Dear All,<br>
<br>
I have some problems with running BSpline with Mattes MI metric<br>
registration from example\registration directory.<br>
<br>
No matter how I try the various conbination of the paramters of <br>
LBFGSB or RegularStepGradient optimizer, the results that I can<br>
get are "Joint PDF summed to zero" with gradient optimizer or <br>
"Too many samples are mapping outside image" with LBFGSB.<br>
<br>
The images for registration are T1 256*256*92 brains. I am sure<br>
that the origin of fix and mov images are both [0,0,0], and the <br>
images have been rigidly aligned.<br>
<br>
I am windering is that the effects with regarding to the CMake<br>
option "ITK_USE_ORIENTED_IMAGE_DIRECTION=ON"? Because<br>
now the itkMattesMutualInformationImageMetric has been redirect<br>
to itkOptMattesMutualInformationImageMetric.<br>
<br>
The examples that I try were Deformable8, 12, 13 and 15. It all gave<br>
me the exceptions that mentioned above.<br>
<br>
Could you give some advice on this problem?<br>
<br>
Thanks very much.<br>
john<br>
<br>
<div class="AOLPromoFooter">
<hr style="margin-top:10px;" />
<b>AOL Email goes Mobile!</b> You can now read your AOL Emails whilst on the move. <a href="http://info.aol.co.uk/email1" target=_blank>Sign up</a> for a free AOL Email account with unlimited storage today.<br />
</div>