[Insight-users] Medial curve extraction (itk::MedialCurveImageFilter)

[Sergio Vera]

Hi
The combination that worked for me is to use a Smoothed version of the
distance map (dist map + gaussian filter) however, check the following
things: distance map is correctly applied (ie: values are bigger at the
center of your mask).

Also check for any other wring input image. Input to the
AverageOutwardFluxFilter should be the smoothed distance map. Input for the
MedialSurfaceImageFilter should be the smoothed dmap + the output of the
AverageOutwardFluxFilter...

If this fails, maybe having a look at the code might help.

Regards.

On Tue, May 24, 2011 at 7:01 PM, Pedro Névoa <pedronevoa at gmail.com> wrote:

> Yes, the image contains a binary mask of the bone... What should I do then?
>
>
> I used the DanielssonDistanceMapImageFilt
> er to obtain the distance map and tried to run MedialCurve with the output
> of this algorithm, but it still fails.
>
> Thank you,
>
>
> No dia 24 de Maio de 2011 17:31, Sergio Vera <sergio.vera at alma3d.com>escreveu:
>
> Hi
>> Yes, vtk file, but what the image contains? it is a binary mask of the
>> bone? If this is true, medialAxis will  fail.
>>
>> regards
>>
>>
>> On Tue, May 24, 2011 at 5:49 PM, Pedro Névoa <pedronevoa at gmail.com>wrote:
>>
>>> Thank you for the answers.
>>>
>>> I am using a .vtk image as input to the filter.
>>>
>>>
>>> 2011/5/24 Sergio Vera <sergio.vera at alma3d.com>
>>>
>>>> Pedro,
>>>> what image are you passing as input to the filter?
>>>>
>>>> MedialCurveImageFilter requires a distance map in order to work
>>>> properly. Even more, you need to supply a smoothed distance map in. Although
>>>> not explicitly specified in the insight journal article, in the code example
>>>> you can see how it is done. My experience is that unsmoothed distance map
>>>> does not work, and that a gaussian blurred dist map is required.
>>>>
>>>> Hope it helps
>>>>
>>>> On Tue, May 24, 2011 at 12:16 AM, Daniel Blezek <Blezek.Daniel at mayo.edu
>>>> > wrote:
>>>>
>>>>>  Pedro,
>>>>>
>>>>>   We’ve found the MedialCurve method to be very sensitive, and
>>>>> difficult to use correctly.  In contrast, the BinaryThinningImageFilter3D
>>>>> (also from an Insight Journal article), does a very nice job.
>>>>>
>>>>> -dan
>>>>>
>>>>>
>>>>>
>>>>> On 5/23/11 3:26 PM, "Pedro Névoa" <pedronevoa at gmail.com> wrote:
>>>>>
>>>>> Hello,
>>>>>
>>>>> I'm trying to reduce a femur to a simple line, in order to achieve an
>>>>> image of the femur's medial axis. I tried to use the MedialCurve method to
>>>>> accomplish this but no results were obtained.
>>>>>
>>>>> The pixel type of the input image is signed short. I realize that the
>>>>> input pixel type accepted by Medial Curve is float so I changed the pixel
>>>>> type of my image to float using ImageReadCastWrite but it kept on not giving
>>>>> any results - the algorithm is processed endlessly.
>>>>>
>>>>> Does anyone know what may be the problem?
>>>>>
>>>>> Grateful for your attention,
>>>>>
>>>>>
>>>>> --
>>>>> *Daniel Blezek, PhD
>>>>> *Medical Imaging Informatics Innovation Center
>>>>>
>>>>> P 127 or (77) 8 8886
>>>>> T 507 538 8886
>>>>> E blezek.daniel at mayo.edu
>>>>>
>>>>> Mayo Clinic
>>>>> 200 First St. S.W.
>>>>> Harwick SL-44
>>>>> Rochester, MN 55905
>>>>> mayoclinic.org
>>>>> "It is more complicated than you think." -- RFC 1925
>>>>>
>>>>> _____________________________________
>>>>> 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
>>>>>
>>>>>
>>>>
>>>>
>>>> --
>>>> Sergio Vera
>>>>
>>>>  Alma IT Systems
>>>>  C/ Vilana, 4B, 4º 1ª
>>>>  08022 Barcelona
>>>>  T. (+34) 932 380 592
>>>>  www.alma3d.com
>>>>
>>>
>>>
>>>
>>> --
>>> Pedro Névoa
>>>
>>>
>>
>>
>> --
>> Sergio Vera
>>
>>  Alma IT Systems
>>  C/ Vilana, 4B, 4º 1ª
>>  08022 Barcelona
>>  T. (+34) 932 380 592
>>  www.alma3d.com
>>
>
>
>
> --
> Pedro Névoa
>
>


-- 
Sergio Vera

 Alma IT Systems
 C/ Vilana, 4B, 4º 1ª
 08022 Barcelona
 T. (+34) 932 380 592
 www.alma3d.com
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.itk.org/pipermail/insight-users/attachments/20110525/c44789a2/attachment-0001.htm>