[Insight-users] Vessel network extraction

[Karthik Krishnan]

I've used VMTK. Its a nice toolkit and can do part of what you want.

In particular it can do extraction of the centerline from the surface
of your binary segmentation. You could do this in ITK as well by
iterative thinning, but VMTK's approach is better. It does this by
doing a fastmarching on the embedded voronoi diagram of the
surface. On the downside, your surface needs to be topologically
good for this to happen well. The fastmarching approach also
has the downside of requiring you to specify the starting the
ending points of each segment

Given a centerline, it can also detect the branch points.



On Thu, Oct 16, 2008 at 8:14 AM, Simon Wilson <lists at xeosdd.net> wrote:
> Jordi,
>
> You might find what you're looking for in the Vascular Modeling Toolkit
> (VMTK):
>
> http://www.vmtk.org/
>
> I haven't looked into it in too much detail, but its based on both VTK and
> ITK.
>
> Hope that helps.
>
> Simon Wilson
>
> On 16/10/08 7:07 AM, "jordi inglada" <jordi.inglada at cnes.fr> wrote:
>
>> Hi all,
>>
>> I have found several classes in ITK which are useful for vessel extraction and
>> segmentation. I was wondering if there is anything in the library for the
>> reconstruction of the vessel network. That is, once a set of vessels have been
>> extracted, how to build the connections, brachings, junctions, etc.
>>
>> Thanks for your hints.
>>
>> Jordi
>>
>>
>> _______________________________________________
>> 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
>



-- 
Karthik Krishnan
R&D Engineer,
Kitware Inc.
Ph: 518 371 3971 x119
Fax: 518 371 3971