Image Computing Based on Bayesian Models (BM)

  • Zhong Xue
  • Stephen Wong
Part of the Lecture Notes in Computational Vision and Biomechanics book series (LNCVB, volume 14)


Many medical image computing tasks apply the prior knowledge about the variability of shapes or deformations to improve the performance of shape analysis, segmentation, registration, as well as group comparison or computer-aided diagnosis. Statistical model-based algorithms play important roles in capturing such prior information and applying them for robust image segmentation and registration. Given the prior distribution of a high-dimensional data, which can be a shape description, a deformation field, or other feature vectors from the training images, the objectiveis to come up with the best estimation of the shape, the deformation, or feature vectors from an observed data/image. The traditional maximum a posteriori (MAP) framework is the most commonly used methodology to incorporate the prior information in the estimation. One example of MAP estimation is the active shape model (ASM), which encodes the prior information of object shapes using principal component analysis (PCA) and then extracts the shape of an object from the PCA model that matches the image the best. Such statistical model-based method is constrained by the prior distribution from sample data for improved robustness. However, ASM takes directly the reconstructed object shape as the matching result, and it may not be able to match a new image accurately if the variations of the shape are not presented in the sample data, or if the number of model modes has been truncated too severely. This chapter introducesa new Bayesian model (BM) for accurate and robust medical image computing. BM overcomes the limitation of MAP by incorporating an intermediate variable and jointly estimating the result and the intermediate variable simultaneously. In this way the BM framework allows for convenient incorporation of additional constraints, reduces the constraints of the prior distributions, and increases the flexibility of shape matching. In this chapter, after a brief literature review of the statistical model-based image analysis methods, we first introduce the BM framework in both segmentation and registration and then present our two works that apply the BM methodology. From the techniques presented we can see that image segmentation and registration can be uniformly formulated in the same BM framework, and such formulation can also easily facilitate other image computing tasks.


Maximum a posteriori Bayesian model Segmentation Registration 



Active shape model


Bayesian model


Bayesian shape model


Gray matter


Maximum a posteriori


Magnetic resonance


Partial differential equation


Principal component analysis


Region of interest


Statistical models of deformations


Statistical parametric mapping


Support vector machine


Temporal smoothness


White matter


Wavelet packet transform


  1. 1.
    Jain AK, Zhong Y, Lakshmanan S (1996) Object matching using deformable templates. IEEE Trans Pattern AnalMachine Intell 18:267–278CrossRefGoogle Scholar
  2. 2.
    Kass M, Witkin A, Terzopoulos D (1987) Snakes - Active Contour Models. Int J Comput Vis 1:321–331CrossRefGoogle Scholar
  3. 3.
    Chan TF, Vese LA (2001) Active contours without edges. IEEE Trans Image Process 10:266–277CrossRefMATHGoogle Scholar
  4. 4.
    Kim J, Cetin M, Willsky AS (2007) Nonparametric shape priors for active contour-based image segmentation. Sign Process 87:3021–3044CrossRefMATHGoogle Scholar
  5. 5.
    Tsai A, Yezzi A, Wells W, Tempany C, Tucker D, Fan A et al (2003) A shape-based approach to the segmentation of medical imagery using level sets. IEEE Trans Med Imaging 22:137–154CrossRefGoogle Scholar
  6. 6.
    Lakshmanan S, Grimmer D (1996) A deformable template approach to detecting straight edges in radar images. IEEE Trans Pattern Anal Machine Intell 18:438–443CrossRefGoogle Scholar
  7. 7.
    McInerney T, Terzopoulos D (1996) Deformable models in medical image analysis: a survey. Med Image Anal 1:91–108CrossRefGoogle Scholar
  8. 8.
    Staib LH, Duncan JS (1992) Boundary finding with parametrically deformable models. IEEE Trans Pattern Anal Machine Intell 14:1061–1075CrossRefGoogle Scholar
  9. 9.
    Yuille AL, Hallinan PW, Cohen DS (1992) Feature-extraction from faces using deformable templates. Int J Comput Vis 8:99–111CrossRefGoogle Scholar
  10. 10.
    Lai KF, Chin RT (1995) Deformable contours-modeling and extraction. IEEE Trans Pattern Anal Machine Intell 17:1084–1090CrossRefGoogle Scholar
  11. 11.
    Cootes TF, Edwards GJ, Taylor CJ (2001) Active appearance models. IEEE Trans Pattern Anal Machine Intell 23:681–685CrossRefGoogle Scholar
  12. 12.
    Cootes TF, Taylor CJ, Cooper DH, Graham J (1995) Active shape models–their training and application. Comput Vis Image Underst 61:38–59CrossRefGoogle Scholar
  13. 13.
    Li H, Xue Z, Guo L, Wong ST (2009) Simultaneous consideration of spatial deformation and tensor orientation in diffusion tensor image registration using local fast marching patterns. Inf Process Med Imaging 21:63–75Google Scholar
  14. 14.
    Rueckert D, Sonoda LI, Hayes C, Hill DL, Leach MO, Hawkes DJ (1999) Nonrigid registration using free-form deformations: application to breast MR images. IEEE Trans Med Imaging 18:712–721CrossRefGoogle Scholar
  15. 15.
    Shen D, Davatzikos C (2002) HAMMER: hierarchical attribute matching mechanism for elastic registration. IEEE Trans Med Imaging 21:1421–39CrossRefGoogle Scholar
  16. 16.
    Toga AW, Thompson PM (2001) The role of image registration in brain mapping. Image Vis Comput 19:3–24CrossRefGoogle Scholar
  17. 17.
    Twining CJ, Cootes T, Marsland S, Petrovic V, Schestowitz R, Taylor CJ (2005) A unified information-theoretic approach to groupwise non-rigid registration and model building. Inf Process Med Imaging 19:1–14Google Scholar
  18. 18.
    Xue Z, Li H, Guo L, Wong ST (2010a) A local fast marching-based diffusion tensor image registration algorithm by simultaneously considering spatial deformation and tensor orientation. Neuroimage 52:119–130CrossRefGoogle Scholar
  19. 19.
    Xue Z, Shen D (2009) A new statistically-constrained deformable registration framework for MR brain images. Int J Med Eng Inform 1:357–367CrossRefGoogle Scholar
  20. 20.
    Xue Z, Shen D, Karacali B, Stern J, Rottenberg D, Davatzikos C (2006b) Simulating deformations of MR brain images for validation of atlas-based segmentation and registration algorithms. Neuroimage 33:855–66CrossRefGoogle Scholar
  21. 21.
    Xue Z, Wong K, Wong STC (2010b) Joint registration and segmentation of serial lung CT images for image-guided lung cancer diagnosis and therapy. Comput Medl Imaging Graph 34:55–60CrossRefGoogle Scholar
  22. 22.
    Yeo BT, Sabuncu M, Vercauteren T, Ayache N, Fischl B, Golland P (2008) Spherical demons: fast surface registration. In: Medical image computing and computer-assisted intervention MICCAI 2008, 11 May 2008 Vol. 11. pp 745–53Google Scholar
  23. 23.
    Xue Z, Shen D, Davatzikos C (2006a) Statistical representation of high-dimensional deformation fields with application to statistically constrained 3D warping. Med Image Anal 10:740–751CrossRefGoogle Scholar
  24. 24.
    Miller M, Banerjee A, Christensen G, Joshi S, Khaneja N, Grenander U et al (1997) Statistical methods in computational anatomy. Stat Methods Med Res 6:267–299CrossRefGoogle Scholar
  25. 25.
    Ashburner J, Friston KJ (2000) Voxel-based morphometry-the methods. Neuroimage 11:805–821CrossRefGoogle Scholar
  26. 26.
    Xue Z, Shen D, Karacali B, Davatzikos C (2005) Statistical representation and simulation of high-dimensional deformations: application to synthesizing brain deformations. Med Image Comput Comput Assist Interv 8:500–508Google Scholar
  27. 27.
    Xue Z, Li SZ, Teoh EK (2003) Bayesian shape model for facial feature extraction and recognition. Pattern Recogn 36:2819–2833CrossRefMATHGoogle Scholar
  28. 28.
    Heimann T, Meinzer HP (2009) Statistical shape models for 3D medical image segmentation: a review. Med Image Anal 13:543–563CrossRefGoogle Scholar
  29. 29.
    Chen T, Metaxas D (2003) Gibbs prior models, marching cubes, and deformable models: a hybrid framework for 3D medical image segmentation. In: Medical image computing and computer-Assisted intervention MICCAI 2003, vol 22879. pp 703–710Google Scholar
  30. 30.
    Chen T, Metaxas D (2000) Image segmentation based on the integration of Markov Random Fields and deformable models. In: Medical image computing and computer-assisted intervention MICCAI 2000, vol 1935. pp 256–265Google Scholar
  31. 31.
    Xue Z, Li SZ, Teoh EK (2002) Al-EigenSnake: an affine-invariant deformable contour model for object matching. Image Vis Comput 20:77–84CrossRefGoogle Scholar
  32. 32.
    Farzinfar M, Xue Z, Teoh EK (2008) Joint parametric and non-parametric curve evolution for medical image segmentation. In: European conference on computer vision ECCV 2008, Springer, pp 167–78Google Scholar
  33. 33.
    Farzinfar M, Xue Z, Teoh EK (2010) A novel approach for curve evolution in segmentation of medical images. Comput Med Imaging Graph 34:354–361CrossRefGoogle Scholar
  34. 34.
    Xue Z, Shen D (2007) Statistically-constrained deformable registration of MR brain images. In: 4th IEEE International Symposium on biomedical imaging from Nano to Macro, ISBI 2007, pp 25–8Google Scholar
  35. 35.
    Caselles V, Catte F, Coll T, Dibos F (1993) A geometric model for active contours in image-processing. Numer Math 66:1–31CrossRefMATHMathSciNetGoogle Scholar
  36. 36.
    Caselles V, Kimmel R, Sapiro G (1997) Geodesic active contours. Int J Comput Vis 22:61–79CrossRefMATHGoogle Scholar
  37. 37.
    Osher S, Sethian JA (1988) Fronts propagating with curvature-dependent speed: algorithms based on Hamilton–Jacobi formulations. J Comput Phys 79:12–49CrossRefMATHMathSciNetGoogle Scholar
  38. 38.
    Cohen LD, Cohen I (1993) Finite-element methods for active contour models and balloons for 2-D and 3-D images. IEEE Trans Pattern Anal Machine Intell 15:1131–1147CrossRefGoogle Scholar
  39. 39.
    Zhu SC, Yuille A (1996) Region competition: unifying snakes, region growing, and Bayes/MDL for multiband image segmentation. IEEE Trans Pattern Anal Machine Intell 18:884–900Google Scholar
  40. 40.
    Mumford D, Shah J (1988) Boundary detection by minimizing functionals. In: Image understanding, pp 19–43Google Scholar
  41. 41.
    Dal Maso G, Morel J-M, Solimini S (1992) A variational method in image segmentation: existence and approximation results. Acta Math 168:89–151CrossRefMATHMathSciNetGoogle Scholar
  42. 42.
    Samson C, Blanc-Feraud L, Aubert G, Zerubia J (2000) A variational model for image classification and restoration. IEEE Trans Pattern Anal Machine Intell 22:460–472CrossRefGoogle Scholar
  43. 43.
    Yezzi Jr A, Tsai A, Willsky A (1999) A statistical approach to snakes for bimodal and trimodal imagery. In: Proceedings of the Seventh IEEE international conference on computer vision, 1999, Vol 2. pp 898–903Google Scholar
  44. 44.
    Paragios N, Deriche R (2002) Geodesic active regions: a new framework to deal with frame partition problems in computer vision. J Vis Commun Image Represent 13:249–268CrossRefGoogle Scholar
  45. 45.
    Kim JM, Fisher JW, Yezzi A, Cetin M, Willsky AS (2005) A nonparametric statistical method for image segmentation using information theory and curve evolution. IEEE Trans Image Process 14:1486–1502CrossRefMathSciNetGoogle Scholar
  46. 46.
    Bresson X, Vandergheynst P, Thiran JP (2006) A variational model for object segmentation using boundary information and shape prior driven by the Mumford-Shah functional. Int J Comput Vis 68:145–162CrossRefGoogle Scholar
  47. 47.
    Chen YM, Tagare HD, Thiruvenkadam S, Huang F, Wilson D, Gopinath KS et al (2002) Using prior shapes in geometric active contours in a variational framework. Int J Comput Vis 50:315–328CrossRefMATHGoogle Scholar
  48. 48.
    Rousson M, Paragios N (2008) Prior knowledge, level set representations & visual grouping. Int J Comput Vis 76:231–243CrossRefGoogle Scholar
  49. 49.
    Leventon ME, Grimson WEL, Faugeras O (2000) Statistical shape influence in geodesic active contours. In: Proceedings of IEEE Conference on computer vision and pattern recognition, Hilton Head Island, 13–15 June 2000, Vol 1. pp 316–323Google Scholar
  50. 50.
    Charpiat G, Faugeras O, Keriven R (2005) Approximations of shape metrics and application to shape warping and empirical shape statistics. Found Comput Math 5:1–58CrossRefMATHMathSciNetGoogle Scholar
  51. 51.
    Cremers D, Kohlberger T, Schnorr C (2002) Nonlinear shape statistics in Mumford-Shah based segmentation. In: European conference on computer vision ECCV 2002, Pt 2, vol 2351. pp. 93–108Google Scholar
  52. 52.
    Cremers D, Osher SJ, Soatto S (2004) Kernel density estimation and intrinsic alignment for knowledge-driven segmentation: teaching level sets to walk. Pattern Recogn 3175:36–44Google Scholar
  53. 53.
    Rousson M, Paragios N, Deriche R (2004) Implicit active shape models for 3D segmentation in MR imaging. In: Proceedings of medical image computing and computer-assisted intervention MICCAI 2004, Pt 1, vol 3216. pp 209–216Google Scholar
  54. 54.
    Duncan JS, Ayache N (2000) Medical image analysis: progress over two decades and the challenges ahead. IEEE Trans Pattern Anal Machine Intell 22:85–106CrossRefGoogle Scholar
  55. 55.
    Davatzikos C, Tao X, Shen D (2003) Hierarchical active shape models, using the wavelet transform. IEEE Trans Med Imaging 22:414–423CrossRefGoogle Scholar
  56. 56.
    Davatzikos C, Genc A, Xu D, Resnick SM (2001) Voxel-based morphometry using the RAVENS maps: methods and validation using simulated longitudinal atrophy. Neuroimage 14:1361–1369CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  1. 1.Houston Methodist Research InstituteHouston Methodist HospitalHoustonUSA
  2. 2.Weill Cornell Medical CollegeNew YorkUSA

Personalised recommendations