ITK Registration Optimization

From NAMIC Wiki
Jump to: navigation, search
Home < ITK Registration Optimization

Summary

Goals

There are two components to this research

  1. Identify registration algorithms that are suitable for non-rigid registration problems that are endemic to NA-MIC
  2. Develop implementations of those algorithms that take advantage of multi-core and multi-processor hardware

Steps involved

  1. Modify ITK's registration framework to support oriented images
  2. Modify ITK's registration framework to be thread safe
  3. Develop multi-threaded versions of select registration modules
  4. Make everything backward compatible with ITK's existing registration methods and framework
  5. Deliver in ITK
  6. Develop helper classes and write IJ article

Target date for these deliverables: Jan 1, 2008

Planned follow-on work

Helper-classes in ITK

  1. Current available in Slicer3/Applications/CLI/RegisterImages
    • e.g., b-spline deformable registration using LBFSGB optimizer and Mattes MI metric

Slicer Modules for Registration

  1. Uses the helper classes and is available with them.

Devise a new metric for MI registration

Ideas for a new metrick

  1. If we always use every voxel for the metric, then we can cache the weights by the voxel's position wrt the adjacent control points. For example, for Kilian's situation of a control point every 2 voxels, then there really are only a few unique weight sets that are repeated throughout the volume. Luis had already brought up a variation on this idea.
  2. This method could also be combined with the rule to not evaluate voxels or control points that fall on background voxels. This too has been discussed, but such a rule makes multi-threading tricky in that we don't want to waste threads by allocating them to image regions that contain only background voxels.
  3. The metric could be closely tied to a multiresolution registration scheme. In fact, the grid and the image resolutions should perhaps be linearly related. That is, we could tie the metric computation to the resolution of the deformation grid by subsampling the image. There are situations where this is not a right thing to do (just because the grid is coarse doesn't mean that a small movement isn't important); HOWEVER, as part of a multiresolution registration strategy, it is perhaps the viable option. This would need to be evaluated on the data.

Instructions for early adopters

These instructions will tell you how to

  1. update your Slicer's getbuildtest.tcl and getbuildtest2.tcl files to perform a cvs checkout of itk
  2. update your ITK build process to enable the use of code in ITK's review directory (which is still in-development) and to specifically enable the use of optimized registration methods within that review directory.
  3. enable building the RegisterImages module

If you are using getbuildtest.tcl

  • Slicer3/slicer_variables.tcl
    • Line 82 (or there about): change it
SET ::ITK_TAG "HEAD"
  • Slicer3/Scripts/genlib.tcl
    • Line 636 (add the following to cmake definitions)
-DITK_USE_REVIEW:BOOL=ON \
-DITK_USE_OPTIMIZED_REGISTRATION_METHODS:BOOL=ON \
    • Line 646 (add the following to cmake definitions)
-DITK_USE_REVIEW:BOOL=ON \
-DITK_USE_OPTIMIZED_REGISTRATION_METHODS:BOOL=ON \

If you are using getbuildtest2.tcl

  • Slicer3/slicer_variables2.tcl
    • Line 83 (or there about): change it
SET ::ITK_TAG "HEAD"
  • Slicer3/Scripts/genlib2.tcl
    • The svn checkout needs to instead do a cvs update. You need to have cvs in your system path. You should edit the runcmd svn line to instead read:
 runcmd cvs -d :pserver:anonymous@www.itk.org:/cvsroot/Insight co Insight
    • Line 671 (add the following to cmake definitions)
-DITK_USE_REVIEW:BOOL=ON \
-DITK_USE_OPTIMIZED_REGISTRATION_METHODS:BOOL=ON \
    • Line 684 (add the following to cmake definitions)
-DITK_USE_REVIEW:BOOL=ON \
-DITK_USE_OPTIMIZED_REGISTRATION_METHODS:BOOL=ON \

Enable the RegisterImages module

  • Slicer3/Applications/CLI/CMakeLists.txt
    • Line 447 (or there about): add the line
SUBDIRS( RegisterImagesModule )

Done

  • With the above completed, perform getbuildtest.tcl or getbuildtest2.tcl as normal.
  • If you have questions, please contact stephen.aylward(at)kitware.com
    • Special thanks to Matt Turek and Luis Ibanez!

Known issues

  • BSplines registration is still a memory hog. We're working on it. See aboe for a discussion of the metric used.

Status and News

  1. Have developed mult-threaded registration metrics in ITK
    • Lead to the discovery that ITK's registration framework was not thread safe.
    • Making ITK's registration framework thread safe is conceptually a bug fix for ITK.
    • The incomplete implementation of oriented images in ITK has greatly extended the time and effort needed for this project.
      • Fixing this must be done in a manner that maintains ITK's backward compatibility.
      • This is a major effort involving approximately 50,000 lines of new code and over 400 new tests in ITK.
      • We have chosen to spend the time to integrate with ITK because it will serve the broader community, it will benefit from the support of the broader community, it will avoid having to incorporate another SVN checkout into Slicer's build process, and it will keep us from having to maintain and monitor separate dashboards for this effort.
  2. Weekly tcons, Monday, 10am
    • Luis Ibanez, Matt Turek, Stephen Aylward
  3. Active proposal to the ITK community:
  4. Project plan
  5. IJ article on oriented images and registration in ITK

