[Insight-users] Inconsistent registration result.

brian avants stnava at gmail.com
Wed Mar 13 10:08:40 EDT 2013 

 i believe the v4 version of mattes would allow you to avoid this problem.



brian




On Wed, Mar 13, 2013 at 9:46 AM, lien lee <lienlee at gmail.com> wrote:

> Hi Brain,
>
> Thanks. I did ask for information about v4.
>
> The issue I encountered could be stated as that, when I applied both the
> fixed image mask and moving image mask to MattesMI, and let it run with
> multi-threading technique, the results won't be consistent among different
> runs. A bunch of tests were done, the outcome of which appears as that it
> is an issue of thread safety (looks like Seth and Bradley both agreed on
> this), instead of an issue of sample points creation.  So, do you think
> that v4 has done the correct job about thread safety in my case?
>
>
> 2013/3/12 brian avants <stnava at gmail.com>
>
>> not sure if it was covered on this thread but i believe the v4 version of
>> mattes would allow you to avoid this problem.
>>
>> the implementation is slightly different in that the user determines the
>> point set and then passes it into the metric via  SetPointSet
>>
>>
>> brian
>>
>>
>>
>>
>> On Tue, Mar 12, 2013 at 11:31 AM, Seth Gilchrist <seth at mech.ubc.ca>wrote:
>>
>>> Hi Lien,
>>> Sorry for the confusion, by resampling I was thinking of the sampling
>>> that happens between your runs in which you are checking for consistency.
>>>  It appears you are doing this with your redefinition of
>>> SampleFixedImageRegion(). It seems that it must be a thread issue.
>>>
>>> Seth
>>>
>>>
>>> On Tue, Mar 12, 2013 at 7:00 AM, lien lee <lienlee at gmail.com> wrote:
>>>
>>>>  Hi Seth,
>>>>
>>>>  Thanks for your input. I want to make sure I understand you
>>>> correctly. I assume that you are suggesting to call
>>>> vMetric->SetUseFixedImageIndexes(true); and then manage to create and use
>>>> an index list of the sample points, so that I can avoid the random sampling
>>>> process.  But, I am not so sure I understand your term "re-sampling". I
>>>> looked into itk source code carefully. I found that the sampling process
>>>> (for creating the list of samples) was called in
>>>> itk::ImageToImageMetric::MultiThreadingInitialize(), which is called in
>>>> itk::MultiResolutionImageRegistrationMethod::Initialize().  That is to say,
>>>> the sample list is created only once for one image resolution level, but it
>>>> must be re-created for a new image resolution level since it is actually a
>>>> new image object.  Therefore, looks to me, there is no redundant repeated
>>>> sampling process to avoid.
>>>>
>>>>  In the sense of avoiding the random sampling procedure, I created a
>>>> sub-class of MattesMetric, and rewrote the SampleFixedImageRegion()
>>>> function, where I gave up the random sampling strategy and just used all
>>>> the odd indices of the points in my fixed image mask. Unfortunately, the
>>>> results are still inconsistent, which makes me prone to believe that this
>>>> is the problem of thread safety when two masks are applied as I mentioned
>>>> after I tried Bradley's suggestion.
>>>>
>>>>
>>>>
>>>> 2013/3/11 Seth Gilchrist <seth at mech.ubc.ca>
>>>>
>>>>> Hi Lien,
>>>>> Could you use create a sub class of the MattesMetric and define a new
>>>>> function GetFixedImageIndexes() to give you the indexes? You could then use
>>>>> SetFixedImageIndexes( <your index list> ) and that would
>>>>> prevent re-sampling. Maybe put in a request to have GetFixedImgeIndexes()
>>>>> added at some point.
>>>>>
>>>>>  Seth
>>>>>
>>>>>
>>>>>  On Mon, Mar 11, 2013 at 10:29 AM, lien lee <lienlee at gmail.com> wrote:
>>>>>
>>>>>>  Hi Bradley,
>>>>>>
>>>>>>  Sorry for the late response.
