[Insight-users] Fwd: regarding itk_snap segmentation

[Luis Ibanez]

---------- Forwarded message ----------
From: Luis Ibanez <luis.ibanez at kitware.com>
Date: Sun, Aug 9, 2009 at 3:33 PM
Subject: Re: [Insight-users] regarding itk_snap segmentation
To: Taru S <swork24 at gmail.com>



Hi Taru,

The vtkContour filter is a much more evolved tool than the
itkBinaryMask3DMesh, so you may want to rely more on
that first filter.

You should be able to use either one for extracting surfaces
of structures that are, at least, on pixel apart.

What are you planning to do with the extracted surfaces ?

If it is Visualization,
then you are better off using the vtkContour filter.


      Regards,


              Luis


--------------------------------------------------------------------------

On Sun, Aug 9, 2009 at 2:53 PM, Taru S <swork24 at gmail.com> wrote:

> Hello Luis,
>
> Thank you  for your guidance. I  will try the  approach you  have
> mentioned.
>
> I  tried another approach so far and have a question regarding that:
>
> I extracted some of the iso-surfaces from my  segmented image using the
> vtk MarchingCubes(discrete) so far and am able to  show  the surface
> meshes.
> If I am not mistaken, this filter or the Contour filter  may not work for
> structures/labels with very close boundaries (i.e. there may be more than
> one structure with iso value < iso value for a particular str).
>  I am confused about the best approach for implementing the required
> functionality. I  read  some of the posts which  mention about  using vtk
> filters(contour, marching cubes)  directly to  generate surface meshes.
>
> Is there any specific advantage of using one approach ( vtkMarching cube
> vs. itkBinaryMask3DMesh) over the other ? Also, would  it help solving the
> above  problem with  close boundaries?
>
> I  will really appreciate your advise.
>
> Thank you,
>
> Regards,
> Taru
> On Sat, Aug 8, 2009 at 1:09 PM, Luis Ibanez <luis.ibanez at kitware.com>wrote:
>
>> Hi Taru,
>>
>> You may want to do the following:
>>
>>
>>    - Use the itkConnectedComponentImageFilter
>>    on the resulting segmentation
>>    - Then use the itkBinaryMask3DMeshSource
>>    to extract an itkMesh for each one of the labels
>>    in the connected components image
>>    - Finally use the itkVTKPolyDataWriter to write
>>    the itkMeshes in to .vtk legacy files.
>>
>>
>> Then to display the sufaces, yes, you need to create
>> a vtkActor for each one.
>>
>> See for example:
>>
>> InsightApplications/Auxiliary/vtk/
>>     itkReadITKImage3DSegmentShowVTK.cxx
>>     itkReadITKImageSegmentShowVTK.cxx
>>
>>
>>
>> Regards,
>>
>>
>>        Luis
>>
>>
>> -----------------------------
>>   On Wed, Aug 5, 2009 at 10:00 AM, Taru S <swork24 at gmail.com> wrote:
>>
>>>  Hello,
>>>
>>> I am new to VTK.  I have segmented a 3D MR volume using ITK-SNAP and now
>>> need to process each of these segmented structures using VTK.
>>>
>>> ITK-Snap allows me to save either the entire 3D segmentation or the
>>> individual mesh structures.
>>>
>>> Could you please guide me regarding the best way to extract the
>>> individual segmented structures from the full 3D segmented image (single
>>> image with all the segmented str not the individual meshes) so that I can
>>> process them individually(vtk filters - decimation etc) and create
>>> polygonal mesh models for each and finally a 3D volumetric model using all
>>> these meshes.
>>>
>>>
>>> Also, as per my understanding, I will need to create one vtkActor for
>>> each of the segmented structures. Please advise if this is the right way to
>>> do it ?
>>>
>>> I will really appreciate your help.
>>>
>>> --
>>> Regards,
>>> Taru
>>>
>>> _____________________________________
>>> Powered by www.kitware.com
>>>
>>> Visit other Kitware open-source projects at
>>> http://www.kitware.com/opensource/opensource.html
>>>
>>> Please keep messages on-topic and check the ITK FAQ at:
>>> http://www.itk.org/Wiki/ITK_FAQ
>>>
>>> Follow this link to subscribe/unsubscribe:
>>> http://www.itk.org/mailman/listinfo/insight-users
>>>
>>>
>>
>
>
> --
> Regards,
> Taru
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.itk.org/pipermail/insight-users/attachments/20090809/2dcecbb3/attachment.htm>