csci 6971: image registration lecture 9: registration components february 10, 2004

79
CSci 6971: Image Registration Lecture 9: Registration Components February 10, 2004 Prof. Chuck Stewart, RPI Dr. Luis Ibanez, Kitware

Upload: skyler

Post on 17-Mar-2016

63 views

Category:

Documents


1 download

DESCRIPTION

CSci 6971: Image Registration Lecture 9: Registration Components February 10, 2004. Prof. Chuck Stewart, RPI Dr. Luis Ibanez, Kitware. Registration Components. Basic Registration Framework. Image Registration Framework. Fixed Image. Metric. Moving Image. Interpolator. Optimizer. - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

CSci 6971: Image Registration Lecture 9: Registration Components

February 10, 2004

Prof. Chuck Stewart, RPIDr. Luis Ibanez, Kitware

Page 2: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 2

Registration Components

Basic Registration Framework

Page 3: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 3

Image Registration Framework

FixedImage

MovingImage

Metric

Transform

Interpolator Optimizer

Parameters

Page 4: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 4

Other Image Metrics

Mean Reciprocal

Square Differences

Page 5: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 5

Mean Reciprocal Squared Differences

Image A Image B

For each pixel in A

Difference( index ) = A( index ) – B( index )

1Match( A , B ) += ( 1 + λ ∙ Difference( index ) 2 )

Page 6: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 6

For each pixel in the Fixed Image

Fixed Image Grid

j

i

y

xFixed Image

Physical Coordinates

y’

x’Moving Image

Physical Coordinates

Moving Image Grid

j

i

Space Transform

Page 7: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 7

Mean Reciprocal Squared Differences

#include "itkImage.h"#include "itkMeanReciprocalSquareDifferenceImageToImageMetric.h"#include "itkLinearInterpolateImageFunction.h"#include "itkTranslationTransform.h"

typedef itk::Image< char, 2 > ImageType;

ImageType::ConstPointer fixedImage = GetFixedImage(); ImageType::ConstPointer movingImage = GetMovingImage();

typedef itk::LinearInterpolateImageFunction< ImageType, double > InterpolatorType;

InterpolatorType::Pointer interpolator = InterpolatorType::New();

typedef itk::TranslationTransform< double, 2 > TransformType;

TransformType::Pointer transform = TransformType::New();

Page 8: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 8

typedef itk::MeanReciprocalSquareDifferenceImageToImageMetric< ImageType, ImageType > MetricType;

MetricType::Pointer metric = MetricType::New();

metric->SetInterpolator( interpolator );metric->SetTransform( transform );

metric->SetFixedImage( fixedImage );metric->SetMovingImage( movingImage );

MetricType::TransformParametersType translation( Dimension );

translation[0] = 12;translation[1] = 27;

double value = metric->GetValue( translation );

Mean Reciprocal Squared Differences

Page 9: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 9

Evaluating many matches

y

Fixed Image

Transform

x

y

Moving Imagex

Page 10: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 10

Plotting the Metric

Mean Reciprocal Squared Differences

Transform Parametric Space

Page 11: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 11

Plotting the Metric

Mean Reciprocal Squared Differences

Transform Parametric Space

Page 12: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 12

Evaluating many matches

y

Fixed Image

Transform

x

y

Moving Imagex

(-15,-25) mm

Page 13: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 13

Plotting the Metric

Mean Reciprocal Squared Differences

Transform Parametric Space

Page 14: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 14

Plotting the Metric

Mean Reciprocal Squared Differences

Transform Parametric Space

Page 15: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 15

Watch over your optimizer

Example:

Optimizer registering an image with itself starting at (-15mm, -25mm)

Page 16: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 16

Plotting the Optimizer’s Path

Mean Reciprocal Squared Differences

Step Length = 1.0 mm

Page 17: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 17

Plotting the Optimizer’s Path

Mean Reciprocal Squared Differences

Step Length = 2.0 mm

Page 18: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 18

Plotting the Optimizer’s Path

Mean Reciprocal Squared Differences

Step Length = 5.0 mm

Page 19: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 19

Plotting the Optimizer’s Path

Mean Reciprocal Squared Differences

Step Length = 10.0 mm

Page 20: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 20

Plotting the Optimizer’s Path

Mean Reciprocal Squared Differences

Step Length = 20.0 mm

Page 21: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 21

Plotting the Optimizer’s Path

Mean Reciprocal Squared Differences

Step Length = 40.0 mm

Page 22: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 22

Quiz #1

If the Metric is Noisy

Where is the noise coming from ?

