Difference between revisions of "EMSegmenter-Tasks:Human-Eye"

From Slicer Wiki
Jump to: navigation, search
m (Text replacement - "\[http:\/\/www\.slicer\.org\/slicerWiki\/index\.php\/([^ ]+) ([^]]+)]" to "$2")
 
(7 intermediate revisions by one other user not shown)
Line 3: Line 3:
 
=Description=
 
=Description=
 
Single channel automatic segmentation of t1w-MRI brain scans into the major tissue classes (gray matter, white matter, csf). The task can only be applied to t1w brain scan showing parts of the skull and neck. The pipeline consist of the following steps:
 
Single channel automatic segmentation of t1w-MRI brain scans into the major tissue classes (gray matter, white matter, csf). The task can only be applied to t1w brain scan showing parts of the skull and neck. The pipeline consist of the following steps:
* Step 1: Perform image inhomogeneity correction of the MRI scan via [http://www.slicer.org/slicerWiki/index.php/Modules:N4ITKBiasFieldCorrection-Documentation-3.6 N4ITKBiasFieldCorrection] (Tustison et al 2010)
+
* Step 1: Perform image inhomogeneity correction of the MRI scan via [[Modules:N4ITKBiasFieldCorrection-Documentation-3.6|N4ITKBiasFieldCorrection]] (Tustison et al 2010)
 
* Step 2: Register the atlas to the MRI scan via [[Modules:BRAINSFit| BRAINSFit]] (Johnson et al 2007)
 
* Step 2: Register the atlas to the MRI scan via [[Modules:BRAINSFit| BRAINSFit]] (Johnson et al 2007)
 
* Step 3: Compute the intensity distributions for each structure <BR>
 
* Step 3: Compute the intensity distributions for each structure <BR>
Line 11: Line 11:
 
=Anatomical Tree=
 
=Anatomical Tree=
  
labels/colors need to be updated
+
* root
 +
** 1 (dark blue) : eye globe
 +
** 2 (pink) : fat tissue
 +
** 4 (blue) : superior oblique muscle
 +
** 5 (red) : medial rectus muscle
 +
** 6 (green) : lateral rectus muscle
 +
** 8 (yellow) : inferior rectus muscle
 +
** 9 (violet) : superior rectus muscle
  
* root
+
* not used
** 1 (dark blue) : not used
 
** 2 (pink) : fat tissue
 
 
** 3 (white) : not used
 
** 3 (white) : not used
** 4 (blue) : inferior extraocular muscle
+
** 7 (azure blue) : not used
** 5 (red) : medial extraocular muscle
+
** 10 (olive green) : not used
** 6 (green) : superior extraocular muscle
 
** 7 (azure blue) : superior oblique extraocular muscle
 
** 8 (olive green) : lateral extraocular muscle
 
** 9 (violet) : inferior extraocular muscle
 
** 10 (olive green) : non used
 
  
 
=Atlas=
 
=Atlas=
Atlas was generated based on 5 scans and corresponding segmentations provided by Raphaël Olszewski, l'Université catholique de Louvain à Louvain-La-Neuve, Belgique [link]. We registered the scans to a preselected template via the atlas creator using the fixed template approach by  (Warfield et al. 2001.) <BR>  
+
Atlas was generated based on 5 scans and corresponding segmentations provided by Raphaël Olszewski, l'Université catholique de Louvain à Louvain-La-Neuve, Belgium [http://www.stom.ucl.ac.be/]. We registered the scans to a preselected template via the   [[Modules:AtlasCreator|atlas creator]] using the fixed template approach by  (Warfield et al. 2001.) <BR>  
 
Image Dimension = 256 x 256 x 100 <br>
 
Image Dimension = 256 x 256 x 100 <br>
 
Image Spacing  = 1 x 1 x 1 <BR>
 
Image Spacing  = 1 x 1 x 1 <BR>
Line 32: Line 32:
 
<gallery perrow=1: widths=630px : heights=210px>
 
<gallery perrow=1: widths=630px : heights=210px>
 
Image:EMS HumanEyeAtlasLabels.png
 
Image:EMS HumanEyeAtlasLabels.png
 +
Image:EMS Human Eye Atlas plus template.png
 
</gallery>
 
</gallery>
  
Line 47: Line 48:
  
 
=Collaborators=
 
=Collaborators=
Raphaël Olszewski, l'Université catholique de Louvain à Louvain-La-Neuve, Belgique
+
Dr Raphael Olszewski DDS,MD,PhD, Department of oral and maxillofacial surgery, Cliniques universitaires saint Luc, Université catholique of Louvain, Brussels, Belgium [http://www.stom.ucl.ac.be/]
  
 
=Acknowledgment=
 
=Acknowledgment=

Latest revision as of 02:22, 27 November 2019

Home < EMSegmenter-Tasks:Human-Eye

Return to EMSegmenter Task Overview Page

Description

Single channel automatic segmentation of t1w-MRI brain scans into the major tissue classes (gray matter, white matter, csf). The task can only be applied to t1w brain scan showing parts of the skull and neck. The pipeline consist of the following steps:

  • Step 1: Perform image inhomogeneity correction of the MRI scan via N4ITKBiasFieldCorrection (Tustison et al 2010)
  • Step 2: Register the atlas to the MRI scan via BRAINSFit (Johnson et al 2007)
  • Step 3: Compute the intensity distributions for each structure

Compute intensity distribution (mean and variance) for each label by automatically sampling from the MR scan. The sampling for a specific label is constrained to the region that consists of voxels with high probability (top 95%) of being assigned to the label according to the aligned atlas.

  • Step 4: Automatically segment the MRI scan into the structures of interest using EM Algorithm (Pohl et al 2007)

Anatomical Tree

  • root
    • 1 (dark blue) : eye globe
    • 2 (pink) : fat tissue
    • 4 (blue) : superior oblique muscle
    • 5 (red) : medial rectus muscle
    • 6 (green) : lateral rectus muscle
    • 8 (yellow) : inferior rectus muscle
    • 9 (violet) : superior rectus muscle
  • not used
    • 3 (white) : not used
    • 7 (azure blue) : not used
    • 10 (olive green) : not used

Atlas

Atlas was generated based on 5 scans and corresponding segmentations provided by Raphaël Olszewski, l'Université catholique de Louvain à Louvain-La-Neuve, Belgium [1]. We registered the scans to a preselected template via the atlas creator using the fixed template approach by (Warfield et al. 2001.)
Image Dimension = 256 x 256 x 100
Image Spacing = 1 x 1 x 1

Result


Collaborators

Dr Raphael Olszewski DDS,MD,PhD, Department of oral and maxillofacial surgery, Cliniques universitaires saint Luc, Université catholique of Louvain, Brussels, Belgium [2]

Acknowledgment

The construction of the pipeline was supported by funding from NIH NCRR 2P41RR013218 Supplement.

Citations