[Insight-users] [Insight-developers] A problem about segmentation

[Xiaoxiao Liu]

Hi Jianfeng,

Yes, user mailing list is a better place for such topics.

Some quick comments:

VectorGradientMagnitudeAnisotropicDiffusionImageFilter is used to smooth an
image while preserving the edges.
Please refer to  the example and the documentation for the filter:

http://www.itk.org/Wiki/ITK/Examples/Smoothing/VectorGradientAnisotropicDiffusionImageFilter

Are you trying to use watershed segmentation to label lung regions? Please
refer to the software guide about watershed segmentation:
http://www.itk.org/ItkSoftwareGuide.pdf   Or other segmentation
methods discussed in the guide.

Lung region in CT images usually have high contrast due to the air content.
  Simple image processing combinations ( threshold,   region growing,
mathematical morphological operations etc.) usually
generate satisfactory results.

Thanks!
-Xiaoxiao

On Fri, Oct 12, 2012 at 10:03 PM, 杨建峰 <13787890 at qq.com> wrote:

>
>
> I have a lung CT image,I want to segment the lung. First ,I used the
> itk::VectorGradientMagnitudeAnisotropicDiffusionImageFilter  class .
>
> The output is a lable image ,then I converted it to a RGB image .
>
> but, how can I find out the lung region in the original image.
>
> thanks for your help.
>
>
> 2012.10.13
>
>
> Yang Jianfeng
>
> _______________________________________________
> 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://kitware.com/products/protraining.php
>
> 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-developers
>
>


-- 


---------------------------------------------
*Xiaoxiao Liu*, Ph.D.
R & D Engineer
Kitware Inc <http://www.kitware.com/>.
Clifton Park, NY
Phone: (518) 881-4924  or  (518) 371-3971 x124
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.itk.org/pipermail/insight-users/attachments/20121013/00105f8f/attachment.htm>