Segmentation-Assisted Registration for Brain MR Images

  • Jundong Liu


Tracking brain morphological changes in magnetic resonance images (MRIs) requires high accurate segmentation or registration of brain structures. In this chapter, we propose a robust solution for this problem, based on a unified variation framework where prior segmentation information can be seamlessly integrated into a nonrigid registration procedure. Under this framework, in addition to the force arising from the similarity minimization in seeking for detailed correspondence, atlas contours provide an extra guidance to assist the alignment procedure in achieving a more meaningful, stable, and noise-tolerant result. Sum of local correlation (LC) is used as the underlying similarity metric. Our approach can very well handle intensity scaling, contrast reversal, as well as image noise. Experimental results on 2D/3D synthetic and real data demonstrate the improvement made by our algorithm.


Local Correlation Nonrigid Registration Normal Pressure Hydrocephalus Fixed Image Intensity Scaling 
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.


  1. 1.
    Simulated brain database [Online].
  2. 2.
    Alfano B, Quarantelli M, Brunnetti A et al (1998) Reproducibility of intracranial volume measurement by unsupervised multispectral brain segmentation. Magn Reson Med 39:497–499PubMedCrossRefGoogle Scholar
  3. 3.
    Bajscy R, Kovacic S (1989) Multiresolution elastic matching. Comput Vis Graph Image Process 46(1):1–21CrossRefGoogle Scholar
  4. 4.
    Barron JL, Fleet DJ, Beauchemin SS (1994) Performance of optical flow techniques. Int J Comput Vis 1(12):43–77CrossRefGoogle Scholar
  5. 5.
    Cachier P, Pennec X (2000) Non-rigid registration by gradient descent on a Gaussian-windowed similarity measure using convolutions. In: Proceedings of the IEEE workshop on mathematical methods in biomedical image analysis, p 182Google Scholar
  6. 6.
    Chan T, Vese L An active contour model without edges. IEEE Trans Image Process 10(2):266–277Google Scholar
  7. 7.
    Chen M, Kanade T, Rowley H, Pomerleau D (1998) Anomaly detection through registration. In: IEEE CVPR, pp 304–310Google Scholar
  8. 8.
    Christensen GE, Miller MI, Vannier M (1996) Individualizing neuroanatomical atlases using a massively parallel computer. IEEE Comput 1(29):32–38Google Scholar
  9. 9.
    Collignon A, Maes F, Delaere D, Vandermeulen D, Suetens P, Marchal G (1995) Automated multimodality image registration using information theory. In: Proceedings of IPMI, pp 263–274Google Scholar
  10. 10.
    Davatzikos C, Prince JL (1994) Brain image registration based on curve mapping. In: IEEE WBIA, Seattle, WA, pp 245–254Google Scholar
  11. 11.
    Evans AC (1991) Warping of computerized 3D atlas to match brain image volumes for quantitative neuroanatomical and functional analysis. In: Proceedings of SPIE Medical Imaging V, vol 1445:236–246Google Scholar
  12. 12.
    Lai SH, Vemuri BC (1995) Robust and efficient computation of optical flow. In: IEEE Symposium on CVS, Miami, FL, pp 455–460Google Scholar
  13. 13.
    Lavallee S, Szeliski R, Brunie L (1991) Matching 3D smooth surfaces with their 2D projections using 3D distance maps. In: Proceedings of SPIE, vol 1570, pp 322–336CrossRefGoogle Scholar
  14. 14.
    Leventon M, Grimson WEL (1999) Multi-modal volume registration using joint intensity distributions. In: MICCAI 1999Google Scholar
  15. 15.
    Maintz JB, Viergever MA (1998) A survey of medical image registration. In: MedIA, vol 2, pp 1–36Google Scholar
  16. 16.
    Maintz JBA, van den Elsen PA, Viergever MA (1996) Comparison of edge-based and ridge-based registration of CT and MR brain images. Med Image Anal 1(2):151–161PubMedCrossRefGoogle Scholar
  17. 17.
    Meyer C et al (1997) Demonstration of accuracy and clinical versatitlity of mutual information for automatic multimodality image fusion using affine and thin-plate spline-warped geometric deformation. Med Image Anal 1:195–206PubMedCrossRefGoogle Scholar
  18. 18.
    Netsch T et al (2001) Towards real-time multi-modality 3D medical image registration. In: ICCV 2001, pp 718–725Google Scholar
  19. 19.
