[Insight-users] Segmentation of noisy images

[Jon Haitz Legarreta]

Dear Claudia,
as for the dimensions, since ITK image types are templated over the
dimensionality, ITK will perform segmentation over 2D or 3D images without
any further consideration
.
As for the noise, you can try any edge preserving smothing filter ITK
offers (depending on the input images and requirements you have). You will
get rid of the noise and the sharp boundaries of your structures of
interest will be hopefully preserved, since you will need them afterwards
to perform the segmentation.
If you didn't have a look at it yet, the ITK Software Guide may give you
some hints on this.

In order to fill the holes, since you will apply the filter to an already
binarized image you may want to use the use the
BinaryMorphologicalClosingImageFilter. It works quite well.

So far, I've only used VTK for visualization purposes, so I am not aware of
the image processing filters it may have.

Hope this helps.

Kind regards,
JON HAITZ





On 6 December 2011 16:42, mlsc 310 <mlsc310 at gmail.com> wrote:

> Hi,
>
> I would like to do 3D segmentation on noisy medical images. The aim is to
> obtain at the end a binarized image volume where voxels that correspond to
> tissue are set to 1 and the background voxels are set to 0. I can consider
> that the object is uniform, but I have to eliminate the noisy voxels on the
> background and after segmentation I need to fill the holes on the object
> that I'll get during the segmentation process.
> As I'm using C++, I think that I can find on ITK and VTK some of the tools
> I need, but it is not clear for me which tools are more appropriate and
> when shall I use ITK or VTK for some of the steps.
> So far, I'm trying to find out if ConnectedThresholdImageFilter (ITK),
> FillHolesFilter (VTK) and PolyDataToImageData (VTK) are of any use on this.
> I appreciate any help.
>
> Regards,
> Claudia
> _____________________________________
> Powered by www.kitware.com
>
> Visit other Kitware open-source projects at
> http://www.kitware.com/opensource/opensource.html
>
> Kitware offers ITK Training Courses, for more information visit:
> http://www.kitware.com/products/protraining.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
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.itk.org/pipermail/insight-users/attachments/20111207/f2896a69/attachment.htm>