Difference between revisions of "2010 Winter Project Week Spine Segmentation Module in Slicer3"
Sylvainjaume (talk | contribs) (add Slicer screenshot of a vertebrae shape model) |
|||
Line 4: | Line 4: | ||
Image:spine_segmentation_module_in_slicer_002.png|Results of the SpineSegmentation module in Slicer 3.5 | Image:spine_segmentation_module_in_slicer_002.png|Results of the SpineSegmentation module in Slicer 3.5 | ||
Image:spine_segmentation_in_slicer_004.png|3D meshes of our automated segmentation results | Image:spine_segmentation_in_slicer_004.png|3D meshes of our automated segmentation results | ||
− | Image: | + | Image:Jaume_Loepprich_vertebrae_3D_rendering.png|Model of a lumbar vertebrae for our shape-based segmentation algorithm. This complex shape is detected across the volumetric image following an automated pattern recognition approach ([http://www.youtube.com/watch?v=kkAuP80kE8E see video]) |
</gallery> | </gallery> | ||
Line 50: | Line 50: | ||
|[[Image:spine_segmentation_module_in_slicer_000.png|thumb|280px|Results of the SpineSegmentation module in Slicer 3.5]] | |[[Image:spine_segmentation_module_in_slicer_000.png|thumb|280px|Results of the SpineSegmentation module in Slicer 3.5]] | ||
|[[Image:spine_segmentation_module_in_slicer_003.png|thumb|280px|Results of the SpineSegmentation module in Slicer 3.5]] | |[[Image:spine_segmentation_module_in_slicer_003.png|thumb|280px|Results of the SpineSegmentation module in Slicer 3.5]] | ||
+ | |} | ||
+ | |||
+ | {| | ||
+ | |[[Image:spine-segmentation-slicer-cylinder.png|thumb|280px|Double cylinder used for our model-based.]] | ||
|[[Image:Sylvain_Jaume_nerve_segmentation_rendering_2009.png|thumb|280px|Results of our automated nerve segmentation algorithm. The 3D rendering shows the nerves exiting the spinal cord and the ganglia]] | |[[Image:Sylvain_Jaume_nerve_segmentation_rendering_2009.png|thumb|280px|Results of our automated nerve segmentation algorithm. The 3D rendering shows the nerves exiting the spinal cord and the ganglia]] | ||
|} | |} | ||
Line 55: | Line 59: | ||
{| | {| | ||
|[[Image:Sylvain_Jaume_nerve_segmentation_intensity_profile_2009.png|thumb|560px|Intensity profile for the cross-section of a nerve. The MRI image was acquired using the wideband steady-state free-precession (WB-SSFP) protocol.]] | |[[Image:Sylvain_Jaume_nerve_segmentation_intensity_profile_2009.png|thumb|560px|Intensity profile for the cross-section of a nerve. The MRI image was acquired using the wideband steady-state free-precession (WB-SSFP) protocol.]] | ||
− | |[[Image:jaume_loepprich_graph_spine_segmentation_module_2010.png|thumb| | + | |} |
+ | |||
+ | {| | ||
+ | |[[Image:jaume_loepprich_graph_spine_segmentation_module_2010.png|thumb|560px|Organization of the source code for the SpineSegmentation module. This module is available as an extension module for Slicer 3.5.]] | ||
|} | |} | ||
Revision as of 05:47, 21 January 2010
Home < 2010 Winter Project Week Spine Segmentation Module in Slicer3Model of a lumbar vertebrae for our shape-based segmentation algorithm. This complex shape is detected across the volumetric image following an automated pattern recognition approach (see video)
Key Investigators
- Sylvain Jaume (MIT)
- Martin Loepprich (University of Heidelberg)
- Ron Kikinis, Steve Pieper (BWH)
- Polina Golland (MIT)
Objective
We are developing a Slicer module to segment the region within the thecal sac in MRI images of the spine. Our objective is to provide a segmentation and visualization tool to improve the treatment of disc herniation. The structures of interests are the cerebro-spinal fluid (CSF), the discs, the vertebrae and the spinal nerves. The main challenge is to perform the segmentation in a fully automated way.
Approach, Plan
Our plan for the project week is to integrate our code into Slicer 3.5. Our code analyzes the intensity profile of different regions in the MRI and automatically defines the optimum region for the CSF.
Progress
The algorithm has been implemented in Slicer 3.5 as an extension module. The code is organized as ITK and VTK classes. No interaction is required. The module has been tested on data sets acquired at Brigham and Women's Hospital using the Wideband Steady-State Free-Precession (WB-SSFP) MRI protocol [Krishna Nayak 2007].