    Pelizarri CA, Chen GTY, Spelbring DR (1989) Accurate three-dimensional registration of CT, PET and MR images of the brain. J Comput Assist Tomogr 13(1):20–26CrossRefGoogle Scholar
  20. 20.
    Pluim JP, Maintz JB, Viergever MA (2000) Image registration by maximization of combined mutual information and gradient information. IEEE Trans Med Imag 19(8):809–814CrossRefGoogle Scholar
  21. 21.
    Roche A, Malandain G, Pennec X, Ayache N (1998) Multimodal image registration by maximization of the correlation ratio. Research Report RR-3378, INRIA, August 1998Google Scholar
  22. 22.
    Rueckert D, Sonoda LI, Hayes C, Hill DLG, Leach MO, Hawkes DJ (1999) Non-rigid registration using free-form deformations: application to breast MR images. IEEE Trans Med Imag 18(8):712–721CrossRefGoogle Scholar
  23. 23.
    Russakoff DB, Tomasi C, Rohlfing T, Maurer CR Jr (2004) Image similarity using mutual information of regions. In: ECCV 2004, LNCS 3023, pp 596–607Google Scholar
  24. 24.
    Studholme C, Hill D, Hawkes D (1999) An overlap invariant entropy measure of 3D medical image alignment. Pattern Recogn 32:71–86CrossRefGoogle Scholar
  25. 25.
    Sussman M, Smereka P, Osher S (1994) A level set approach for computing solutions to incompressible two-phase flow. J Comput Phys 114:146–159CrossRefGoogle Scholar
  26. 26.
    Thirion JP (1998) Image matching as a diffusion process: an analogy with Maxwell’s demons. Med Image Anal 2(3):243–260PubMedCrossRefGoogle Scholar
  27. 27.
    Tsai A, Yezzi AJ, Willsky A (2000) A curve evolution approach to smoothing and segmentation using the Mumford-Shah functional. In: CVPR 2000, pp 1119–1124Google Scholar
  28. 28.
    Udupa JK, Samarasekera S (1996) Fuzzy connectdedness and object definition: theory, algorithms and applications in image segmentation. Graph Models Image Process 58:246–261CrossRefGoogle Scholar
  29. 29.
    Unal G, Slaaugh G (2005) Coupled PDEs for non-rigid registration and segmentation. In: CVPR 2005, San Diego, CAGoogle Scholar
  30. 30.
    Unal G, Slabaugh G, Yezzi A, Tyan J (2004) Joint segmentation and non-rigid registration without shape priors. Siemens Technical Report SCR-04-TR-7495Google Scholar
  31. 31.
    Vemuri BC, Huang S et al. (1998) An efficient motion estimator with application to medical imaging. Med Image Anal 2(1):79–98PubMedCrossRefGoogle Scholar
  32. 32.
    Vemuri B, Chen Y, Wang Z (2002) Registration assisted image smoothing and segmentation. In: ECCV, vol 4, pp 546–559Google Scholar
  33. 33.
    Vemuri B, Ye J, Chen Y, Leonard C (2003) Image registration via level-set motion: applications to atlas-based segmentation. Med Image Anal 7(1):1–20PubMedCrossRefGoogle Scholar
  34. 34.
    Viola PA, Wells WM (1995) Alignment by maximization of mutual information. In: Fifth ICCV, MIT, Cambridge, MA, pp 16–23Google Scholar
  35. 35.
    Wang Y, Staib LH (2000) Physical model-based non-rigid registration incorporating statistical shape information. Med Image Anal 4(1):7–20PubMedCrossRefGoogle Scholar
  36. 36.
    Weese J, Rosch P, Netsch T, Blaffert T, Quist M (1999) Gray-value based registration of CT and MR images by maximization of local correlation. In: MICCAI 99, pp 656–663Google Scholar
  37. 37.
    Wells WM III, Viola P, Atsumi H (1997) Multi-modal volume registration by maximization of mutual information. Med Image Anal 1(1):35–51CrossRefGoogle Scholar
  38. 38.
    Wyatt PP, Noble JA (2003) MAP MRF joint segmentation and registration of medical images. Med Image Anal 7:539–552PubMedCrossRefGoogle Scholar
  39. 39.
    Yezzi A, Zollei L, Kapur T (2003) A variational framework for joint segmentation and registration. Med Image Anal 7:171–185PubMedCrossRefGoogle Scholar
  40. 40.
    Zhang T, Freedman D (2003) Tracking objects using density matching and shape priors. In: ICCV 2003, vol 2, pp 1056–1062Google Scholar
  41. 41.
    Zhang Y, Brady M, Smith S (2001) Segmentation of brain MR image through a hidden Markov random field model and the expectation-maximization algorithm. IEEE Trans Med Imaging 20:45–57PubMedCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  1. 1.School of Electrical Engineering and Computer ScienceOhio UniversityAthensUSA

Personalised recommendations