[Insight-users] Vascular Segmentation in ITK?

[Luis Ibanez]

Hi Steve,

When using LevelSets, common methods for generating
an initial estimate of the segmentation are:


A) Edge-preserving smoothing followed by

    A.1) Watersheds  or
    A.2) ConfidenceConnected  or
    A.3) ThresholdConnected


B) User-selected seed + FuzzyConnectednees
    followed by thresholding


C) User-selected seed(s) + FastMarchingLevelSet


D) User interaction for placing SpatialObjects
    and generating binary masks. E.g. use a
    sphere of a given radius for generating
    the initial binary mask.



You will find multiple examples of (C) in the
software guide


http://www.itk.org/ItkSoftwareGuide.pdf



  Regards,


    Luis



------------------
Steve Urban wrote:

> Hi Josh,
>  
> I'm following your and Luis's suggestions but from what I can see all of 
> the level-set examples require an initial estimate of the surface you 
> are trying to detect. Do you know of any methods that would not need an 
> estimate of the surface in the entire volume beforehand? It would be 
> kind of useless for the application I'm trying to implement if I'd have 
> to get an initial guess beforehand.
>  
> Thanks,
>  
> Steve
> 
> */Joshua Cates <cates at sci.utah.edu>/* wrote:
> 
>     Hi Steve,
> 
>     Have a look at the level-sets chapter the Software Guide and the
>     NarrowBandCurvesLevelSetImageFilterTest in
>     Testing/Code/Algorithms. These should help.
> 
>     Josh.
> 
> 
>     On Mon, 15 Mar 2004, Steve Urban wrote:
> 
>      > Thanks Josh and Luis,
>      >
>      > Luis I'm looking at the functions on your links (my
>      > application is in 3D) and for
>      > CurvesLevelSetImageFilter
>      > it says that my first input image must be an initial
>      > level set, and the other image is edge potential map.
>      >
>      > I'm not sure how I'm supposed to get these images? I
>      > assume that one is an edge-detected image of the basic
>      > shape/size we are looking for and the second one is
>      > the original image? Is that correct or am I missing a
>      > step?
>      >
>      > Thanks again!
>      >
>      > __________________________________
>      > Do you Yahoo!?
>      > Yahoo! Mail - More reliable, more storage, less spam
>      > http://mail.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
>