Page 23: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 23

Smoothing the Image

Page 24: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 24

Evaluating many matches

y

Fixed Image

Transform

x

y

Moving Imagex

Page 25: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 25

Plotting the Smoothed Metric

Mean Reciprocal Squared Differences

Transform Parametric Space

Page 26: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 26

Plotting the Smoothed Metric

Mean Reciprocal Squared Differences

Transform Parametric Space

Page 27: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 27

Watch over your optimizer

Example:

Optimizer registering an image with itself starting at (-15mm, -25mm)

Page 28: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 28

Plotting the Optimizer’s Path

Mean Reciprocal Squared Differences

Step Length = 1.0 mm

Page 29: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 29

Plotting the Optimizer’s Path

Mean Reciprocal Squared Differences

Step Length = 2.0 mm

Page 30: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 30

Plotting the Optimizer’s Path

Mean Reciprocal Squared Differences

Step Length = 5.0 mm

Page 31: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 31

Plotting the Optimizer’s Path

Mean Reciprocal Squared Differences

Step Length = 10.0 mm

Page 32: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 32

Plotting the Optimizer’s Path

Mean Reciprocal Squared Differences

Step Length = 20.0 mm

Page 33: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 33

Plotting the Optimizer’s Path

Mean Reciprocal Squared Differences

Step Length = 40.0 mm

Page 34: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 34

Evaluating many matches

y

Fixed Image

Transform

x

y

Moving Imagex

(-15,-25) mm

Page 35: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 35

Plotting the Smoothed Metric

Mean Reciprocal Squared Differences

Transform Parametric Space

Page 36: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 36

Plotting the Smoothed Metric

Mean Reciprocal Squared Differences

Transform Parametric Space

Page 37: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 37

Watch over your optimizer

Example:

Optimizer registering an image shifted by (-15mm, -25mm)

The optimizer starts at (0mm,0mm)

Page 38: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 38

Plotting the Optimizer’s Path

Mean Reciprocal Squared Differences

Step Length = 1.0 mm

Page 39: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 39

Plotting the Optimizer’s Path

Mean Reciprocal Squared Differences

Step Length = 2.0 mm

Page 40: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 40

Plotting the Optimizer’s Path

Mean Reciprocal Squared Differences

Step Length = 5.0 mm

Page 41: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 41

Plotting the Optimizer’s Path

Mean Reciprocal Squared Differences

Step Length = 10.0 mm

Page 42: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 42

Plotting the Optimizer’s Path

Mean Reciprocal Squared Differences

Step Length = 20.0 mm

Page 43: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 43

Plotting the Optimizer’s Path

Mean Reciprocal Squared Differences

Step Length = 40.0 mm

Page 44: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 44

Other Image Metrics

Multi – Modality

Registration

Page 45: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 45

Multiple Image Modalities

Number of pairs

Page 46: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 46

Multiple Image Modalities

More possible pairs

Page 47: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 47

Intuitive Notion of Joint Entropy

The More Pairs Exist

The Larger the Joint Entropy

Page 48: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 48

Mutual Information

Reduction of Number of Pairs

Reduction of Joint Entropy

Page 49: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 49

Mutual Information

Mutual Information =

Joint Entropy ( Image A, Image B )

- Entropy Image A

- Entropy Image B

Page 50: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 50

Mattes Mutual Information

#include "itkImage.h"#include "itkMattesMutualInformationImageToImageMetric.h"#include "itkLinearInterpolateImageFunction.h"#include "itkTranslationTransform.h"

typedef itk::Image< char, 2 > ImageType;

ImageType::ConstPointer fixedImage = GetFixedImage(); ImageType::ConstPointer movingImage = GetMovingImage();

typedef itk::LinearInterpolateImageFunction< ImageType, double > InterpolatorType;

