[Insight-users] Extract centerlines from a 3D segmented binary image

[Dan Mueller]

Hi SuperZZ,

You need to use a distance map (e.g.
SignedMaurerDistanceMapImageFilter) as the speed function. Basically
you want an image which has the highest values near the centerline,
and lower values as you move further from the centerlines. (As I said,
this method is a little tricky due to the need for a good speed
function, but the result is a continuous directed path.) Perhaps you
could post your dataset?

HTH

Cheers, Dan

On 9 April 2012 03:37, zlf <jxdw_zlf at yahoo.com.cn> wrote:
> Thank you Dan,
>
> I tested this algorithm with my test data. Unfortunately, the result(red
> line) is obviously not centerline.
>
> I have a pre-segmented binary airway image. Speed image is produced in this
> way: all points inside the airway are filled value 1.0. Other points are
> filled with value 0.0.
>
> I am not sure whether my speed image is acceptable for fast marching.
>
> http://itk-insight-users.2283740.n2.nabble.com/file/n7448137/centerline.jpg
>
> Regards,
>
> superZZ
>
> --
> View this message in context: http://itk-insight-users.2283740.n2.nabble.com/Extract-centerlines-from-a-3D-segmented-binary-image-tp7442320p7448137.html
> Sent from the ITK Insight Users mailing list archive at Nabble.com.
> _____________________________________
> Powered by www.kitware.com
>
> Visit other Kitware open-source projects at
> http://www.kitware.com/opensource/opensource.html
>
> Kitware offers ITK Training Courses, for more information visit:
> http://www.kitware.com/products/protraining.php
>
> Please keep messages on-topic and check the ITK FAQ at:
> http://www.itk.org/Wiki/ITK_FAQ
>
> Follow this link to subscribe/unsubscribe:
> http://www.itk.org/mailman/listinfo/insight-users