>>>>>>
>>>>>>  Just now, I tried what you have suggested, and I do see consistent
>>>>>> results among different runs on the two computers I have. So, the problem
>>>>>> should be that it is not thread safe when applying the two masks. I am
>>>>>> wondering what I should do next, since the single-threaded program runs
>>>>>> slowly. Is there any solution that I can use faster multi-threading
>>>>>> technique and still keep the results consistent? Does ITK v4 do a better
>>>>>> job in this regards?
>>>>>>
>>>>>>  BTW, another trial was done before I set
>>>>>> ITK_GLOBAL_DEFAULT_NUMBER_OF_THREADS to 1.
>>>>>> I called vMetric->SetNumberOfThreads(1), and I noticed that most of
>>>>>> the time only one thread was working through starring at the CPU usage in
>>>>>> Windows Task Manager.  But still, the results were inconsistent in
>>>>>> different runs. I could not explain this. I mention it just because it
>>>>>> might mean something to itk-developers.
>>>>>>
>>>>>> Thanks!
>>>>>>
>>>>>>
>>>>>> 2013/3/1 Bradley Lowekamp <blowekamp at mail.nih.gov>
>>>>>>
>>>>>>>  Hello,
>>>>>>>
>>>>>>>  How many threads are you running? Have you tried setting the
>>>>>>> environment variable ITK_GLOBAL_DEFAULT_NUMBER_OF_THREADS to 1, to see of
>>>>>>> the results then become consistent?
>>>>>>>
>>>>>>>  Brad
>>>>>>>
>>>>>>>    On Feb 28, 2013, at 5:52 PM, lien lee <lienlee at gmail.com> wrote:
>>>>>>>
>>>>>>>     Hi itk-users,
>>>>>>>
>>>>>>>  I took a further step today.  I derived a class
>>>>>>> from MattesMutualInformationImageToImageMetric, and made it being the
>>>>>>> metric, so that, I could sneak into itk and visit the protected
>>>>>>> member ImageToImageMetric< TFixedImage, TMovingImage
>>>>>>> >::m_FixedImageSamples. I printed out a couple of sample points (their
>>>>>>> coordinates and image values), and I also printed out the seed value of the
>>>>>>> random number generator, which I set as ReinitializeSeed(76926294).  I get
>>>>>>> the seed value by
>>>>>>> calling Statistics::MersenneTwisterRandomVariateGenerator::GetInstance()->GetSeed();
>>>>>>> In different runs, I do see same seed were used, but I also do see
>>>>>>> different sample points.  I tried this on two different computers, at both
>>>>>>> of which I saw the inconsistent results. Seems to be the random number
>>>>>>> generator is non-deterministic even with same seed.  However, the weird
>>>>>>> thing is if I do not use the image mask, it would be consistent.
>>>>>>>
>>>>>>>  Any thoughts?
>>>>>>>
>>>>>>>
>>>>>>> 2013/2/26 lien lee <lienlee at gmail.com>
>>>>>>>
>>>>>>>>  Hi Seth,
>>>>>>>>
>>>>>>>>  By clicking the link you provided, the code I saw there is as
>>>>>>>> partly attached, which is different from what I have with ITK 4.2 on my
>>>>>>>> computer.
>>>>>>>>
>>>>>>>>  I do not have experience with this code, and I am not exactly
>>>>>>>> sure how it works.  But, looks to me, optimizer would call the function
>>>>>>>> during each iteration, and the function would rebuild all the sample points
>>>>>>>> again and again for all the iterations.  If my understanding were correct,
>>>>>>>> this would be quite different from what I have with ITK 4.2 on my computer,
>>>>>>>> where all the samples were created
>>>>>>>> in MattesMutualInformationImageToImageMetric::Initialize() as *a
>>>>>>>> one time thing*, and the counted points would be determined for
>>>>>>>> each iteration using the current transform by checking whether the mapped
>>>>>>>> points were inside the moving image mask. Therefore, for the code I am
>>>>>>>> working on, to my understanding, if I called ReinitializeSeed(76926294)
>>>>>>>> before generating all the sample points
>>>>>>>> in MattesMutualInformationImageToImageMetric::Initialize(), the results
>>>>>>>> should be deterministic, no matter whether I applied the image masks or
>>>>>>>> not. But, the testing results with image mask applied does NOT support my
>>>>>>>> understanding.