InterpolatorType::Pointer interpolator = InterpolatorType::New();

typedef itk::TranslationTransform< double, 2 > TransformType;

TransformType::Pointer transform = TransformType::New();

Page 51: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 51

typedef itk::MattesMutualInformationImageToImageMetric< ImageType, ImageType > MetricType;

MetricType::Pointer metric = MetricType::New();

metric->SetNumberOfHistogramBins( 20 );metric->SetNumberOfSpatialSamples( 10000 );

metric->SetInterpolator( interpolator );metric->SetTransform( transform );

metric->SetFixedImage( fixedImage );metric->SetMovingImage( movingImage );

MetricType::TransformParametersType translation( Dimension );translation[0] = 12;translation[1] = 27;

double value = metric->GetValue( translation );

Mattes Mutual Information

Page 52: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 52

Evaluating many matches

y

Fixed Image

Transform

x

y

Moving Imagex

Page 53: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 53

Plotting the Same Modality Metric

Mattes Mutual Information

Transform Parametric Space

Page 54: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 54

Plotting the Same Modality Metric

Mattes Mutual Information

Transform Parametric Space

Page 55: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 55

Evaluating many matches

y

Fixed Image

Transform

x

y

Moving Imagex

(-15,-25) mm

Page 56: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 56

Plotting the Same Modality Metric

Mattes Mutual Information

Transform Parametric Space

Page 57: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 57

Plotting the Same Modality Metric

Mattes Mutual Information

Transform Parametric Space

Page 58: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 58

Evaluating many matches

y

Fixed Image

Transform

x

y

Moving Imagex

Page 59: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 59

Plotting the Multi-Modality Metric

Mattes Mutual Information

Transform Parametric Space

Page 60: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 60

Plotting the Multi-Modality Metric

Mattes Mutual Information

Transform Parametric Space

Page 61: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 61

Evaluating many matches

y

Fixed Image

Transform

x

y

Moving Imagex

Page 62: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 62

Plotting the Multi-Modality Metric

Mattes Mutual Information

Transform Parametric Space

Page 63: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 63

Plotting the Multi-Modality Metric

Mattes Mutual Information

Transform Parametric Space

Page 64: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 64

Watch over your optimizer

Example:

Optimizer registering two aligned multi-modality images

starting at (-15mm, -25mm)

Page 65: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 65

Plotting the Optimizer’s Path

Mattes Mutual Information

Step Length = 1.0 mm

Page 66: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 66

Plotting the Optimizer’s Path

Mattes Mutual Information

Step Length = 2.0 mm

Page 67: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 67

Plotting the Optimizer’s Path

Mattes Mutual Information

Step Length = 5.0 mm

Page 68: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 68

Plotting the Optimizer’s Path

Mattes Mutual Information

Step Length = 10.0 mm

Page 69: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 69

Plotting the Optimizer’s Path

Mattes Mutual Information

Step Length = 20.0 mm

Page 70: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 70

Plotting the Optimizer’s Path

Mattes Mutual Information

Step Length = 40.0 mm

Page 71: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 71

Watch over your optimizer

Example:

Optimizer registering two multi-modality

images shifted by (-15mm, -25mm)

The optimizer starts at (0mm,0mm)

Page 72: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 72

Plotting the Optimizer’s Path

Mattes Mutual Information

Step Length = 1.0 mm

Page 73: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 73

Plotting the Optimizer’s Path

Mattes Mutual Information

Step Length = 2.0 mm

Page 74: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 74

Plotting the Optimizer’s Path

Mattes Mutual Information

Step Length = 5.0 mm

Page 75: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 75

Plotting the Optimizer’s Path

Mattes Mutual Information

Step Length = 10.0 mm

Page 76: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 76

Plotting the Optimizer’s Path

Mattes Mutual Information

Step Length = 20.0 mm

Page 77: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 77

Plotting the Optimizer’s Path

Mattes Mutual Information

Step Length = 40.0 mm

Page 78: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 78

Mutual Information Variants in ITK

• Viola – Wells• Mattes• Mutual Information Histogram

Page 79: CSci 6971: Image Registration  Lecture 9:  Registration Components February 10, 2004

Image Registration Lecture 9 79

End

Enjoy ITK !