Difference between revisions of "2011 Winter Project Week:SegEye"

From NAMIC Wiki
Jump to: navigation, search
Line 37: Line 37:
  
 
<h3>Progress</h3>
 
<h3>Progress</h3>
*We can segmented the eye ball.
+
*We segmented the eye ball.
 +
*Experiments:
 +
-VMTK Modules in Slicer for optic nerve segmentation.
 +
-The particle filtering based approach for nerve segmentation.
 +
-Ellipse constrained segmentation of optic lens.
 +
*Received a number of suggestions for future experiments:
 +
-Incorporate constraints on Hounsfield units for segmentation of CT imagery.
 +
-Use atlas for more robust localization of eye ball.
 +
-Add prior anatomical knowledge for optic nerve segmentation (surrounding bone easily visible).
 +
 
  
 
</div>
 
</div>

Revision as of 23:16, 13 January 2011

Home < 2011 Winter Project Week:SegEye


Segmentation of the eye ball.
Axial view of the eye ball segmentation.


Key Investigators

  • Georgia Tech: Ivan Kolesov and Allen Tannenbaum
  • MGH: Gregory Sharp

Objective

  • We are interested in segmenting the eye ball, lens, optic nerve, and the optic chiasm.
  • Anatomical structures are highly sensitive to radiation.
  • We are creating a framework to perform these segmentations, which is likely to require a different approach for each structures due to the proximity of multiple structures to each other.

Approach

  • The eye ball is considered to be the pivotal organ since its segmentation will localize the region of interest when looking for other structures.
  • We will reduce the dimensionality of this problem by performing model based segmentation for each structure.
  • Once the eye is segmented, we use this knowledge to locate the lens/ initialize optic nerve segmentation.
  • We would like to leverage the information provided by a CT scan with additional data from an MRI -- we have to consider this registration problem.



Progress

  • We segmented the eye ball.
  • Experiments:

-VMTK Modules in Slicer for optic nerve segmentation. -The particle filtering based approach for nerve segmentation. -Ellipse constrained segmentation of optic lens.

  • Received a number of suggestions for future experiments:

-Incorporate constraints on Hounsfield units for segmentation of CT imagery. -Use atlas for more robust localization of eye ball. -Add prior anatomical knowledge for optic nerve segmentation (surrounding bone easily visible).