[Insight-users] HessiantoObjectnessMeasureImageFilter

Jesse Ross-Jones jesse.rj at gmail.com
Fri Aug 23 09:07:19 EDT 2013


Thanks very much for the reply.

the example from here
http://itk.org/ITKExamples/src/Nonunit/Review/SegmentBloodVesselsWithMultiScaleHessianBasedMeasure/Documentation.htmlis
complete, and works great in the 2D case. When I tried to extend the
same filter for the 3D case however I end up with an empty volume. I looked
through both of the following
ITK/Modules/Nonunit/Review/test/itkMultiScaleHessianBasedMeasureImageFilterTest.cxx
ITK/Modules/Nonunit/Review/test/itkHessianToObjectnessMeasureImageFilterTest.cxx
To try to get a better idea, but the examples for these are also in 2D
also.
Reading the original paper in the submission of the filters to ITK i find
an example in 3d but it seems the filter has changed quite a bit since 2007.

For anyone coming across this thread in the future, the solution for me was
to set objectnessFilter->SetScaleObjectnessMeasure( true ); From the
documentation "Toggle scaling the objectness measure with the magnitude of
the largest absolute eigenvalue " I am reading further to figure out why
this is necessary for the 3D case but now I am able to generate the
segmented vessels using the multiscale Hessian filter.

Many thanks for your help,
Jesse


On Thu, Aug 22, 2013 at 6:39 PM, Matt McCormick
<matt.mccormick at kitware.com>wrote:

> On Thu, Aug 22, 2013 at 3:23 PM, Kevin H. Hobbs <hobbsk at ohio.edu> wrote:
> > On 08/22/2013 10:35 AM, Jesse Ross-Jones wrote:
> >> Hi,
> >> Thanks for the quick reply.
> >> Reading the documentation on the MultiScaleHessian, "The Hessian-based
> >> measure is computed from the Hessian image at each scale level and the
> >> best response is selected." Does this mean that the final image produced
> >> is the result at only one scale producing the best response or a mixture
> >> of the results at different scales and each pixel is takes the value
> >> from the hessian image giving the best response?
> >
> > The output images have at each pixel the greatest response and the scale
> > that produced it.
> >
> > I just took a look at :
> >
> >
> ITK/Modules/Nonunit/Review/include/itkMultiScaleHessianBasedMeasureImageFilter.hxx
> >
> > to make sure.
> >
> > The decision is made in the function UpdateMaximumResponse.
> >
>
> Yes, looking at the source code always has the most detailed,
> up-to-date explanation :-).
>
> This Insight Journal article for this class (referenced earlier) is
> informative, too.
>
> Here is an example:
>
>
> http://itk.org/ITKExamples/src/Nonunit/Review/SegmentBloodVesselsWithMultiScaleHessianBasedMeasure/Documentation.html
>
> HTH,
> Matt
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.itk.org/pipermail/insight-users/attachments/20130823/141e32e6/attachment.htm>


More information about the Insight-users mailing list