>>>>>>>>
>>>>>>>>  BTW, to your question, my moving image mask may not be
>>>>>>>> "restrictive" because it occupied pretty much about 80% of the whole moving
>>>>>>>> image.
>>>>>>>>
>>>>>>>>  Thanks again for your inputs.
>>>>>>>>
>>>>>>>>
>>>>>>>>    106<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l106>template <class TFixedImage,
>>>>>>>> class TMovingImage>
>>>>>>>> 107<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l107>void
>>>>>>>> 108<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l108>MutualInformationImageToImageMetric<TFixedImage, TMovingImage>
>>>>>>>> 109<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l109>::SampleFixedImageDomain(
>>>>>>>> 110<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l110>  SpatialSampleContainer & samples) const
>>>>>>>> 111<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l111>{
>>>>>>>> 112<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l112>  typedef ImageRandomConstIteratorWithIndex<FixedImageType> RandomIterator;
>>>>>>>> 113<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l113>  RandomIterator randIter( this->m_FixedImage, this->GetFixedImageRegion() );
>>>>>>>> 114<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l114>
>>>>>>>> 115<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l115>  randIter.SetNumberOfSamples(m_NumberOfSpatialSamples);
>>>>>>>> 116<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l116>  randIter.GoToBegin();
>>>>>>>> 117<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l117>
>>>>>>>> 118<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l118>  typename SpatialSampleContainer::iterator iter;
>>>>>>>> 119<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l119>  typename SpatialSampleContainer::const_iterator end = samples.end();
>>>>>>>> 120<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l120>
>>>>>>>> 121<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l121>  bool allOutside = true;
>>>>>>>> 122<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l122>
>>>>>>>> 123<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l123>  this->m_NumberOfPixelsCounted = 0;    // Number of pixels that map into the
>>>>>>>> 124<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l124>                                        // fixed and moving image mask, if
>>>>>>>> 125<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l125>                                        // specified
>>>>>>>> 126<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l126>                                        // and the resampled fixed grid after
>>>>>>>> 127<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l127>                                        // transformation.
>>>>>>>> 128<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l128>
>>>>>>>> 129<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l129>  // Number of random picks made from the portion of fixed image within the
>>>>>>>> 130<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l130>  // fixed mask
>>>>>>>> 131<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l131>  SizeValueType numberOfFixedImagePixelsVisited = 0;
>>>>>>>> 132<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l132>  SizeValueType dryRunTolerance = this->GetFixedImageRegion().GetNumberOfPixels();
>>>>>>>> 133<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l133>  for( iter = samples.begin(); iter != end; ++iter )
>>>>>>>> 134<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l134>    {
>>>>>>>> 135<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l135>    // Get sampled index
>>>>>>>> 136<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l136>    FixedImageIndexType index = randIter.GetIndex();
>>>>>>>> 137<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l137>    // Get sampled fixed image value
>>>>>>>> 138<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l138>    ( *iter ).FixedImageValue = randIter.Get();
>>>>>>>> 139<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l139>    // Translate index to point
>>>>>>>> 140<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l140>    this->m_FixedImage->TransformIndexToPhysicalPoint(index,
>>>>>>>> 141<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l141>                                                      ( *iter ).FixedImagePointValue);
>>>>>>>> 142<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l142>
>>>>>>>> 143<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l143>    // If not inside the fixed mask, ignore the point
>>>>>>>> 144<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l144>    if( this->m_FixedImageMask
>>>>>>>> 145<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l145>        && !this->m_FixedImageMask->IsInside( ( *iter ).FixedImagePointValue ) )
>>>>>>>> 146<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l146>      {
>>>>>>>> 147<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l147>      ++randIter; // jump to another random position
>>>>>>>> 148<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l148>      continue;
>>>>>>>> 149<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l149>      }
>>>>>>>> 150<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l150>
>>>>>>>> 151<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l151>    if( allOutside )
>>>>>>>> 152<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l152>      {
>>>>>>>> 153<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l153>      ++numberOfFixedImagePixelsVisited;
>>>>>>>> 154<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l154>      if( numberOfFixedImagePixelsVisited > dryRunTolerance )
>>>>>>>> 155<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l155>        {
>>>>>>>> 156<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l156>        // We randomly visited as many points as is the size of the fixed image
>>>>>>>> 157<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l157>        // region.. Too may samples mapped ouside.. go change your transform
>>>>>>>> 158<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l158>        itkExceptionMacro(<< "Too many samples mapped outside the moving buffer");
>>>>>>>> 159<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l159>        }
>>>>>>>> 160<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l160>      }
>>>>>>>> 161<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l161>
>>>>>>>> 162<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l162>    MovingImagePointType mappedPoint =
>>>>>>>> 163<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l163>      this->m_Transform->TransformPoint( ( *iter ).FixedImagePointValue );
>>>>>>>> 164<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l164>
>>>>>>>> 165<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l165>    // If the transformed point after transformation does not lie within the
>>>>>>>> 166<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l166>    // MovingImageMask, skip it.
