Modules:EMSegment-TemplateBuilder:EMSegment-TemplateBuilder-Steps

EMSegment Template Builder Workflow Wizard Steps

(1/9) Define Parameters Set: Select parameter set or create new parameters

Step 1/9

* For now, use tutorial set
* Later use this interface to create a new parameter set

(2/9) Define Hierarchy: Define a hierarchy of anatomical structures

Step 2/9

* Right click to add or delete nodes
* Label corresponds to eventual voxel values in segmentation result

(3/9) Assign Atlas: Assign atlases for anatomical structures

Step 3/9

• To change or add new atlas volumes: Load new volumes into Slicer3, then Select new volumes at this step

(4/9) Select Target Images: Choose the set of images that will be segmented

• To change or add new atlas volumes: Load new volumes into Slicer3, then Select new volumes at this step
• You can reorder target images; order is important
• You can choose to align target images
• First target is fixed image
• Rigid, mutual information registration

Step 4/9

(5/9) Intensity Normalization: Normalize target images

• You can choose to normalize target images
• Simple, default strategy
• Default parameter sets available from pulldown

Step 5/9

(6/9) Specify Intensity Distributions: Define intensity distribution for each anatomical structure

• Intensity distributions define appearance of each leaf structure
• Gaussian
• Dimensionality equal to number of target images
• Two methods
  • Sample voxels from images

Step 6/9 - Sample Voxels

Step 6/9 - Remove Voxels

• • • Load first target image into Slicer3 slicer view
    • Choose anatomical structure
    • Choose `manual sampling’
    • Ctrl-left-click on image to add voxels
    • To remove an unwanted sample right-click on it and choose “remove”
    • Change back to “manual” mode to tweak distribution
  • Specify mean and covariance manually
• Tip: sample first, then fine tune manually

Step 6/9

(7/9) Edit Node-based Parameters: Specify node-based segmentation parameters

• Segmentation parameters for every tree node
• Influence
  • Prior weight relative to other structures
  • Atlas
  • Input channels
  • Smoothing (parent nodes only)
• Stopping Conditions

Step 7/9

(8/9) Edit Registration Parameters: Specify atlas-to-target registration parameters

• Moving image registered to first target image (You can choose any image loaded into Slicer3)
• Same transformation applied to all atlas images before segmentation begins

Step 8/9

(9/9) Run Segmentation: Save work and apply EM Algorithm to segment target images

• Select output and run registration
• You can troubleshoot preprocessing by saving intermediate results
• Choose an output labelmap
• ROI governs segmentation processing (one-based, not zero-based)

Step 9/9

Generate EM Segmentation Result Gallery

• Select the first target volume for display
• Select the segmentation results volume in the Labelmap chooser
• Adjust opacity of the label map
• (Optional) Generate and display surfaces from the segmentation results

1. Select the "Model Generation" -> "Model Maker" module
2. For "Input Volume", select the $My_Segmentation_Result
3. For "Output Directory", create and select $PLAYPEN_DIR/Models
4. For "Model Scene File", select $PLAYPEN_DIR/Models.mrml
5. Enable "Generate All Models"
6. Set "End Label" to the highest label that you produced (e.g., 8 fro the tutorial)
7. Enable "Joint Smoothing"
8. Click on Apply (this will generate the models and will take approximately 5 minutes)
9. Load the models into Slicer (File->Import Scene; select $PLAYPEN_DIR/Models.mrml)
10. Use The Models module to manipulate display attributes

• 

  EMSegmenter Applied to MR T1 & T2 tutorial data

• 

  Segmentation of brain structures using EMSegmenter