Neuroinformatics

, Volume 11, Issue 4, pp 447–468 | Cite as

Deformable Templates Guided Discriminative Models for Robust 3D Brain MRI Segmentation

  • Cheng-Yi Liu
  • Juan Eugenio Iglesias
  • Zhuowen Tu
  • for The Alzheimer’s Disease Neuroimaging Initiative
Original Article

Abstract

Automatically segmenting anatomical structures from 3D brain MRI images is an important task in neuroimaging. One major challenge is to design and learn effective image models accounting for the large variability in anatomy and data acquisition protocols. A deformable template is a type of generative model that attempts to explicitly match an input image with a template (atlas), and thus, they are robust against global intensity changes. On the other hand, discriminative models combine local image features to capture complex image patterns. In this paper, we propose a robust brain image segmentation algorithm that fuses together deformable templates and informative features. It takes advantage of the adaptation capability of the generative model and the classification power of the discriminative models. The proposed algorithm achieves both robustness and efficiency, and can be used to segment brain MRI images with large anatomical variations. We perform an extensive experimental study on four datasets of T1-weighted brain MRI data from different sources (1,082 MRI scans in total) and observe consistent improvement over the state-of-the-art systems.

Keywords

Brain image segmentation Fusion Deformable templates Discriminative models Generative models 

Supplementary material

12021_2013_9190_MOESM1_ESM.doc (206 kb)
(PDF 205 KB)

