Difference between revisions of "EMSegmenter-Tasks:MRI-Human-Brain-HIPR"

From Slicer Wiki
Jump to: navigation, search
Line 7: Line 7:
 
* 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>
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. The alpha parameter for the EMSegmenter has been set to 0.01 to handle the high in-plane resolution of the scans.
+
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. '''The alpha parameter for the EMSegmenter has been set to 0.01 to handle the high in-plane resolution of the scans.'''
 
* Step 4: Automatically segment the MRI scan into the structures of interest using [[Modules:EMSegmenter-3.6|EM Algorithm]]  (Pohl et al 2007)
 
* Step 4: Automatically segment the MRI scan into the structures of interest using [[Modules:EMSegmenter-3.6|EM Algorithm]]  (Pohl et al 2007)
  

Revision as of 17:55, 29 March 2011

Home < EMSegmenter-Tasks:MRI-Human-Brain-HIPR

Return to EMSegmenter Task Overview Page

Description

High In-Plane Resolution (HIPR)
Single channel automatic segmentation of T1 and T2 MRI brain scans into the major tissue classes (gray matter, white matter, csf). The task can be applied to T1 and T2 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. The alpha parameter for the EMSegmenter has been set to 0.01 to handle the high in-plane resolution of the scans.

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

Input data

Image Dimension = 512 x 512 x 26
Image Spacing = 0.4688 x 0.4688 x 6

Anatomical Tree

  • root
    • background (BG)
      • air (AIR)
      • skull (skull)
    • intracranial cavity (ICC)
      • white matter (WM)
      • grey matter (GM)
      • cerebrospinal fluid (CSF)

Atlas

Atlas was generated based on 82 scans and corresponding segmentations provided by Psychiatry Neuroimaging Laboratory, BWH. We registered the scans to a preselected template via Warfield et al. 2001.
Image Dimension = 256 x 256 x 124
Image Spacing = 0.9375 x 0.9375 x 1.5

EMSegmenter MRI-Human-Brain Template 420x420.png EMSegmenter MRI-Human-Brain CSF 420x420.png EMSegmenter MRI-Human-Brain GM 420x420.png EMSegmenter MRI-Human-Brain WM 420x420.png
Template (T1) CSF GM WM

Result

Acknowledgment

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

Collaborators

Gabriella Szatmary, MD, PhD
Director of Neuro-Ophthalmology, Neuroimaging, Hattiesburg Clinic P.A., Mississippi

Tatjana Polgar, MBA
Research Assistant Neuro-Ophthalmology, Hattiesburg Clinic P.A., Mississippi

Citations