[ITK-users] What is an accepted duration of a 3D registration? Should I expect the MSE to "converge" to 0?

[Siavash Khallaghi]

Marina, for example in Visual Studio, you can compile and run your program in release mode by changing the compilation type from a drop down menu. This makes your program run faster.

Siavash

Sent from my iPhone

> On Sep 20, 2015, at 10:35 PM, Marina Bendersky <marina.bendersky at gmail.com> wrote:
> 
> I'm not sure I understand what you mean ... I'm using the ITK version
> 4.6.1, compiling and building the example and then running the
> executable with my images. Is there an alternative/better way to run
> ITK code? (I apologize if the question is too basic).
> 
> Thanks,
> Marina
> 
> 
>> On Thu, Sep 17, 2015 at 9:53 AM, Dženan Zukić <dzenanz at gmail.com> wrote:
>> One possible reason for such slow registration could be compiling you
>> application in debug mode. Release mode is many times faster with ITK,
>> sometimes even hundredfold!
>> 
>> On Mon, Sep 14, 2015 at 6:56 PM, Marina Bendersky
>> <marina.bendersky at gmail.com> wrote:
>>> 
>>> Hello,
>>> 
>>> I'm doing a 3D registration of 2 CT volumes (the fixed one contains
>>> 131 dicom images and the moving has 145 dicom images).
>>> 
>>> I first converted each dicom series into one mha volume, using the
>>> example DicomSeriesReadImageWrite2.cxx and then, I do the registration
>>> following the example imageRegistration20.cxx. Below are the main
>>> registration components and parameters (other parameters had their
>>> default values):
>>> 
>>> typedef itk::AffineTransform< double, Dimension  >  TransformType;
>>> typedef itk::RegularStepGradientDescentOptimizer     OptimizerType;
>>> typedef itk::MeanSquaresImageToImageMetric< FixedImageType,
>>> MovingImageType >  MetricType;
>>> typedef itk::LinearInterpolateImageFunction< MovingImageType, double >
>>> InterpolatorType;
>>> 
>>> double translationScale = 1.0 / 1000.0;
>>> optimizer->SetMaximumStepLength( 0.05 );
>>> optimizer->SetMinimumStepLength( 0.01 );
>>> 
>>> 
>>> This 3D registration runs on a MacBookPro laptop for 5.5 hours, so I
>>> was wondering, is this "normal"? How long should a 3D registration
>>> take?
>>> 
>>> Also, the MSE metric keeps decreasing (though incrementally) even
>>> after 300 iterations (plot attached), and there are oscillations
>>> around the iteration 150 (I ran this twice and both times I get this
>>> plot!) - why could this be?
>>> 
>>> Should I expect the MSE metric to converge to 0, or something closer
>>> to 0 (instead of the current values, in the ninety thousands...)?
>>> 
>>> Thank you for your help,
>>> Marina
>>> 
>>> _____________________________________
>>> 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://public.kitware.com/mailman/listinfo/insight-users
> _____________________________________
> 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://public.kitware.com/mailman/listinfo/insight-users