[Insight-users] On the convergence speed of level set methods
Kai Li
likai at cs.uoregon.edu
Wed, 7 Apr 2004 14:11:32 -0700 (PDT)
Hi,
I just looked at the slides that you pointed to. Both of the multiscale
segmentation methods and the parallel approach are interesting and I
believe they are effective. I have several further questions about these
two approaches. For example, how much speedup the multiscale method can
achieve and does it cause any adverse influence to the segmentation
result for applications like human brain segmentation. About the parallel
approach, the speedup shown in the slides looks very good. It's
interesting to know if the parallel algorithm depends on shared memory
system, etc. So, I'd like to know more details on these approaches. It
would great if you can point me some materials such as papers on them.
Thanks again,
Kai
On Wed, 7 Apr 2004, Joshua Cates wrote:
> Hi,
>
> The best way to deal with this issue is to do a multi-scale segmentation
> with level-sets, or initialize your level-set segmentation with a prior
> generated by some faster method (confidence connected, for example). A
> multi-scale approach uses downsampled volumes at progressively higher
> resolutions to produce successively larger initializations. By the time
> you reach the full resolution, your initialization will be very close to
> the final solution, requiring much few iterations.
>
> There are a few slides on this in the tutorial:
>
> http://www.itk.org/CourseWare/Training/SegmentationMethodsOverview.pdf
>
> In general, level-sets are most effective when given an initialization
> that is reasonably close to the solution. Different methods will be more
> or less sensitive to initial conditions, but you will find some methods to
> be useless if initialized from a "seed point" surface. This is because
> the solver might converge on many reasonable solutions between your seed
> point and the solution that you are after.
>
> Another approach is to run the code in parallel. Both the narrow band
> level-set solver and the sparse field level-set solver can take advantage
> of multiple processors.
>
> Josh.
>
>
> On Wed, 7 Apr 2004, Kai Li wrote:
>
> > Hi,
> > I tried the level set method (GeodesicActiveContour) in ITK. I found
> > that when the front grows larger and larger, the time for each iteration
> > becomes slower and slower. It finally takes a long time for the whole
> > process to converge. This is especially the case for segmenting
> > shapes like the white matter. I'm investigating methods for improving this
> > problem. The question I'd like to ask here is whether ITK already has any
> > effective mechanism for this problem.
> >
> > Thanks,
> > Kai
> > _______________________________________________
> > Insight-users mailing list
> > Insight-users at itk.org
> > http://www.itk.org/mailman/listinfo/insight-users
> >
>