Contents

1 Reading and Writing Images
 1.1 Basic Example
 1.2 Pluggable Factories
 1.3 Using ImageIO Classes Explicitly
 1.4 Reading and Writing RGB Images
 1.5 Reading, Casting and Writing Images
 1.6 Extracting Regions
 1.7 Extracting Slices
 1.8 Reading and Writing Vector Images
  1.8.1 The Minimal Example
  1.8.2 Producing and Writing Covariant Images
  1.8.3 Reading Covariant Images
 1.9 Reading and Writing Complex Images
 1.10 Extracting Components from Vector Images
 1.11 Reading and Writing Image Series
  1.11.1 Reading Image Series
  1.11.2 Writing Image Series
  1.11.3 Reading and Writing Series of RGB Images
 1.12 Reading and Writing DICOM Images
  1.12.1 Foreword
  1.12.2 Reading and Writing a 2D Image
  1.12.3 Reading a 2D DICOM Series and Writing a Volume
  1.12.4 Reading a 2D DICOM Series and Writing a 2D DICOM Series
  1.12.5 Printing DICOM Tags From One Slice
  1.12.6 Printing DICOM Tags From a Series
  1.12.7 Changing a DICOM Header
2 Filtering
 2.1 Thresholding
  2.1.1 Binary Thresholding
  2.1.2 General Thresholding
 2.2 Edge Detection
  2.2.1 Canny Edge Detection
 2.3 Casting and Intensity Mapping
  2.3.1 Linear Mappings
  2.3.2 Non Linear Mappings
 2.4 Gradients
  2.4.1 Gradient Magnitude
  2.4.2 Gradient Magnitude With Smoothing
  2.4.3 Derivative Without Smoothing
 2.5 Second Order Derivatives
  2.5.1 Second Order Recursive Gaussian
  2.5.2 Laplacian Filters
   Laplacian Filter Recursive Gaussian
 2.6 Neighborhood Filters
  2.6.1 Mean Filter
  2.6.2 Median Filter
  2.6.3 Mathematical Morphology
   Binary Filters
   Grayscale Filters
  2.6.4 Voting Filters
   Binary Median Filter
   Hole Filling Filter
   Iterative Hole Filling Filter
 2.7 Smoothing Filters
  2.7.1 Blurring
   Discrete Gaussian
   Binomial Blurring
   Recursive Gaussian IIR
  2.7.2 Local Blurring
   Gaussian Blur Image Function
  2.7.3 Edge Preserving Smoothing
   Introduction to Anisotropic Diffusion
   Gradient Anisotropic Diffusion
   Curvature Anisotropic Diffusion
   Curvature Flow
   MinMaxCurvature Flow
   Bilateral Filter
  2.7.4 Edge Preserving Smoothing in Vector Images
   Vector Gradient Anisotropic Diffusion
   Vector Curvature Anisotropic Diffusion
  2.7.5 Edge Preserving Smoothing in Color Images
   Gradient Anisotropic Diffusion
   Curvature Anisotropic Diffusion
 2.8 Distance Map
 2.9 Geometric Transformations
  2.9.1 Filters You Should be Afraid to Use
  2.9.2 Change Information Image Filter
  2.9.3 Flip Image Filter
  2.9.4 Resample Image Filter
   Introduction
   Importance of Spacing and Origin
   A Complete Example
   Rotating an Image
   Rotating and Scaling an Image
   Resampling using a deformation field
   Subsampling and image in the same space
   Resampling an Anisotropic image to make it Isotropic
 2.10 Frequency Domain
  2.10.1 Computing a Fast Fourier Transform (FFT)
  2.10.2 Filtering on the Frequency Domain
 2.11 Extracting Surfaces
  2.11.1 Surface extraction
3 Registration
 3.1 Registration Framework
 3.2 ”Hello World” Registration
 3.3 Features of the Registration Framework
 3.4 Monitoring Registration
 3.5 Multi-Modality Registration
  3.5.1 Mattes Mutual Information
 3.6 Center Initialization
  3.6.1 Rigid Registration in 2D
  3.6.2 Initializing with Image Moments
  3.6.3 Similarity Transform in 2D
  3.6.4 Rigid Transform in 3D
  3.6.5 Centered Initialized Affine Transform
 3.7 Multi-Resolution Registration
  3.7.1 Fundamentals
  3.7.2 Fundamentals
 3.8 Multi-Stage Registration
  3.8.1 Fundamentals
  3.8.2 Cascaded Multistage Registration
 3.9 Transforms
  3.9.1 Geometrical Representation
  3.9.2 Transform General Properties
  3.9.3 Identity Transform
  3.9.4 Translation Transform
  3.9.5 Scale Transform
  3.9.6 Scale Logarithmic Transform
  3.9.7 Euler2DTransform
  3.9.8 CenteredRigid2DTransform
  3.9.9 Similarity2DTransform
  3.9.10 QuaternionRigidTransform
  3.9.11 VersorTransform
  3.9.12 VersorRigid3DTransform
