<div dir="ltr">It would be good to ensure the exe you're using is in release mode, it works lot faster than a program compiled in debug mode.</div><br><div class="gmail_quote"><div dir="ltr">El mar., 22 de sept. de 2015 a la(s) 1:31 p. m., Marina Bendersky <<a href="mailto:marina.bendersky@gmail.com">marina.bendersky@gmail.com</a>> escribió:<br></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">I guess I'm using the debug mode ... (not using Visual Studio).<br>
<br>
Thanks so much for your help!<br>
Marina<br>
<br>
On Mon, Sep 21, 2015 at 4:53 AM, Matias Montroull <<a href="mailto:matimontg@gmail.com" target="_blank">matimontg@gmail.com</a>> wrote:<br>
> Hi Marina,<br>
> Did you compile in release mode or debug?<br>
> Regards,<br>
><br>
> Matias<br>
><br>
> On Sep 14, 2015 7:56 PM, "Marina Bendersky" <<a href="mailto:marina.bendersky@gmail.com" target="_blank">marina.bendersky@gmail.com</a>><br>
> wrote:<br>
>><br>
>> Hello,<br>
>><br>
>> I'm doing a 3D registration of 2 CT volumes (the fixed one contains<br>
>> 131 dicom images and the moving has 145 dicom images).<br>
>><br>
>> I first converted each dicom series into one mha volume, using the<br>
>> example DicomSeriesReadImageWrite2.cxx and then, I do the registration<br>
>> following the example imageRegistration20.cxx. Below are the main<br>
>> registration components and parameters (other parameters had their<br>
>> default values):<br>
>><br>
>> typedef itk::AffineTransform< double, Dimension > TransformType;<br>
>> typedef itk::RegularStepGradientDescentOptimizer OptimizerType;<br>
>> typedef itk::MeanSquaresImageToImageMetric< FixedImageType,<br>
>> MovingImageType > MetricType;<br>
>> typedef itk::LinearInterpolateImageFunction< MovingImageType, double ><br>
>> InterpolatorType;<br>
>><br>
>> double translationScale = 1.0 / 1000.0;<br>
>> optimizer->SetMaximumStepLength( 0.05 );<br>
>> optimizer->SetMinimumStepLength( 0.01 );<br>
>><br>
>><br>
>> This 3D registration runs on a MacBookPro laptop for 5.5 hours, so I<br>
>> was wondering, is this "normal"? How long should a 3D registration<br>
>> take?<br>
>><br>
>> Also, the MSE metric keeps decreasing (though incrementally) even<br>
>> after 300 iterations (plot attached), and there are oscillations<br>
>> around the iteration 150 (I ran this twice and both times I get this<br>
>> plot!) - why could this be?<br>
>><br>
>> Should I expect the MSE metric to converge to 0, or something closer<br>
>> to 0 (instead of the current values, in the ninety thousands...)?<br>
>><br>
>> Thank you for your help,<br>
>> Marina<br>
>><br>
>> _____________________________________<br>
>> Powered by <a href="http://www.kitware.com" rel="noreferrer" target="_blank">www.kitware.com</a><br>
>><br>
>> Visit other Kitware open-source projects at<br>
>> <a href="http://www.kitware.com/opensource/opensource.html" rel="noreferrer" target="_blank">http://www.kitware.com/opensource/opensource.html</a><br>
>><br>
>> Kitware offers ITK Training Courses, for more information visit:<br>
>> <a href="http://www.kitware.com/products/protraining.php" rel="noreferrer" target="_blank">http://www.kitware.com/products/protraining.php</a><br>
>><br>
>> Please keep messages on-topic and check the ITK FAQ at:<br>
>> <a href="http://www.itk.org/Wiki/ITK_FAQ" rel="noreferrer" target="_blank">http://www.itk.org/Wiki/ITK_FAQ</a><br>
>><br>
>> Follow this link to subscribe/unsubscribe:<br>
>> <a href="http://public.kitware.com/mailman/listinfo/insight-users" rel="noreferrer" target="_blank">http://public.kitware.com/mailman/listinfo/insight-users</a><br>
>><br>
><br>
</blockquote></div><div dir="ltr">-- <br></div><div dir="ltr">Matias</div>