Abstract
Automatic 3D segmentation of the brain from MR scans is a challenging problem that has received enormous amount of attention lately. Of the techniques reported in literature, very few are fully automatic. In this paper, we present an efficient and accurate, fully automatic 3D segmentation procedure for brain MR scans. It has several salient features namely, (1) instead of a single multiplicative bias field that affects all tissue intensities, separate parametric smooth models are used for the intensity of each class. This may be a more realistic model and avoids the need for a logarithmic transformation. (2) A brain atlas is used in conjunction with a robust registration procedure to find a non-rigid transformation that maps the standard brain to the specimen to be segmented. This transformation is then used to: segment the brain from non-brain tissue; compute prior probabilities for each class at each voxel location and find an appropriate automatic initialization. (3) Finally, a novel algorithm is presented which is a variant of the EM procedure, that incorporates a fast and accurate way to find optimal segmentations, given the intensity models along with the spatial coherence assumption. Experimental results with both synthetic and real data are included, as well as comparisons of the performance of our algorithm with that of other published methods.
Chapter PDF
Similar content being viewed by others
Keywords
- Markov Random Field
- Automatic Segmentation
- Expectation Maximization Algorithm
- Intensity Model
- Spatial Inhomogeneity
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.
References
Evans A.C., Collins D.L., Mills S.R., Brown E.D., Kelly R.L., and Peters T.M. 3d statistical neuroanatomical models from 305 mri volumes. In Proc. IEEE Nuclear Sc. Symp., Med. Imaging, pages 1813–1817, 1993.
Dempster A.P., Laird N.M., and Rubin D.B. Maximum likehood from imcomplete data via the em algorithm. J. Roy. Stat. Soc. B, 39:1–38, 1977.
J. Besag. Spatial interaction and statistical analysis of lattice systems. Journal of Royal Statistical Society B, 36:192–236, 1974.
Vemuri B. C., Ye J., Chen Y., and Leonard C. M. A level-set based approach to image registration. In IEEE Workshop on MMBIA, pages 86–93, June 2000.
Cocosco C.A., Kollokian V., Kwan R.K., and Evans A.C. Brainweb: Online interface to a 3d mri simulated brain database. Neuroimage, 5(4):part2/4, S425 (images available on http://www.bic.mni.mcgill.ca/brainweb/), 1997.
H. E. Cline, C. L. Doumulin, H. R. Hart, W. E. Lorensen, and S. Ludke. 3-d reconstruction of the brain from magnetic resonance images using a connectivity algorithm. Magnetic Resonance Imaging, 5:345–352, 1987.
M. E. Brummer et.al. Automatic detection of brain contours in mri data sets. IEEE Trans. on Med. Imaging, 12:153–166, 1993.
Maes F., Collignon A., Vandermeulen G., Marchal G., and Suetens P. Multimodal-ity image registration by maximization of mutual information. IEEE Trans. on Med. Imaging, 16:187–198, 1997.
Geiger G. and Girosi F. Parallel and deterministic algorithms for mrfs: Surface reconstruction and integration. IEEE TPAMI, 12:401–412, 1991.
Gerig G., Martin J., Kikinis R., Kubler O., Shenton M., and Jolesz F. Automatic segmentation of dual-echo mr head data. In XII Intl. Conf. on IPMI, pages 175–187, 1991.
W.M. Wells III, W.E.L. Grimson, R. Kikinis, and F. A. Jolesz. Adaptive segmentation of mri data. IEEE Trans. on Med. Imaging, 15:429–442, Aug. 1996.
Ashburner J., Friston K., Holmes A., and Poline J.B. Statistical parametric mapping. Technical report, The Wellcome Dept. Cognitive Neurology, Univ. College, London, U.K. Available: http://www.fil.ion.ucl.ac.uk/spm/, 2000.
Marroquin J., Mitter S., and Poggio T. Probabilistic solution of ill-posed problems in computational vision. J. Am. Stat. Asoc., 82:76–89, 1987.
Marroquin J., F. Velasco, Rivera M., and M. Nakamura. Gauss-markov measure field models for low-level vision. IEEE TPAMI, 23:337–348, 2001.
Zhang J. Mean field theory in em procedures for mrf’s. IEEE Trans. on Sig. Proc. 40:2570–2583, 1992.
Rajapakse J.C. and Krugge F. Segmentation of mr images with intensity inhomo-geneities. Image and Vision Computing, 16:165–180, 1998.
M. Joliot and B. M. Majoyer. Three dimensional segmentation and interpolation of magnetic resonance brain images. IEEE Trans. on Med. Imaging, 12(2):269–277, 1993.
Held K., Kopsa E.R., Krause B.J., Wells W.M., Kikinis R., and Müller-Gartner H.W. Markov random field segmentation of brain mr images. IEEE Trans. on Med. Imaging, 16(6):878–886, 1997.
T. Kapur, W.E.L. Grimson, W. M. Wells III, and R. Kikinis. Segmentation of brain tissue from magnetic resonance images. Med. Image Aanalysis, 1(2):109–127, 1996.
Yuille A. L. and Kosowsky. Statistical physics algorithms that converge. Neural Computation, 6(3):341–356, 1994.
R. Leahy, T. Herbert, and R. Lee. Application of markov random fields in medical imaging. In IPMI, pages 1–14, 1989.
K. V. Leemput, F. Maes, D. Vandermeulen, and P. Suetens. Automated model-based bias field correction of mr images of the brain. IEEE Trans. on Med. Imaging, 18(10):885–896, 1999.
K. V. Leemput, F. Maes, D. Vandermeulen, and P. Suetens. Automated model-based tissue classification of mr images of the brain. IEEE Trans. on Med. Imaging, 18(10):897–908, 1999.
Atkins M.S. and Mackiewich B.T. Fully automatic segmentation of the brain in mri. IEEE Trans. on Med. Imaging, 17(1):98–107, 1998.
Zienkiewicz O.C. and Taylor R.L. The Finite Element Method. McGraw Hill, 1989.
T. N. Pappas. An adaptive clustering algorithm for image segmentation. IEEE Trans. on Signal Processing, 40(4):901–914, 1992.
Duda R.O., Hart P.E., and Stork D. G. Pattern Classification. Wiley Interscience, New York, 2001.
Geman S. and Geman D. Stochastic relaxation, gibbs distributions and the bayesian restoration of images. IEEE TPAMI, 6:721–741, 1984.
Kirkpatrick S., Gelatt C.D., and M.P. Vecchi. Optimization by simulated annealing. Science, 220(4598):671–680, 1983.
Sandor S. and Leahy R. A 3d morphological algorithm for automated labeling of the cortex in magnetic resonance brain images. In AAAI Spring Symp. on Applications of Compu. Vision in Medical Image Processing, 1994.
Hofmann T., Puzicha J., and Buhmann J. M. Unsupervised texture segmentation in a deterministic annealing framework. IEEE TPAMI, 20(8):803–818, 1998.
U. Tiede T. Schiemann and K. H. Hohne. Segmentation of visible human for high quality volume-based visualization. Medical Image Analysis, 1(4):263–270, 1996.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Marroquin, J.L., Vemuri, B.C., Botello, S., Calderon, F. (2002). An Accurate and Efficient Bayesian Method for Automatic Segmentation of Brain MRI. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds) Computer Vision — ECCV 2002. ECCV 2002. Lecture Notes in Computer Science, vol 2353. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-47979-1_38
Download citation
DOI: https://doi.org/10.1007/3-540-47979-1_38
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-43748-2
Online ISBN: 978-3-540-47979-6
eBook Packages: Springer Book Archive