Measurement of brain structures based on statistical and geometrical 3D segmentation

  • Miguel ángel
  • González Ballester
  • Andrew Zisserman
  • Michael Brady
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1496)


In this paper we present a novel method for three-dimensional segmentation and measurement of volumetric data based on the combination of statistical and geometrical information. We represent the shape of complex three-dimensional structures, such as the cortex by combining a discrete 3D simplex mesh with the construction of a smooth surface using triangular Gregory-Bézier patches. A Gaussian model for the tissues present in the image is adopted, and a classification procedure which also estimates and corrects for the bias field present in the MRI is used. Confidence bounds are produced for all the measurements, thus obtaining bounds on the position of the surface segmenting the image. Performance is illustrated on multiple sclerosis phantom data and on real data.


Shape Descriptor Multiple Sclerosis Lesion Bias Field Volumetric Data Uniform Class 
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]
    Blake A., Curwen R., Zisserman A. A Framework for Spatiotemporal Control in the Tracking of Visual Contours. IJCV, 11(2):127–145, 1993.CrossRefGoogle Scholar
  2. [2]
    Brechbühler CH., Gerig G, Szekely G. Compensation of Spatial Inhomogeneity in MRI Based on a Parametric Bias Estimate. Lecture Notes in Computer Science 1131, Proc. VBC’96, Eds: Karl H. Hoehne and Ron Kikinis, pp. 141–146, 1996.Google Scholar
  3. [3]
    Cootes T.F., Hill A., Taylor C.J., Haslam J. The Use of Active Shape Models for Locating Structures in Medical Images. Image Vision and Computing, vol. 12, no. 6, jul. 94.Google Scholar
  4. [4]
    Colchester A.C.F., Gerig G., Crow T., Ayache N. and Vandermeulen D. Development and Validation of Techniques for Brain Morphometry (BIOMORPH). In Proc. CVRMED’97.Google Scholar
  5. [5]
    Crow T.J. Temporal Lobe Asymmetries as the Key Etiology of Schizophrenia. Schizophrenia Bulletin 16, pp. 433–443, 1990.CrossRefPubMedGoogle Scholar
  6. [6]
    Delingette H. Simplex Meshes: a General Representation for 3D Shape Reconstruction. INRIA research report no. 2214. March 1994.Google Scholar
  7. [7]
    DeLisi L.E., Tew W., Xie S., Hoff S.L., Sakuma M., Kushner M., Lee G., Shedlack K., Smith A.M., Grimson R. A Prospective Follow-up Study of Brain Morphology and Cognition in First-Episode Schizophrenic Patients: Preliminary Findings. Biol. Psychiatry 38, pp. 349–360, 1995.CrossRefPubMedGoogle Scholar
  8. [8]
    Gilles S., Brady M., Thirion J.P., Ayache N. Bias Field Correction and Segmentation of MR Images. Visualization in Biomedical Computing, Proceedings of VBC’96, vol. 1131 of Lecture Notes in Computer Science, pp. 153–158, Ed. Springer Verlag, 1996.Google Scholar
  9. [9]
    González Ballester M.A. Computer-Aided MRI-Based Analysis of Brain Morphology. DPhil transfer report, University of Oxford, July 1997.Google Scholar
  10. [10]
    González Ballester M.A., Zisserman A., Brady M. Combined Statistical and Geometrical 3D Segmentation and Measurement of Brain Structures. Proc. Workshop on Biomedical Image Analysis, Santa Barbara, Ca., 1998.Google Scholar
  11. [11]
    Guillemaud R., Brady M. Estimating the Bias Field of MR Images. IEEE Transactions on Medical Imaging, vol. 16, no. 3, pg. 238, 1997.CrossRefPubMedGoogle Scholar
  12. [12]
    Kass M., Witkin A., Terzopoulus D. Snakes: Active Contour Models. Proceedings of ICCV, pp. 259–268, 1987.Google Scholar
  13. [13]
    Marais P. In preparation.Google Scholar
  14. [14]
    Marais P., Guillemaud R., Sakuma M., Zisserman A., Brady M. Visualising Cerebral Asymetry. Lecture Notes in Computer Science 1131, Proc. VBC’96, Eds: Karl Heinz Hoehne and Ron Kikinis, pp. 411–416, 1996.Google Scholar
  15. [15]
    McInerney D., Terzopoulos T. A Finite Element Model for 3D Shape Reconstruction and Nonrigid Motion Tracking. In Proceedings of the Fourth Int. Conf. on Computer Vision (ICCV’93), pp. 518–523, 1993.Google Scholar
  16. [16]
    Röll S.A., Colchester A.C.F., Summers P.E., Griffin L.D. Intensity-Based Object Extraction from 3D Medical Images Including a Correction for Partial Volume Errors. Proceedings of BMVC, pp. 195–204, 1994.Google Scholar
  17. [17]
    Schmitt F., Chen X., Du W.H. Geometric Modelling From Range Image Data. Proceedings of Eurographics’91, pp. 317–328, Ed. Elsevier, 1991.Google Scholar
  18. [18]
    Székely G., Kelemen A., Brechbühler C., Gerig G. Segmentation of 2-D and 3-D Objects from MRI Volume Data Using Constrained Elastic Deformations of Flexible Fourier Contour and Surface Models. Medical Image Analysis, vol. 1, no. 1, pp. 19–34.Google Scholar
  19. [19]
    Van Leemput K., Vandermeulen D., Suetens P. Automatic Segmentation of Brain Tissues and MR Bias Correction Using a Digital Brain Atlas. Technical report, Kathoelieke Universiteit Leuven, Leuven, Belgium, Jan. 1998.Google Scholar
  20. [20]
    Wells III W.M., Grimson W.E.L., Kikinis R., Jolesz F.A. Actaptive Segmentation of MRI Data. IEEE Transactions on Medical Imaging, vol. 15, no. 4, pp. 429–442, 1996.CrossRefPubMedGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Miguel ángel
    • 1
  • González Ballester
    • 1
  • Andrew Zisserman
    • 1
  • Michael Brady
    • 1
  1. 1.Robotics Research Group, Dept. of Engineering ScienceUniversity of OxfordOxfordUK

Personalised recommendations