[Insight-users] How to smooth the segmented surface

[Bradley Lowekamp]

If the results of your segmentation was just labeled pixels, you may consider a level-set representation to obtain a sub-pixel representation of the surface. This could be a completed simply by smoothing the mask with a filter such as CurvatureFlowImageFilter, or refining the segmentation with a filter such as LaplacianSegmentationLevelSetImageFilter.


On Mar 21, 2012, at 6:07 AM, Dženan Zukić wrote:

> You can resample the image, or use linear interpolator.
> 
> On Tue, Mar 20, 2012 at 14:07, Xiaopeng Yang <yxp233 at postech.ac.kr> wrote:
> Hi Kent,
> 
>  
> 
> Do you know any interpolate class in ITK which can generate more slices? For volumetry, I guess I can use the original data.
> 
>  
> 
> Thanks,
> 
> Xiaopeng
> 
>  
> 
> From: Kent Ogden [mailto:ogdenk at upstate.edu] 
> Sent: Tuesday, March 20, 2012 9:50 PM
> To: insight-users at itk.org; Xiaopeng Yang
> 
> 
> Subject: Re: [Insight-users] How to smooth the segmented surface
> 
>  
> 
> Xiaopeng,
>  
> 
> This is a fundamental limitation of your data that can only truly be solved by reconstructing thinner slices at the time of the scan.  You could interpolate between images to generate more slices, which would result in a smoother looking rendering.  If you are trying to make quantitative measurements (e.g. volume) you must be careful about these kinds of manipulations though.
>  
> 
> Kent
>  
> 
> 
> 
> >>> "Xiaopeng Yang" <yxp233 at postech.ac.kr> 3/19/2012 10:17 PM >>>
> Dear Users,
> 
>  
> 
> I have tried to segment the liver from 5 mm CT slices. When I tried to visualize the segmented liver in 3D, I found that the surface of the 3D liver was discrete, just like stairs. I guess that is because of the 5 mm interval between CT slices. Do you guys have any good idea how to make the 3D surface of the liver look continuous and smooth?
> 
>  
> 
> Thanks,
> 
> Xiaopeng
> 
> 
> _____________________________________
> 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.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-users
> 
> 
> _____________________________________
> 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.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-users

========================================================
Bradley Lowekamp  
Medical Science and Computing for
Office of High Performance Computing and Communications
National Library of Medicine 
blowekamp at mail.nih.gov



-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.itk.org/pipermail/insight-users/attachments/20120321/3b2bd995/attachment-0001.htm>