>>>>>>>> 167<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l167>    if( this->m_MovingImageMask
>>>>>>>> 168<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l168>        && !this->m_MovingImageMask->IsInside(mappedPoint) )
>>>>>>>> 169<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l169>      {
>>>>>>>> 170<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l170>      ++randIter;
>>>>>>>> 171<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l171>      continue;
>>>>>>>> 172<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l172>      }
>>>>>>>> 173<http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l173>
>>>>>>>> <http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD#l174>
>>>>>>>>
>>>>>>>>   2013/2/26 Seth Gilchrist <seth at mech.ubc.ca>
>>>>>>>>
>>>>>>>>> Hi Lien,
>>>>>>>>>  Unfortunately I have not used masks when performing
>>>>>>>>> registrations, so can't help you with this specific problem.
>>>>>>>>>
>>>>>>>>>  I took a look at the git blob for the MattesMutual...Metric and
>>>>>>>>> was examining how the decision to keep or reject a give point is handled.
>>>>>>>>> If you are setting a mask on both the fixed and moving images, this will
>>>>>>>>> change what points are used because a check is done to see if a point is in
>>>>>>>>> the fixed mask and if it is in the moving mask after applying the current
>>>>>>>>> transform. Could your moving image mask be too restrictive for the early
>>>>>>>>> stages of the registration?
>>>>>>>>>
>>>>>>>>>  You can read the code at:
>>>>>>>>>
>>>>>>>>> http://itk.org/gitweb?p=ITK.git;a=blob;f=Modules/Registration/Common/include/itkMutualInformationImageToImageMetric.hxx;h=1244e5c0be768696cf042f6f39739f4b2bdcbba6;hb=HEAD
>>>>>>>>>
>>>>>>>>>  Starting on line 108, specifically on line 162.
>>>>>>>>>
>>>>>>>>>  Cheers,
>>>>>>>>> Seth
>>>>>>>>>
>>>>>>>>> *Seth Gilchrist, MASc, PhD Candidate
>>>>>>>>> +---------------------------------------+
>>>>>>>>> Orthopaedic and Injury Biomechanics Group
>>>>>>>>> UBC Department of Mechanical Engineering
>>>>>>>>> 6th Floor-2635 Laurel Street
>>>>>>>>> Vancouver, BC V5Z-1M9
>>>>>>>>> +---------------------------------------+
>>>>>>>>> seth at mech.ubc.ca
>>>>>>>>> Fax 604-675-2576*
>>>>>>>>>
>>>>>>>>>
>>>>>>>>
>>>>>>>   _____________________________________
>>>>>>> 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
>>>>>>>
>>>>>>>
>>>>>>>
>>>>>>
>>>>>
>>>>
>>>
>>> _____________________________________
>>> 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
>>>
>>>
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.itk.org/pipermail/insight-users/attachments/20130313/fda46a45/attachment.htm>

More information about the Insight-users mailing list