1 / 26

Image Registration Using Mutual Information

Image Registration Using Mutual Information. Gen-Jia Jaguar Li Advisor: Shu-Yen Wan. Problem description. Flowchart of image registration. A problem of optimization. Objective function Transformation Interpolation Similarity measure (e.g. mutual information). Optimization

hilda-horne
Download Presentation

Image Registration Using Mutual Information

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Image Registration Using Mutual Information Gen-Jia Jaguar Li Advisor: Shu-Yen Wan

  2. Problem description

  3. Flowchart of image registration A problem of optimization • Objective function • Transformation • Interpolation • Similarity measure (e.g. mutual information) • Optimization • Degree of freedom • optimization strategies

  4. Give an example in Avizo

  5. Papers Review • Mutual-Information-Based Registration of Medical Images: A Survey [Pluim JP,Maintz JB,Viergever MA. IEEE Trans Med Imaging.2003 Aug;22(8):986-1004] • Nonrigid Image Registration Using Conditional Mutual Information.[Loeckx D,Slagmolen P,Maes F,Vandermeulen D,Suetens P. IEEE Trans Med Imaging.2009 May 12.]

  6. Mutual-Information-Based Registration of Medical Images: A Survey Pluim JP,Maintz JB,Viergever MAIEEE Trans Med Imaging.2003 Aug;22(8):986-1004

  7. Introduction • A new idea in approximately 1994 (Collignon and colleagues and Viola and Wells) • Outline • Definition of entropy and its interpretation • Mutual information • Survey of literature

  8. Entropy • Measure of information (entropy) • Hartley 1928 • Shannon entropy 1948

  9. EntropyInterpretations • Amount of information an event gives when it takes place • Uncertainty about the outcome of an event • Dispersion of the probabilities with which the events take place

  10. Image Regisration • Woods et al. 1990 (first introduced) regions of similar tissue in one image would correspond to regions in the other image • Hill et al. 1993 (an adaption of Woods) regions are defined in feature space

  11. Feature space (or joint histogram) Fig. 1. Example of a feature space for (a) a CT image and (b) an MR image. (c) Along the axes of the feature space, the gray values of the two images are plotted: from left to right for CT and from top to bottom for MR. The feature space is constructed by counting the number of times a combination of gray values occurs. For each pair of corresponding points (x; y), with x a point in the CT image and y a point in the MR image, the entry (I (x); I (y)) in the feature space on the right is increased. A distinguishable cluster in the feature space is the stretched vertical cluster, which is the rather homogeneous area of brain in the CT image corresponding to a range of gray values for the MR image.

  12. Feature space (or joint histogram) Fig. 2. Joint gray value histograms of anMRimage with itself. (a) Histogram shows the situation when the images are registered. Because the images are identical, all gray value correspondences lie on the diagonal. (b), (c), and (d) show the resulting histograms when one MR image is rotated with respect to the other by angles of 2, 5, and 10, respectively. The corresponding joint entropy values are (a) 3.82; (b) 6.79; (c) 6.98; and (d) 7.15..

  13. Image Registrationmeasures of dispersion • Hill et al. 1994 (skewness of distribution) Third-order moment of the joint histogram • Collignon et al and Studholme et al. 1995 (Shannon entropy for joint distribution) Minimizes their joint entropy

  14. Mutual Information • Collignon et al 1995-1998 & Viola and Wells 1995 applied to rigid registration of multi-modality image and with a few years it become the most investigated measure for medical image registration

  15. Mutual InformationDefinition The best explains the term “mutual information” The most closely related to joint entropy Related to Kullback-Leibler distance summation of p(i)log(p(i)/q(i))

  16. Mutual InformationProperties • I(A,B) = I(B,A) • I(A,A) = H(A) • I(A,B) <= H(A), I(A,B) <= H(B) • I(A,B) >= 0 • I(A,B) = 0

  17. MethodPreprocessing • Region or structures define • Low-pass filtering, e.g. ultrasound image • Thresholding or filtering to remove noise • Resample

  18. MethodMeasure (Mutual Information) • Entropy • Shannon entropy • Jumarie entropy or Renyi entropy • Normalization • NMI, Studholme et al. 1997, 1999 • ECC, Collignon 1998 and Maes 1997 • Spatial information • MI ignored the neighboring voxels

  19. MethodTransformation • Degree of freedom • Rigid (translation and rotation) • Affine (scaling and shear) • Curved (mapping of straight lines to curves)

  20. MethodImplementation • Interpolation • Probability distribution estimation • Optimization • Acceleration

  21. MethodImage Dimensionality • Majority of researches treat registraion of 3D image • 2-D / 2-D, less reliable estimation of the probability distributions • 2-D / 3-D, find the correspondence between the operative scene and a preoperative image

  22. MethodNumber of Images Fig5. Different definitions of the mutual information (shaded areas) of three images (a)–(c). The dark gray color in (c) signifies that the area is counted twice. The circles denote the entropy of an image; joint entropy is the union of circles.

  23. Discussion • The underlying process is difficult to envisage • It can be used without need for preprocessing, user initialization or parameter tuning • May not be a universal cure: thin structures (e.g. retinal images) or MR and ultrasound images

  24. What We Know • NMI with respect to image overlap is a useful adaptation • Curved registration based on MI is viable, but still challenge. • Interpolation method influences both accuracy and smoothness of measure

  25. In the Future • Curved registration is still challenge • Ultrasound, the most challenging • Gray values of neighboring voxels are uncorrelated

  26. Nonrigid Image Registration Using Conditional Mutual Information.Loeckx D,Slagmolen P,Maes F,Vandermeulen D,Suetens PIEEE Trans Med Imaging.2009 May 12.[Epub ahead of print]

More Related