[Insight-users] IJ Test that will fail

[Luis Ibanez]

Kevin,

>
> The error shows up in background pixels near the piece boundaries.
>


                           This is an important clue.


The Fast Marching method uses very large values to mark pixels
that have not been visited yet by the propagation front.

It may well be that when distributing the computation, your code
is accumulating these large values. We won't be able to tell for
sure until your code is posted somewhere...


    Regards


      Luis