[ITK-users] Computational time of fast marching

[Lin M]

Hi guys.

I'm using fast marching to compute the distance map, but the time of
computation is much slower than I expected. Is it normal to cost about
250secs for a 512*512*365 image? I'm using the released mode.

My process is like this:
1. initialize a binary image (alive image) where segmented target is set to
1, the rest is set to 0
2. initialize the trial image where the neighbourhood of alive image is set
to 1, the rest is set to 0
3. give the two images to the adaptor and set the alive value and the trial
value both to 1
4. run fast marching

Do you have any ideas about that or some suggestions to improve the
performance. Thank you very much!

Best,
Lin
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/insight-users/attachments/20150323/47d7caba/attachment.html>