<html>
<head>
<style>
.hmmessage P
{
margin:0px;
padding:0px
}
body.hmmessage
{
font-size: 10pt;
font-family:Verdana
}
</style>
</head>
<body class='hmmessage'>
metric->SetNumberOfSpatialSamples( numberOfSamples );<BR>it seems that mutualinformation method only uses part of the image samples,<BR>
itkMeanSquaresImageToImageMetric uses all the image pixels. It is not surprise<BR>
for you to get the result for same modality image registration.<BR>
Guys, is it right?<BR><BR>> Date: Fri, 19 Dec 2008 17:00:24 +0100<BR>> From: carola.schmidt@igd.fraunhofer.de<BR>> To: insight-users@itk.org<BR>> Subject: [Insight-users] Problem with BSplines-Registration and Mutual Information Metric<BR>> <BR>> Hi, itk users.<BR>> <BR>> I am implementing the BSpline Registration to register CT-Data of the <BR>> abdomen. I use the LBFGSBOptimizer<BR>> and use the parameters of the deformableRegistration8.cxx file<BR>> <BR>> OptimizerType::BoundSelectionType <BR>> boundSelect(transform->GetNumberOfParameters());<BR>> OptimizerType::BoundValueType <BR>> upperBound(transform->GetNumberOfParameters());<BR>> OptimizerType::BoundValueType <BR>> lowerBound(transform->GetNumberOfParameters());<BR>> <BR>> boundSelect.Fill(0);<BR>> upperBound.Fill(0.0);<BR>> lowerBound.Fill(0.0);<BR>> <BR>> optimizer->SetBoundSelection(boundSelect);<BR>> optimizer->SetUpperBound(upperBound);<BR>> optimizer->SetLowerBound(lowerBound);<BR>> <BR>> optimizer->SetCostFunctionConvergenceFactor( 1e+7 );<BR>> optimizer->SetProjectedGradientTolerance( 1e-4 );<BR>> optimizer->SetMaximumNumberOfIterations( 500 );<BR>> optimizer->SetMaximumNumberOfEvaluations( 500 );<BR>> optimizer->SetMaximumNumberOfCorrections( 12 );<BR>> <BR>> <BR>> As metrics I tried itkMeanSquaresImageToImageMetric and <BR>> itkMattesMutualInformationImageToImageMetric. When I use the <BR>> itkMeanSquaresImageToImageMetric the registration takes really long but <BR>> the results are quite ok.<BR>> When I use itkMattesMutualInformationImageToImageMetric the registration <BR>> only takes a few seconds but most of the time the warped image looks <BR>> like a hardly deformed moving image. Since the registration time is very <BR>> short, it seems that the registration stops after a few steps and warps <BR>> the image then. I use those parameters for the mututal information:<BR>> <BR>> metric->SetNumberOfHistogramBins( 40 );<BR>> const unsigned int numberOfSamples = 10000; <BR>> //fixedRegion.GetNumberOfPixels()/ 10;<BR>> metric->SetNumberOfSpatialSamples( numberOfSamples );<BR>> metric->ReinitializeSeed( 76926294 );<BR>> metric->SetMovingImage(m_itkimage);<BR>> metric->SetFixedImage(m_itkatlas);<BR>> metric->SetFixedImageRegion(fixedRegion);<BR>> <BR>> Why does the Mutual Information Metric not work as expected? Should I <BR>> change the parameters of the optimizer?<BR>> Thanks for an answer.<BR>> <BR>> Ciao,<BR>> Carola<BR>> _______________________________________________<BR>> Insight-users mailing list<BR>> Insight-users@itk.org<BR>> http://www.itk.org/mailman/listinfo/insight-users<BR><BR><br /><hr />将地图和路线添加到您的聚会邀请中。 <a href='http://www.microsoft.com/windows/windowslive/events.aspx' target='_new'>为朋友们导航！</a></body>
</html>