Use Case 1: Brain morphological information
 +
** The measurement of morphological features in brain images (e.g. volume of white or grey matter, brain atrophy, etc) are commonly used in several clinical studies.
 +
 
 +
 
 +
 
 +
<gallery widths="400px" heights="400px" perrow="3">
 
Image:MRI_raw.png|Raw T1 weighted MRI Image
 
Image:MRI_raw.png|Raw T1 weighted MRI Image
Image:MRI_AAD.png|T1 weighted MRI Image with AAD filter (q=1.2)
 
Image:MRI_IAD.png|T1 weighted MRI Image with IAD filter (q=1.2)
 
Image:DTI_FA_raw.png|DTI-FA map without image filtering process
 
Image:DTI_FA_AAD.png|DTI-FA map with AAD image filtering (q=0.4)
 
 
</gallery>
 
</gallery>
  
 
<!-- ---------------------------- -->
 
<!-- ---------------------------- -->
 
{{documentation/{{documentation/version}}/extension-section|Similar Extensions}}
 
{{documentation/{{documentation/version}}/extension-section|Similar Extensions}}
*[[Documentation/{{documentation/version}}/Modules/GradientAnisotropicDiffusion|Gradient Anisotropic Diffusion]]
+
*[[Documentation/{{documentation/version}}/Modules/EMSegment_Easy|EM Segmenter Easy]]
 +
*[[EMSegmenter-Tasks]]
  
 
<!-- ---------------------------- -->
 
<!-- ---------------------------- -->
 
{{documentation/{{documentation/version}}/extension-section|References}}
 
{{documentation/{{documentation/version}}/extension-section|References}}
* 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), pp.2355–2373. DOI: 10.1088/0031-9155/60/6/2355
+
* PAPER
* Filho, A.C. da S.S. et al., 2014. Anisotropic Anomalous Diffusion Filtering Applied to Relaxation Time Estimation in Magnetic Resonance Imaging. In Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE, pp. 3893–3896.
 
* Filho, A.C. da S.S., Barizon, G.C. & Junior, L.O.M., 2014. Myocardium Segmentation Improvement with Anisotropic Anomalous Diffusion Filter Applied to Cardiac Magnetic Resonance Imaging. In Annual Meeting of Computing in Cardiology.
 
* Filho, A.C. da S.S. et al., 2014. Brain Activation Inhomogeneity Highlighted by the Isotropic Anomalous Diffusion Filter. In Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Chicago: IEEE, pp. 3313–3316.
 
* Senra Filho, A.C. da S., Duque, J.J. & Murta, L.O., 2013. Isotropic anomalous filtering in Diffusion-Weighted Magnetic Resonance Imaging. I. E. in M. and B. Society, ed. Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference, 2013, pp.4022–5.
 
  
 
<!-- ---------------------------- -->
 
<!-- ---------------------------- -->
Line 75: Line 68:
  
 
Repositories:
 
Repositories:
* Source code: [https://github.com/CSIM-Toolkits/AnomalousFiltersExtension GitHub repository]
+
* Source code: [https://github.com/CSIM-Toolkits/BabyBrain GitHub repository]
* Issue tracker:  [https://github.com/CSIM-Toolkits/AnomalousFiltersExtension/issues open issues and enhancement requests]
+
* Issue tracker:  [https://github.com/CSIM-Toolkits/BabyBrain/issues open issues and enhancement requests]
  
 
<!-- ---------------------------- -->
 
<!-- ---------------------------- -->
 
{{documentation/{{documentation/version}}/extension-footer}}
 
{{documentation/{{documentation/version}}/extension-footer}}
 
<!-- ---------------------------- -->
 
<!-- ---------------------------- -->

Revision as of 15:13, 7 March 2018

Home < Documentation < Nightly < Extensions < BabyBrain


For the latest Slicer documentation, visit the read-the-docs.


Introduction and Acknowledgements

This work was partially funded by CAPES and CNPq, a Brazillian Agencies. Information on CAPES can be obtained on the CAPES website and CNPq website.
Author: Antonio Carlos da S. Senra Filho, CSIM Laboratory (University of Sao Paulo, Department of Computing and Mathematics) and Sara...
Contact: Antonio Carlos da S. Senra Filho <email>acsenrafilho@usp.br</email>

CSIM Laboratory  
University of Sao Paulo  
CNPq Brazil  
CAPES Brazil  


Extension Description

BabyBrainExtension-logo.png

This module offers a set of algorithms to biomedical image data preparation, which is focused on the neonate and fetal MRI analysis. The methods used are optimized to structural MRI images, namely T2 and T1. Further improvements are under development stage in order to address new imaging modalities (e.g. diffusion-weighted images). The general procedure assumes that the MRI image was already reconstructed in a volume representation and also brain extracted.

Basically, there are two different modules: BabyBrainPreparation and BabyBrainSegmentation, which each of them are optimized for a specific set of image processing. More details are elucidated below.

Modules

Use Cases

Baby Brain Preparation:

  • Use Case 1: Image preparation to further tissue segmentation
    • The structural MRI images (fetal or neonate) often have a strong level of image artefacts (e.g. noise and grey level inhomogeneity), hence a previous data preparation is needed for further segmentation process.
  • Use Case 2: Volume rendering
    • Image preprocessing frequently increases the quality of volume renderings

Baby Brain Segmentation:

  • Use Case 1: Brain morphological information
    • The measurement of morphological features in brain images (e.g. volume of white or grey matter, brain atrophy, etc) are commonly used in several clinical studies.


Similar Extensions

References

  • PAPER

Information for Developers


Repositories: