Advertisement

Physically And Statistically Based Deformable Models For Medical Image Analysis

  • Ghassan Hamarneh
  • Chris McIntosh
Part of the Topics in Biomedical Engineering. International Book Series book series (ITBE)

Medical imaging continues to permeate the practice of medicine, but automated yet accurate segmentation and labeling of anatomical structures continues to be a major obstacle to computerized medical image analysis. Deformable models, with their roots in estimation theory, optimization, and physics-based dynamical systems, represent a powerful approach to the general problem of medical image segmentation. This chapter presents an introduction to deformable models, beginning with the classical Active Contour Models (ACMs), or snakes, and focusing on explicit, physics-based methods. Snakes are useful for segmenting amorphous shapes when little or no prior knowledge about shape and motion is available. Many extensions of snakes incorporate such additional knowledge. An example presented in this chapter is the use of optical flow forces to incorporate knowledge of shape dynamics and guide the snake deformations to track the leading edge of an injected contrast agent in an echocardiographic image sequence. Active Shape Models (ASMs), or smart snakes, is a powerful method for incorporating statistical models of shape variability in the segmentation process. ASMs and ACMs offer different advantages, and, as such, a method combining both is presented. Statistical knowledge about shape dynamics is useful for segmenting and tracking objects with distinctive motion patterns (such as a beating heart). An extension of the ASM to model knowledge of spatiotemporal constraints is presented.

Keywords

Discrete Cosine Transform IEEE Computer Society Shape Variation Deformable Model Active Contour Model 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Terzopoulos D. 1987. On matching deformable models to images. Technical Report 60, Schlum-berger Palo Alto Research, 1986. Reprinted in Topical Meeting on MachineVision, Technical Digest Series, Vol. 12, pp. 160-167.Google Scholar
  2. 2.
    Kass M, Witkin A, Terzopoulos D. 1987. Snakes: active contour models. Int J Comput Vision 1(4):321-331.CrossRefGoogle Scholar
  3. 3.
    Widrow B. 1973. The rubber mask technique, part I. Pattern Recognit 5(3):175-211.CrossRefGoogle Scholar
  4. 4.
    Fischler M, Elschlager R. 1973. The representation and matching of pictorial structures. IEEE Trans Comput 22(1):67-92.CrossRefGoogle Scholar
  5. 5.
    Blake A, Isard M. 2000. Active contours. Berlin: Springer.Google Scholar
  6. 6.
    Elsgolc LE. 1962. Calculus of variations. Reading, MA: Addison-Wesley.Google Scholar
  7. 7.
    McInerney T, Terzopoulos D. 1996. Deformable models in medical image analysis: a survey. Med Image Anal 1(2):91-108.CrossRefGoogle Scholar
  8. 8.
    Sonka M, Hlavac V, Boyle R. 1998. Image processing, analysis, and machine vision, 2nd ed. Pacific Grove, CA: Brooks/Cole.Google Scholar
  9. 9.
    Cohen LD, Cohen. 1993. Finite-element methods for active contour models and balloons for 2D and 3D images. IEEE Trans Pattern Anal Machine Intell 15:1131-1147.Google Scholar
  10. 10.
    Leroy B, Herlin I, Cohen LD. 1996. Multi-resolution algorithms for active contour models. In Proceedings of the 12th international conference on analysis and optimization of systems, pp. 58-65. Washington, DC: IEEE Computer Society.Google Scholar
  11. 11.
    McInerney T, Terzopoulos D. 2000. T-snakes: topology adaptive snakes. Med Image Anal 4(2):73-91.CrossRefGoogle Scholar
  12. 12.
    Ivins J, Porrill J. 1994. Statistical snakes: active region models. In Proceedings of the 5th British machine vision conference (BMVC’94), pp. 377-386. Surrey, UK: BMVA Press.Google Scholar
  13. 13.
    Xu C, Prince JL. 1998. Snakes, shapes, and gradient vector flow. IEEE Trans Image Process 7(3):359-369.MATHCrossRefMathSciNetGoogle Scholar
  14. 14.
    Sapiro G. 1997. Color snakes. Comput Vision Image Understand 68(2):247-253.CrossRefMathSciNetGoogle Scholar
  15. 15.
    Delingette H. 1999. General object reconstruction based on simplex meshes. Int J Comput Vision 32(2):111-146.CrossRefGoogle Scholar
  16. 16.
    McInerney T, Terzopoulos D. 1995. A dynamic finite-element surface model for segmentation and tracking in multidimensional medical images with application to cardiac 4D image analysis. Comput Med Imaging Graphics 19(1):69-83.CrossRefGoogle Scholar
  17. 17.
    Hamarneh G, Althoff K, Gustavsson T. 2000. Snake deformations based on optical flow forces for contrast agent tracking in echocardiography. In Proceedings of the Swedish Sympo-sium on image analysis, pp. 45-48. Available online at http://db.s2.chalmers.se/download/ publications/hamarneh 824.pdf.
  18. 18.
    Althoff K, Hamarneh G, Gustavsson T. 2000. Tracking contrast in echocardiography by a com-bined snake and optical flow technique. IEEE Proc Comput Cardiol 27:29-32.Google Scholar
  19. 19.
    McKenna WJ, Thiene G, Nava A, Fontaliran F, Blomström-Lundqvist C, Fontaine G, Camerini F. 1994. Diagnosis of arrhythmogenic right ventricular dysplasia/cardiomyopathy. Br Heart J 71 215-218.CrossRefGoogle Scholar
  20. 20.
    Mikic I, Krucinski S, Thomas JD. 1998. Segmentation and tracking in echocardiographic se- quences: active contours guided by optical flow estimates. IEEE Trans Med Imaging 17(2):274-284.CrossRefGoogle Scholar
  21. 21.
    Peterfreund N. 1999. Robust tracking of position and velocity with Kalman snakes. IEEE Trans Pattern Anal Machine Intell 21(6):564-569.CrossRefGoogle Scholar
  22. 22.
    Akgul YS, Kambhamettu C, Stone M. 1998. Extraction and tracking of the tongue surface from ultrasound image sequences. Proceedings of the IEEE computer society conference on computer vision and pattern recognition (CVPR 1991), pp. 298-303. Washington, DC: IEEE Computer Society.Google Scholar
  23. 23.
    Horn B, Schunk B. 1981. Determining optical flow. Artif Intell 17 185-204.CrossRefGoogle Scholar
  24. 24.
    Perona P, Malik J. 1990. Scale-space and edge detection using anisotropic diffusion. IEEE Trans Pattern Anal Machine Intell 12:629-639.CrossRefGoogle Scholar
  25. 25.
    Cootes T, Taylor C, Hill A, Halsam J. 1993. The use of active shape models for locating structures in medical images. In Proceedings of the 13th international conference on information processing in medical imaging, pp. 33-47. Ed HH Barrett, AF Gmitro. Berlin: Springer.CrossRefGoogle Scholar
  26. 26.
    Hill A, Taylor C. 1994. Automatic landmark generation for point distribution models. In Proceed-ings of the 5th British machine vision conference (BMVC’94), pp. 429-438. Surrey, UK: BMVA Press.Google Scholar
  27. 27.
    Cootes T, Taylor C, Lanitis A. 1994. Active shape models: evaluation of a multi-resolution method for improving image search. In Proceedings of the 5th British machine vision conference (BMVC’94), pp. 327-336. Surrey, UK: BMVA Press.Google Scholar
  28. 28.
    Cootes T, Edwards G, Taylor C. 1998. Active appearance models. In Proceedings of the fifth European conference on computer vision (ECCV 1998), Volume 2. Lecture notes in computer science, Vol. 1407, pp. 484-498. Ed H Burkhardt, B Neumann. Berlin: Springer.Google Scholar
  29. 29.
    Sclaroff S, Isidoro J. 1998. Active blobs. In Proceedings of the sixth international conference on computer vision (ICCV), pp. 1146-1153. Washington, DC: IEEE Computer Society.Google Scholar
  30. 30.
    Hill A, Thornham A, Taylor C. 1993. Model-based interpretation of 3d medical images. In Pro-ceedings of the fourth British machine vision conference (BMVC’93), pp. 339-348. Surrey, UK: BMVA Press.Google Scholar
  31. 31.
    Lanitis A, Taylor A, Cootes T. 1994. Automatic tracking, coding and reconstruction of human faces using flexible appearance models. Electron Lett 30(19):1578-1579.CrossRefGoogle Scholar
  32. 32.
    Baumberg A, Hogg D. 1994. An efficient method for contour tracking using active shape models. In Proceedings of the 1994 IEEE workshop on motion of non-rigid and articulated objects, pp.194-199. Washington, DC: IEEE Computer Society.CrossRefGoogle Scholar
  33. 33.
    Cootes T, Taylor C. 1995. Combining point distribution models with shape models based on finite element analysis. Image Vision Comput 13(5):403-409.CrossRefGoogle Scholar
  34. 34.
    Lanitis A, Taylor C, Cootes T. 1994. Recognising human faces using shape and grey-level informa-tion. In Proceedings of the third international conference on automation, robotics and computer vision, pp. 1153-1157. Washington, DC: IEEE Computer Society.Google Scholar
  35. 35.
    Bookstein F. 1989. Principal warps: thin-plate splines and the decomposition of deformations. IEEE Trans Pattern Anal Machine Intell 11(6):567-585.MATHCrossRefGoogle Scholar
  36. 36.
    Hunter IA, Soraghan JJ, Christie J, Durrani JS. 1993. Detection of echocardiographic left ventricle boundaries using neural networks. IEEE Proc Comput Cardiol 20:201-204.Google Scholar
  37. 37.
    Parker A, Hill A, Taylor C, Cootes T, Jin X, Gibson D. 1994. Application of point distribution models to the automated analysis of echocardiograms. IEEE Proc Comput Cardiol 21:25-28.Google Scholar
  38. 38.
    Taine M, Herment A, Diebold B, Peronneau P. 1994. Segmentation of cardiac and vascular ultrasound images with extension to border kinetics. Proceedings of the 8th IEEE symposium on ultrasonics, Vol. 3, pp. 1773-1776. Washington, DC: IEEE Computer Society.Google Scholar
  39. 39.
    Papadopoulos I, Strintzis MG. 1995. Bayesian contour estimation of the left ventricle in ultrasound images of the heart. Proceedings of the IEEE conference on engineering in medicine and biology, Vol. 1, pp. 591-592. Washington, DC: IEEE Computer Society.Google Scholar
  40. 40.
    Malassiotis S, Strintzis MG. 1999. Tracking the left ventricle in echocardiographic images by learning heart dynamics. IEEE Trans Med Imaging 18(3):282-290.CrossRefGoogle Scholar
  41. 41.
    Amini A, Weymouth T, Jain R. 1990. Using dynamic programming for solving variational prob-lems in vision. IEEE Trans Pattern Anal Machine Intell 12(9):855-867.CrossRefGoogle Scholar
  42. 42.
    Cohen L. 1991. On active contour models and balloons. Comput Vision Graphics Image Process: Image Understand 53(2):211-218.MATHGoogle Scholar
  43. 43.
    Grzeszczuk R, Levin D. 1997. Brownian strings: segmenting images with stochastically de-formable contours. IEEE Trans Pattern Anal Machine Intell 19(10):1100-1114.CrossRefGoogle Scholar
  44. 44.
    Herlin I, Nguyen C, Graffigne C. 1992. A deformable region model using stochastic processes applied to echocardiographic images. In Proceedings of the IEEE computer society conference on computer vision and pattern recognition (CVPR 1992), pp. 534-539. Washington, DC: IEEE Computer Society.CrossRefGoogle Scholar
  45. 45.
    Lobregt S, Viergever M. 1995. A discrete dynamic contour model. IEEE Trans Med Imaging 14(1):12-24.CrossRefGoogle Scholar
  46. 46.
    Cootes T, Taylor C, Cooper D, Graham J. 1995. Active shape models: their training and applica- tion. Comput Vision Image Understand 61(1):38-59.CrossRefGoogle Scholar
  47. 47.
    Staib L, Duncan J. 1992. Boundary finding with parametrically deformable models. IEEE Trans Pattern Anal Machine Intell 14(11):1061-1075.CrossRefGoogle Scholar
  48. 48.
    Leymarie F, Levine M. 1993. Tracking deformable objects in the plane using an active contour model. IEEE Trans Pattern Anal Machine Intell 15(6):617-634.CrossRefGoogle Scholar
  49. 49.
    Niessen W, Duncan J, Viergever M, Romeny B. 1995. Spatiotemporal analysis of left-ventricular motion. Proc SPIE 2434:250-261.CrossRefGoogle Scholar
  50. 50.
    Signh A, Von Kurowski L, Chiu M. 1993. Cardiac MR image segmentation using deformable models. In SPIE proceedings on biomedical image processing and biomedical visualization, Vol. 1905, pp. 8-28. Bellingham, WA: SPIE.Google Scholar
  51. 51.
    Stark K, Fuchs S. 1996. A method for tracking the pose of known 3D objects based on an active contour model. Proceedings of the international conference on pattern recognition (ICPR’96), pp. 905-909. Washington, DC: IEEE Computer Society.CrossRefGoogle Scholar
  52. 52.
    Terzopoulos D, Szeliski R. 1992. Tracking with Kalman snakes. In Active vision, pp. 3-20. Ed A Blake, A Yuille. Cambridge: MIT Press.Google Scholar
  53. 53.
    Lelieveldt B, Mitchell S, Bosch J, van der Geest R, Sonka M, Reiber J. 2001. Time-continuous segmentation of cardiac image sequences using active appearance motion models. Proceedings of the 17th international conference on information processing in medical imaging (ICIPMI’01). Lecture Notes in computer science, Vol. 2082, pp. 446-452. Berlin: Springer.Google Scholar
  54. 54.
    Black M, Yacoob Y. 1997. Recognizing facial expressions in image sequences using local parametrized models of image motion. Int J Comput Vision 25(1):23-48.CrossRefGoogle Scholar
  55. 55.
    Bonciu C, L éger C, Thiel J. 1998. A Fourier-Shannon approach to closed contour modeling. Bioimaging 6:111-125.CrossRefGoogle Scholar
  56. 56.
    Cootes T, Taylor C. 1997. A mixture model for representing shape variation. In Proceedings of the eighth British machine vision conference (BMVC’97), pp. 110-119. Surrey, UK: BMVA Press.Google Scholar
  57. 57.
    Hill A, Taylor CJ. 1992. Model-based image interpretation using genetic algorithms. Image Vision Comput 10(5):295-300.CrossRefGoogle Scholar
  58. 58.
    Metaxas D, Terzopoulos D. 1991. Constrained deformable superquadrics and nonrigid motion tracking. In Proceedings of the IEEE computer society conference on computer vision and pattern recognition (CVPR 1991), pp. 337-343. Washington, DC: IEEE Computer Society.CrossRefGoogle Scholar
  59. 59.
    Singh A, Goldgof D, Terzopoulos D. 1998. Deformable models in medical image analysis. Wash-ington, DC: IEEE Computer Society.Google Scholar
  60. 60.
    Sz ékely G, Kelemen A, Brechb ühler C, Gerig G. 1996. Segmentation of 3D objects from MRI volume data using constrained elastic deformations of flexible Fourier surface models. Med Image Anal 1(1):19-34.Google Scholar
  61. 61.
    Hamarneh G, Chodorowski A, Gustavsson T. 2000. Active contour models: application to oral lesion detection in color images. Proceedings of the IEEE international conference on systems, man, and cybernetics, Vol. 4, pp. 2458-2463. Washington, DC: IEEE Computer Society.Google Scholar
  62. 62.
    Hamarneh G, Gustavsson T. 2000. Statistically constrained snake deformations. In Proceedings of the IEEE international conference on systems, man, and cybernetics, Vol. 3, pp. 1610-1615. Washington, DC: IEEE Computer Society.Google Scholar
  63. 63.
    Hamarneh G, Gustavsson T. 2004. Deformable spatiotemporal shape models: extending ASM to 2D + time. J Image Vision Comput 22(6):461-470.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2007

Authors and Affiliations

  • Ghassan Hamarneh
    • 1
  • Chris McIntosh
    • 1
  1. 1.School of Computing ScienceSimon Fraser UniversityBurnabyCanada

Personalised recommendations