A Survey of Medical Image Registration

1
A Survey of Medical Image Registration

• J.B.Maintz,M.A Viergever
• Medical Image Analysis,1998

2
Medical Image

• SPECT (Single Photon Emission Computed
  Tomography)
• PET (Positron Emission Tomography)
• MRI (Magnetic Resonance Image)
• CT (Computed Tomography)

3
Image Modalities

• Anatomical
• Depicting primarily morphology (MRI,CT,X-ray)
• Functional
• Depicting primarily information on the metabolism
  of the underlying anatomy (SPECT,PET)

4
Medical Image Integration

• Registration
• Bring the modalities involved into spatial
  alignment
• Fusion
• Integrated display of the data involved
• Matching, Integration,Correlation,

5
Registration procedure

• Problem statement
• Registration paradigm
• Optimization procedure
• Pillars and criteria are heavily interwined
  and have many cross-influences

6
Classification of Registration Methods
Dimensionality Nature of Registration basis Nature of transformation
Domain of transformation Interaction Optimization procedure
Modalities involved Subject Object
7
Dimensionality

• Spatial dimensions only
• 2D/2D
• 2D/3D
• 3D/3D
• Time series(more than two images), with spatial
  dimensions
• 2D/2D
• 2D/3D
• 3D/3D

8
Spatial registration methods

• 3D/3D registration of two images
• 2D/2D registration
• Less complex by an order of magnitude both
  where the number of parameters and the volume of
  the data are concerned.
• 2D/3D registration
• Direct alignment of spatial data to projective
  data, or the alignment of a single tomographic
  slice to spatial data

9
Registration of time series

• Time series of images are required for various
  reasons
• Monitoring of bone growth in children (long time
  interval)
• Monitoring of tumor growth (medium interval)
• Post-operative monitoring of healing (short
  interval)
• Observing the passing of an injected bolus
  through a vessel tree (ultra-short interval)
• Two images need to be compared.

10
Nature of registration basis

• Image based
• Extrinsic
• based on foreign objects introduced into the
  imaged space
• Intrinsic
• based on the image information as generated by
  the patient
• Non-image based (calibrated coordinate systems)

11
Extrinsic registration methods

• Advantage
• registration is easy, fast, and can be
  automated.
• no need for complex optimization algorithms.
• Disadvantage
• Prospective character must be made in the
  pre-acquisition phase.
• Often invasive character of the marker objects.
• Non-invasive markers can be used, but less
  accurate.

12
Extrinsic registration methods

• Invasive
• Stereotactic frame
• Fiducials (screw markers)
• Non-invasive
• Mould,frame,dental adapter,etc
• Fiducials (skin markers)

13
Extrinsic registration methods

• The registration transformation is often
  restricted to be rigid (translations and
  rotations only)
• Rigid transformation constraint, and various
  practical considerations, use of extrinsic 3D/3D
  methods are limited to brain and orthopedic
  imaging

14
Intrinsic registration methods

• Landmark based
• Segmentation based
• Voxel property based

15
Landmark based registration

• Anatomical
• salient and accurately locatable points of the
  morphology of the visible anatomy, usually
  identified by the user
• Geometrical
• points at the locus of the optimum of some
  geometric property,e.g.,local curvature
  extrema,corners,etc, generally localized in an
  automatic fashion.

16
Landmark based registration

• The set of registration points is sparse
• ---fast optimization procedures
• Optimize Measures
• Average distance between each landmark
• Closest counterpart (Procrustean Metric)
• Iterated minimal landmark distances
• Algorithm
• Iterative closest point (ICP)
• Procrustean optimum
• Quasi-exhaustive searches, graph matching and
  dynamic programming approaches

17
Segmentation based registration

• Rigid model based
• Anatomically the same structures(mostly
  surfaces) are extracted from both images to be
  registered, and used as the sole input for the
  alignment procedure.
• Deformable model based
• An extracted structure (also mostly surfaces,
  and curves) from one image is elastically
  deformed to fit the second image.

18
Rigid model based

• head-hat method
• rely on the segmentation of the skin surface
  from CT,MR, and PET images of the head
• Chamfer matching
• alignment of binary structures by means of a
  distance transform

19
Deformable model based

• Deformable curves
• Snakes, active contours,nets(3D)
• Data structure
• Local functions, i.e., splines
• Deformable model approach
• Template model defined in one image
• template is deformed to match second image
• segmented structure
• unsegmented

20
Voxel property based registration

• Operate directly on the image grey values
• Two approaches
• Immediately reduce the image grey value content
  to a representative set of scalars and
  orientations
• Use the full image content throughout the
  registration process

21
Principal axes and moments based

• Image center of gravity and its principal
  orientations (principal axes) are computed from
  the image zeroth and first order moment
• Align the center of gravity and the principal
  orientations
• Principal axes Easy implementation, no high
  accuracy
• Moment based require pre-segmentation

22
Full image content based

• Use all of the available information throughout
  the registration process.
• Automatic methods presented

23
Paradigms reported

• Cross-correlation
• Fourier domain based ..
• Minimization of variance of grey values within
  segmentation
• Minimization of the histogram entropy of
  difference images

• Histogram clustering and minimization of
  histogram dispersion
• Maximization of mutual information
• Minimization of the absolute or squared intensity
  differences

24
Non-image based registration

• Calibrated coordinate system
• If the imaging coordinate systems of the two
  scanners involved are somehow calibrated to each
  other, which necessitates the scanners to be
  brought in to he same physical location
• Registering the position of surgical tools
  mounted on a robot arm to images

25
Nature of Transformation

• Rigid
• Affine
• Projective
• Curved

26
Domain of transformation

• Global
• Apply to entire image
• Local
• Subsections have their own

27
Rigid case equation

• Rigid or affine 3D transformation equation

28
Rotation matrix

• rotates the image around axis i by an angle

29
Transformation

• Many methods require a pre-registration
  (initialization) using a rigid or affine
  transformation
• Global rigid transformation is used most
  frequently in registration applications
• Application Human head

30
Interaction

• Interactive
• Semi-automatic
• Automatic
• Minimal interaction and speed, accuracy, or
  robustness

31
Interaction

• Extrinsic methods
• Automated
• Semi-automatic
• Intrinsic methods
• Semi-automatic
• Anatomical landmark
• Segmentation based
• Automated
• Geometrical landmark
• Voxel property based

32
Optimization procedure

• Parameters for registration transformation
• Parameters computed
• Parameters searched for

33
Optimization techniques

• Powells method
• Downhill simplex method
• Levenberg-Marquardt optimization
• Simulated annealing
• Genetic methods
• Quasi-exhaustive searching

34
Optimization techniques

• Frequent additions
• Multi-resolution and multi-scale approaches
• More than one techniques
• Fast coarse one followed by
• accurate slow one

35
Modalities involved

• Monomodal
• Multimodal
• Modality to model
• Patient to modality

36
Subject

• Intrasubject
• Intersubject
• Atlas

37
Object

• Different areas of the body

38
Related issues

• How to use the registration
• Registration visualization
• Registration segmentation
• Validation
• Validation of the registration
• Accuracy,