Publications

  1. Aylward, Stephen; Jomier, Julien; Barre, Sebastien; Davis, Brad; Ibanez, Luis, "Optimizing ITK’s Registration Methods for Multi-processor, Shared-Memory Systems." MICCAI Open Source and Open Data Workshop, 2007 (Download PDF)

Quick Links

  1. Dashboard for this project
  2. Dashboard for BatchMake
  3. Batchboard (nightly experiment results) for this project
  4. BWH Neuroimaging Analysis Center (NAC), 2007-2008: Grid Enabled ITK

Algorithmic Requirements and Use Cases

  • Requirements
    1. relatively robust, with few parameters to tweak
    2. runs on grey scale images
    3. has already been published
    4. relatively fast (ideally speaking a few minutes for volume to volume).
    5. not patented
    6. can be implemented in ITK and parallelized.

Hardware Platform Requirements and Use Cases

  • Requirements
    1. Shared memory
    2. Single and multi-core machines
    3. Single and multi-processor machines
    4. AMD and Intel - Windows, Linux, and SunOS
  • Use-cases
    1. Intel Core2Duo
    2. Intel quad-core Xeon processors, Visual Studio 8, Windows Vista (Kitware: redwall)
    3. 6 CPU Sun, Solaris 8 (SPL: vision)
    4. 12 CPU Sun, Solaris 8 (SPL: forest and ocean)
    5. 16 core Opteron (SPL: john, ringo, paul, george)
    6. 16 core, Sun Fire, AMDOpteron (UNC: Styner)

Data

  • Now distributed with CVS

Workplan

Establish testing and reporting infrastructure

  1. Identify timing tools
    1. Cross platform and multi-threaded
    2. Timing and profiling
  2. Develop performance dashboard for collecting results
    1. Each test will report time and accuracy to a central server
    2. The performance of a test, over time, for a given platform can be viewed on one page
    3. The performance of a set of tests, at one point in time, for all platforms can be viewed on one page


Develop tests

  1. Develop modular tests
  2. Develop complete registration solutions for use cases


ITK Optimization

  • Target bottlenecks
    • Multi-thread metric calculation
      • Initial target is MattesMutualInformationImageToImageMetric
    • Optimize code
      • Sacrifice some memory and algorithm initialization speed to gain algorithm operation speed increases
      • Call multi-threaded functions when possible
  • Integrate metrics with transforms and interpolators for tailored performance

Example Results: MattesMutualInformationImageToImageMetric

Example of Optimizations Employed

  • GetValue
    • Added multi-threading to GetValue function
      • Partitions the samples - thereby distributes the computation of the transforms and interpolations across threads
      • Added the pre-computation of the FixedImageMarginalPDF for the sample to reduce the need for the thread mutex lock
        • Required the concept of an AdjustedFixedImageMarginalPDF that is updated when a fixed image voxel does not map into the moving image and thereby isn't valid for the current computations. By only updating when samples are missed, mutex lock to update a cross-thread data structure is needed less often.
      • Each thread now has its own copy of the joinPDF. After threads complete, jointPDFs from each thread are summed. This eliminates mutex from the main loop over samples.

Results

  • Speedup on a dual-core system is about 30% (reduction in computation time) when using linear transform and linear interpolation and about 45% when using bspline transform and bspline interpolation.

Performance Testing Results

GetValue Test at Identity Parameters

   // Print out a line with the test information
   std::cout << "GetValue2,";
   std::cout << metric->GetNameOfClass() << "," << interpolator->GetNameOfClass();
   std::cout << "," << transform->GetNameOfClass(); 

   // Make a time probe
   itk::TimeProbe timeProbe;

   // Run at the identity transform parameters.
   unsigned int numIters = 100;
   timeProbe.Start();
   for (unsigned int iter = 0; iter < numIters; iter++)
     {
     value = metric->GetValue( identityParameters );
     }
   timeProbe.Stop();

   // Print out the number of samples
   std::cout << "," << metric->GetNumberOfPixelsCounted();
   // Print out the time result.
   std::cout << "," << timeProbe.GetMeanTime()/numIters << std::endl;

GetValueAndDerivative Test at Identity Parameters

   // Print out a line with the test information
   std::cout << "GetValueAndDerivative2,";
   std::cout << metric->GetNameOfClass() << "," << interpolator->GetNameOfClass();
   std::cout << "," << transform->GetNameOfClass();

   // Make a time probe
   itk::TimeProbe timeProbe;

   // Evaluate at the identity transform;
   unsigned int numIters = 100;
   timeProbe.Start();
   for (unsigned int iter = 0; iter < numIters; iter++)
     {
     metric->GetValueAndDerivative( identityParameters, value, derivative );
     }
   timeProbe.Stop();

   // Print out the number of samples
   std::cout << "," << metric->GetNumberOfPixelsCounted();
   // Print out the time result.
   std::cout << "," << timeProbe.GetMeanTime()/numIters << std::endl;

Preliminary Results

January 5, 2008 - Note: "Opt" results are not using the OptLinearInterpolateImageFunction.


Events

Related Pages

Performance Measurement