[Insight-developers] two-input filters don't work

[Kevin H. Hobbs]

On Mon, 2009-09-21 at 16:45 +0200, Michael Xanadu wrote:
> Kevin, finally I found the solution. It turned out that the
> segmentation has worked for the whole time. What I didn't know was
> that the quality of the segmentation depends on the number of slices.
> Usually, I used just four slices of dicom data for the input because
> of performance (all other filters worked fine with a low number of
> slices). But if I use more slices (today I did that for the first time
> for two-input-filters) I get an amazing segment (look at attachement)!
> My mistake was to believe that the segment grows thrue the iterations
> in x- and y-direction, even if z (slices) is low. Can you verify that?

3d segmentation should work fine even with small numbers of slices.

>  But I still wonder:
> 
> 1. Why does the segmentation works for 2D-image-files (png), even if
> an image is only one slice? In 3D it doesn't work with only one slice,
> like mentioned above. Are there differences in the algorithm?

Well yes, there could be differences. In particular I would think about
the boundary conditions of both the gradient magnitude, and curvature
smoothing filters.

> 
> 2. I never get a segment in the first slice of the data, no matter how
> many slices I use or in which slice I set the seedpoint or how many
> iterations I use. In the 16-slice-example, which you can find in the
> attachement, I set the seedpoint to the first slice ("00_slice.png").
> There you can see our cute white spot. And in second slice suddenly
> the segment appears! If I set the seedpoint to a slice in the middle
> of the data, both outer slices appear black. That led me to believe
> that the algorithm doesn't work for the outer slices. Can you verify
> that?

Look at the 3d gradient magnitude image. What does it look like at the
top and bottom slice.

> 
> 3. Why does my application crashes if I put sigmoid output to
> fastMarching input? 

You have not yet provided enough information for me to answer this
question.

> I already wrote that in my last mail. I still use fastMarching without
> an input.

Well you don't have to use that feature of the fast marching filter. It
would just provide a better initial level set when the object you want
is not very spherical.

> 
> Kevin, I just wanna thank you far for your help. You pushed me into
> the right direction to find the answer for my question.
> 

You're welcome.

> 
> Regards, Michael

-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 189 bytes
Desc: This is a digitally signed message part
URL: <http://www.itk.org/mailman/private/insight-developers/attachments/20090921/e7f075b4/attachment.pgp>