[Insight-users] Automated 3D region growing algorithm

[Wes Turner]

Just to build a little on what Luis wrote, many of the algorithms require
seed-points, but that doesn't necessarily imply "interactively" specified
seed-points.  ITK implements the algorithms, but leaves the specification of
the seed-points up to the user of the algorithm.  If you have some
innovative way of automatically providing seed-points for one or more
anatomical structures those points can be used in place of interactive
selection.

- Wes

On 7/5/07, Luis Ibanez <luis.ibanez at kitware.com> wrote:
>
>
> Hi Kambiz,
>
>
> It all depends on how large is your classification of "Region Growing".
>
> What we formally call "Region Growing" methods in ITK: all require
> seed points or initial regions as input data.
>
>
> If you consider Watersheds to be a Region Growing method, then that will
> qualify for your question. Most Level Set methods could arguably be
> called "Region Growing" methods too.
>
>
> That being said, what you described is a pretty "Magical" method, since
> it is not clear to me *what* are you segmenting from the image. That is,
> a typical medical image will contain mutliple organs, and at some point
> you have to specify which one of all of those organs you are interested
> in segmenting, unless the segmentation method produces a total partition
> of the image... and stil we will have to ask if the blood vessels inside
> an organ should be classified as part of the organ or as part of the
> circulatory system...
>
>
> The description of this "magical" method sounds very appealing for a
> standard paper to be submitted to one of the many decadent journals
> and conferences in our field, where the main interest is to qualify for
> the "originality cookie" by claiming that the content of the paper is
> some "never seen before" method.
>
>
> It doesn't sound like the serious method that you may want to use
> for an actual medical application.
>
>
>
>     Regards,
>
>
>        Luis
>
>
>
> ------------------------
> kambiz rakhshan wrote:
> > Hi all users,
> > /I Would like to know if there is an algorithm in ITK that /is proposed
> > for the automated segmentation of three-dimensional images. No initial
> > parameters such as the homogeneity threshold or the seeds location have
> > to be adjusted. The principle of this method is to build a region
> > growing sequence by increasing the maximal homogeneity threshold from a
> > very small value to a large one. On each segmented region, a 3D
> > parameter that has been validated on a test image assesses the
> > segmentation quality.
> >
> > All the region growing algorith which nis developed by ITK need seed
> > points interactively.Is that right?
> > any comments will be appreciated.
> > Kambiz
> >
> >
> > ------------------------------------------------------------------------
> > Moody friends. Drama queens. Your life? Nope! - their life, your story.
> > Play Sims Stories at Yahoo! Games.
> > <http://us.rd.yahoo.com/evt=48224/*http://sims.yahoo.com/>
> >
> >
> > ------------------------------------------------------------------------
> >
> > _______________________________________________
> > 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
>



-- 
Wesley D. Turner, Ph.D.
Kitware, Inc.
R&D Engineer
28 Corporate Drive
Clifton Park, NY 12065-8662
Phone: 518-371-3971 x120
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://public.kitware.com/pipermail/insight-users/attachments/20070705/4de85e5d/attachment.htm