  3.9.13 Euler3DTransform
  3.9.14 Similarity3DTransform
  3.9.15 Rigid3DPerspectiveTransform
  3.9.16 AffineTransform
  3.9.17 BSplineDeformableTransform
  3.9.18 KernelTransforms
 3.10 Interpolators
  3.10.1 Nearest Neighbor Interpolation
  3.10.2 Linear Interpolation
  3.10.3 B-Spline Interpolation
  3.10.4 Windowed Sinc Interpolation
 3.11 Metrics
  3.11.1 Mean Squares Metric
   Exploring a Metric
  3.11.2 Normalized Correlation Metric
  3.11.3 Mutual Information Metric
   Parzen Windowing
   Mattes et al. Implementation
  3.11.4 Normalized Mutual Information Metric
  3.11.5 Demons metric
  3.11.6 ANTS neighborhood correlation metric
 3.12 Optimizers
  3.12.1 Registration using the One plus One Evolutionary Optimizer
  3.12.2 Registration using masks constructed with Spatial objects
  3.12.3 Rigid registrations incorporating prior knowledge
 3.13 Deformable Registration
  3.13.1 FEM-Based Image Registration
  3.13.2 BSplines Image Registration
  3.13.3 Level Set Motion for Deformable Registration
  3.13.4 BSplines Multi-Grid Image Registration
  3.13.5 BSplines Multi-Grid Image Registration in 3D
  3.13.6 Image Warping with Kernel Splines
  3.13.7 Image Warping with BSplines
 3.14 Demons Deformable Registration
  3.14.1 Asymmetrical Demons Deformable Registration
  3.14.2 Symmetrical Demons Deformable Registration
 3.15 Visualizing Deformation fields
  3.15.1 Visualizing 2D deformation fields
  3.15.2 Visualizing 3D deformation fields
 3.16 Model Based Registration
 3.17 Point Set Registration
  3.17.1 Point Set Registration in 2D
  3.17.2 Point Set Registration in 3D
  3.17.3 Point Set to Distance Map Metric
 3.18 Registration Troubleshooting
  3.18.1 Too many samples outside moving image buffer
  3.18.2 General heuristics for parameter fine-tunning
4 Segmentation
 4.1 Region Growing
  4.1.1 Connected Threshold
  4.1.2 Otsu Segmentation
  4.1.3 Neighborhood Connected
  4.1.4 Confidence Connected
   Application of the Confidence Connected filter on the Brain Web Data
  4.1.5 Isolated Connected
  4.1.6 Confidence Connected in Vector Images
 4.2 Segmentation Based on Watersheds
  4.2.1 Overview
  4.2.2 Using the ITK Watershed Filter
 4.3 Level Set Segmentation
  4.3.1 Fast Marching Segmentation
  4.3.2 Shape Detection Segmentation
  4.3.3 Geodesic Active Contours Segmentation
  4.3.4 Threshold Level Set Segmentation
  4.3.5 Canny-Edge Level Set Segmentation
  4.3.6 Laplacian Level Set Segmentation
  4.3.7 Geodesic Active Contours Segmentation With Shape Guidance
 4.4 Feature Extraction
  4.4.1 Hough Transform
   Line Extraction
   Circle Extraction
5 Statistics
 5.1 Data Containers
  5.1.1 Sample Interface
  5.1.2 Sample Adaptors
   ImageToListSampleAdaptor
   PointSetToListSampleAdaptor
  5.1.3 Histogram
  5.1.4 Subsample
  5.1.5 MembershipSample
  5.1.6 MembershipSampleGenerator
  5.1.7 K-d Tree
 5.2 Algorithms and Functions
  5.2.1 Sample Statistics
   Mean and Covariance
   Weighted Mean and Covariance
  5.2.2 Sample Generation
   SampleToHistogramFilter
   NeighborhoodSampler
  5.2.3 Sample Sorting
  5.2.4 Probability Density Functions
   Gaussian Distribution
  5.2.5 Distance Metric
   Euclidean Distance
  5.2.6 Decision Rules
   Maximum Decision Rule
   Minimum Decision Rule
   Maximum Ratio Decision Rule
  5.2.7 Random Variable Generation
   Normal (Gaussian) Distribution
 5.3 Statistics applied to Images
  5.3.1 Image Histograms
   Scalar Image Histogram with Adaptor
   Scalar Image Histogram with Generator
   Color Image Histogram with Generator
   Color Image Histogram Writing
  5.3.2 Image Information Theory
   Computing Image Entropy
   Computing Images Mutual Information
 5.4 Classification
  5.4.1 k-d Tree Based k-Means Clustering
  5.4.2 K-Means Classification
  5.4.3 Bayesian Plug-In Classifier
  5.4.4 Expectation Maximization Mixture Model Estimation
  5.4.5 Classification using Markov Random Field