Atlas-Based Segmentation of Pathological Brains Using a Model of Tumor Growth

  • M. Bach Cuadra
  • J. Gomez
  • P. Hagmann
  • C. Pollo
  • J.-G. Villemure
  • B. M. Dawant
  • J.-Ph. Thiran
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2488)

Abstract

We propose a method for brain atlas deformation in presence of large space-occupying tumors or lesions, based on an a priori model of lesion growth that assumes radial expansion of the lesion from its central point. Atlas-based methods have been of limited use for segmenting brains that have been drastically altered by the presence of large space-occupying lesions. Our approach involves four steps. First, an affine registration brings the atlas and the patient into global correspondence. Secondly, a local registration warps the atlas onto the patient volume. Then, the seeding of a synthetic tumor into the brain atlas provides a template for the lesion. The last step is the deformation of the seeded atlas, combining a method derived from optical flow principles and a model of lesion growth. Results show that a good registration is performed and that method can be applied to automatic segmentation of structures and substructures in brains with gross deformation, with important medical applications in neurosurgery, radiosurgery and radiotherapy.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Dawant, B.M., Hartmann, S.L., Gadamsetty, S.: Brain Atlas Deformation in the Presence of Large Space-occupying Tumors. In: MICCAI. (1999) 589–596Google Scholar
  2. 2.
    Kikinis, R., et al.: A digital brain atlas for surgical planning, model driven segmentation and teaching. IEEE Transactions on Visualization and Computer Graphics 2 (1996) http://splweb.bwh.harvard.edu:8000.
  3. 3.
    Thirion, J.P.: Image matching as a diffusion process: an analogy with Maxwell’s demons. Medical Image Analysis 2 (1998) 243–260CrossRefGoogle Scholar
  4. 4.
    Bach, M., et al: Atlas-based Segmentation of Pathological Brains using a Model of Tumor Growth. Technical report, ITS-EPFL (2002) http://ltswww.epflch/~brain/publications/meri/techreports/report.ps.gz.
  5. 5.
    Cuisenaire, O., Thiran, J.P., Macq, B., Michel, C., Volder, A.D., Marques, F.: Automatic Registration of 3D MR images with a Computerized Brain Atlas. In: SPIE Medical Imaging. Volume 1719. (1996) 438–449Google Scholar
  6. 6.
    Thirion, J.P.: Fast Non-Rigid Matching of 3D Medical Images. Technical Report 2547, INRIA (1995)Google Scholar
  7. 7.
    Bach, M., Cuisenaire, O., Meuli, R., Thiran, J.P.: Automatic segmentation of internal structures of the brain in MRI using a tandem of affine and non-rigid registration of an anatomical atlas. In: ICIP. (2001)Google Scholar
  8. 8.
    Warfield, S.K., Kaus, M., Jolesz, F.A., Kikinis, R.: Adaptive, Template Moderated, Spatially Varying Statistical Classification. Medical Image Analysis 4 (2000) 43–55CrossRefGoogle Scholar
  9. 9.
    Kyriacou, S., Davatzikos, C.: Nonlinear elastic registration of brain images with tumor pathology using a biomechanical model. IEEE Trans. Med. Imaging 18 (1999) 580–592CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • M. Bach Cuadra
    • 1
  • J. Gomez
    • 1
  • P. Hagmann
    • 1
  • C. Pollo
    • 2
  • J.-G. Villemure
    • 2
  • B. M. Dawant
    • 3
  • J.-Ph. Thiran
    • 1
  1. 1.Signal Processing Institute (ITS), Swiss Federal Institute of Technology (EPFL)LausanneSwitzerland
  2. 2.Department of NeurosurgeryLausanne University Hospital (CHUV)LausanneSwitzerland
  3. 3.Department of Electrical and Computer EngineeringVanderbilt UniversityNashville, TennesseeUSA

Personalised recommendations