[Insight-users] Resampling segmentation

Luis Ibanez luis.ibanez at kitware.com
Thu May 15 16:37:30 EDT 2008


Hi Marius,

Is it your purpose to increase the resolution of a binary image ?


In that case, you may want to try one othe following:


    1) binaryImage -> DistanceMap -> Resample -> Threshold

                           or

    2) binaryImage ->AntiAliasFilter ->Resample -> Threshold


In the resampler you can now use a Linear interpolator.

In this way the resampling will have enough information for
reconstructing the contours of the segmentation, and you
will be able to recover a binary image at the end by
thresholding.


     Regards,


         Luis



------------------
Marius Erdt wrote:
> I've now tried nearest neighbor interpolation. This, however, just 
> scales the current segmentation, but does not smooth the "steps" of the 
> segmentation.
> I'm thinking about thresholding the linear interpolation result, but I'm 
> not sure if the result is "correct" if some arbitrary threshold is used.
> 
> Marius
> 
> Dan Mueller wrote:
> 
>> Hi Marius,
>>
>> You might want to try setting the the ResampleImageFilter Interpolator
>> to a NearestNeighborInterpolateImageFunction:
>>     
>> http://www.itk.org/Insight/Doxygen/html/classitk_1_1NearestNeighborInterpolateImageFunction.html 
>>
>>
>> This will keep the resampled output as a binary image.
>>
>> Is it possible to do the binary segmentation on the resampled MRI
>> data? This would be the ideal option in terms of quality...
>>
>> HTH
>>
>> Cheers, Dan
>>
>> 2008/5/15 Marius Erdt <marius.erdt at gmx.de>:
>>  
>>
>>> Hi,
>>>
>>> is there a way in ITK to resample not only greyvalue volumes but binary
>>> volumes?
>>>
>>> I've got a binary segmentation that was created from an anisotropic 
>>> MRI data
>>> set. Resampling the MRI data to isotropic voxels is not a problem 
>>> (using ITK
>>> resampleImageFilter). However resampling the binary volume using
>>> interpolation produces a non-binary output. I could threshold the 
>>> result,
>>> but that would not be a proper result in terms of linear interpolation
>>> between slices.
>>>
>>> Does anyone have an idea how to resample a binary volume such that the
>>> result is equivalent to a linear interpolation between the 
>>> segmentations of
>>> the slices.
>>>
>>> Thanks for any help,
>>>
>>> Marius
>>> _______________________________________________
>>> Insight-users mailing list
>>> Insight-users at itk.org
>>> http://www.itk.org/mailman/listinfo/insight-users
>>>
>>>     
>>
>>
>>   
> 
> 
> _______________________________________________
> Insight-users mailing list
> Insight-users at itk.org
> http://www.itk.org/mailman/listinfo/insight-users
> 


More information about the Insight-users mailing list