References

  1. Akselrod-Ballin, A., Galun, M., Gomori, J., Basri, R., Brandt, A. (2006). Atlas guided identification of brain structures by combining 3D segmentation and SVM classification. In Proceedings of international conference on medical image computing and computer assisted intervention (MICCAI’06), Part I (Vol. 4191, pp. 209–216).Google Scholar
  2. Akselrod-Ballin, A., Galun, M., Gomori, J., Brandt, A., Basri, R. (2007). Prior knowledge driven multiscale segmentation of brain MRI. In Proceedings of international conference on medical image computing and computer assisted intervention (MICCAI’07), Part II (pp.118–126).Google Scholar
  3. Aljabar, P., Heckemann, R., Hammers, A., Hajnal, J., Rueckert, D. (2007). Classifier selection strategies for label fusion using large atlas databases. In Proceedings of international conference on medical image computing and computer assisted intervention (MICCAI’07), Part I (Vol. 4791, pp. 523–531).Google Scholar
  4. Ashburner, J., & Friston, K. (2005). Unified segmentation. NeuroImage, 26(3), 839–851.PubMedCrossRefGoogle Scholar
  5. Avants, B., Epstein, C., Grossman, M., Gee, J. (2008). Symmetric diffeomorphic image registration with cross-correlation: evaluating automated labeling of elderly and neurodegenerative brain. Medical Image Analysis, 12, 26–41.PubMedCrossRefGoogle Scholar
  6. Bauer, S., Nolte, L.P., Reyes, M. (2011). Fully automatic segmentation of brain tumor images using support vector machine classification in combination with hierarchical conditional random field regularization. In Proceedings of international conference on medical image computing and computer assisted intervention (MICCAI’11), Part III (Vol. 6893, pp. 354–361).Google Scholar
  7. Bazin, P.L., & Pham, D. (2007). Topology-preserving tissue classification of magnetic resonance brain images. IEEE Transactions on Medical Imaging, 26(4), 487–496.PubMedCrossRefGoogle Scholar
  8. Bazin, P.L., & Pham, D. (2009). Homeomorphic brain image segmentation with topological and statistical atlases. Medical Image Analysis, 12, 616–625.CrossRefGoogle Scholar
  9. Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.CrossRefGoogle Scholar
  10. Caldairou, B., Passat, N., Habas, P.A., Studholme, C., Rousseau, F. (2011). A non-local fuzzy segmentation method: application to brain MRI. Computer Analysis of Images and Patterns, 44(9), 1916–1927.Google Scholar
  11. Calinon, S., Guenter, F., Billard, A. (2007). On learning, representing and generalizing a task in a humanoid robot. Special issue on robot learning by observation, demonstration and imitation. IEEE Transactions on Systems, Man and Cybernetics, Part B, 37(2), 286–298.Google Scholar
  12. Chan, T., & Vese, L. (2001). Active contours without edges. IEEE Transactions on Image Processing, 10(2), 266–277.PubMedCrossRefGoogle Scholar
  13. Chen, H.M., & Varshney, P. (2003). Mutual information-based CT-MR brain image registration using generalized partial volume joint histogram estimation. IEEE Transactions on Medical Imaging, 22(9), 1111–1119.PubMedCrossRefGoogle Scholar
  14. Corso, J., Sharon, E., Dube, S., El-Saden, S., Sinha, U., Yuille, A. (2008). Efficient multilevel brain tumor segmentation with integrated Bayesian model classification. IEEE Transactions on Medical Imaging, 27, 629–640.PubMedCrossRefGoogle Scholar
  15. Du, J., Younes, L., Qiu, A. (2011). Whole brain diffeomorphic metric mapping via integration of sulcal and gyral curves, cortical surfaces, and images. NeuroImage, 56(1), 162–173.PubMedCrossRefGoogle Scholar
  16. Essen, D.C.V., Dickson, J., Harwell, J., Hanlon, D., Anderson, C.H., Drury, H.A. (2001). An integrated software system for surface-based analyses of cerebral cortex. Journal of American Medical Informatics Association, 8(5), 443–459.CrossRefGoogle Scholar
  17. Fan, Y., Shen, D., Gur, R.C., Gur, R.E., Davatzikos, C. (2007). COMPARE: classification of morphological patterns using adaptive regional elements. IEEE Transactions on Medical Imaging, 1, 93–105.CrossRefGoogle Scholar
  18. Felzenszwalb, P.F. (2005). Representation and detection of deformable shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(2), 208–220.PubMedCrossRefGoogle Scholar
  19. Fischl, B., & et al. (2002). Whole brain segmentation: automated labeling of neuroanatomical structures in the human brain. Neuron, 33, 341–355.PubMedCrossRefGoogle Scholar
  20. Fischl, B., Salat, D.H., van der Kouwe, A.J., Makris, N., Segonne, F., Quinn, B.T., Dale, A.M. (2004). Sequence-independent segmentation of magnetic resonance images. NeuroImage, 23, S69–S84.PubMedCrossRefGoogle Scholar
  21. Fitzpatrick, J., Wang, M.Y., Dawant, B.M., Maurer, C.R.J., Kessler, R.M., Maciunas, R.J. (1999). Retrospective intermodality registration techniques for images of the head: surface-based versus volume-based. IEEE Transactions on Medical Imaging, 18(2), 144–150.PubMedCrossRefGoogle Scholar
  22. Frackowiak, R., Friston, K., Frith, C., Dolan, R., Price, C., Zeki, S., Ashburner, J., Penny, W. (2003). Human brain function. New York: Academic Press.Google Scholar
  23. Freund, Y., & Schapire, R. (1997). A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Comparative and System Sciences, 55(1), 119–139.CrossRefGoogle Scholar
  24. Geremia, E., Clatz, O., Menze, B.H., Konukoglu, E., Criminisi, A., Ayache, N. (2011). Spatial decision forests for ms lesion segmentation in multi-channel magnetic resonance images. NeuroImage, 57(2), 378–390.PubMedCrossRefGoogle Scholar
  25. Geremia, E., Menze, B.H., Clatz, O., Konukoglu, E., Criminisi, A., Ayache, N. (2010). Spatial decision forests for MS lesion segmentation in multi-channel MR images. In Proceedings of international conference on medical image computing and computer assisted intervention (MICCAI’10), Part I (Vol. 6361, pp. 111–118).Google Scholar
  26. Gouttard, S., & et al. (2007). Subcortical structure segmentation using probabilistic atlas priors. Medical Imaging, 6512, 1–11.Google Scholar
  27. Heckemann, R., Hajnal, J., Aljabar, P., Rueckert, D., Hammers, A. (2006). Automatic anatomical brain MRI segmentation combining label propagation and decision fusion. NeuroImage, 33(1), 115–126.PubMedCrossRefGoogle Scholar
  28. Holub, A., Welling, M., Perona, P. (2008). Hybrid generative-discriminative visual categorization.International Journal of Computer Vision, 77(1–3), 239–258.CrossRefGoogle Scholar
  29. Hou, Z. (2006). A review on MR image intensity inhomogeneity correction. International Journal of Biomedical Imaging, 2006, 1–11.CrossRefGoogle Scholar
  30. Hua, X., & et al. (2009). Optimizing power to track brain degeneration in Alzheimer’s disease and mild cognitive impairment with tensor-based morphometry: an ADNI study of 515 subjects. NeuroImage, 48, 668–681.PubMedCrossRefGoogle Scholar
  31. Jack, C., & et al. (2008). The Alzheimer’s disease neuroimaging initiative (ADNI): The MR imaging protocol. Journal of Magnetic Resonance Imaging, 24, 685–691.CrossRefGoogle Scholar
  32. Jebara, T. (2003). Machine learning: discriminative and generative. Boston: Kluwer.Google Scholar
  33. Khan, A., Chung, M., Beg, M. (2009). Robust atlas-based brain segmentation using multi-structure confidence-weighted registration. In Proceedings of international conference on medical image computing and computer assisted intervention (MICCAI’09), Part II (pp. 549–557).Google Scholar
  34. Klauschen, F., Goldman, A., Barra V., Meyer-Lindenberg, A., Lundervold, A. (2009). Evaluation of automated brain MR image segmentation and volumetry methods. Human Brain Mapping, 30, 1310–1327.PubMedCrossRefGoogle Scholar
  35. Klein, A., & et al. (2009). Evaluation of 14 nonlinear deformation algorithms applied to human brain MRI registration. NeuroImage, 46(3), 786–802.PubMedCrossRefGoogle Scholar
  36. Lao, Z., Shen, D., Jawad, A., Karacali, B., Liu, D., Melhem, E., Bryan, N., Davatzikos, C. (2006). Automated segmentation of whitematter lesions in 3D brain MR images, using multivariate pattern classification. In Proceedings of IEEE international symposium on biomedical imaging (ISBI’06) (pp. 307–310). Arlington.Google Scholar
  37. Lasserre, J., Bishop, C., Minka, T. (2006). Principled hybrids of generative and discriminative models. In IEEE conference on computer vision and pattern recognition (CVPR’06) (Vol. 1, pp. 87–94).Google Scholar
  38. Lee, C., Schmidt, M., Murtha, A., Bistritz, A., Sander, J., Greiner, R. (2005). Segmenting brain tumor with conditional random fields and support vector machines. In Proceedings of workshop of computer vision for biomedical image application: current techniques and future trends (pp. 469–478). Beijing.Google Scholar
  39. Leemput, K.V., Maes F., Vandermeulen, D., Colchester, A., Suetens, P. (2001). Automated segmentation of multiple sclerosis lesions by model outlier detection. IEEE Transactions on Medical Imaging, 20(8), 677–688.PubMedCrossRefGoogle Scholar
  40. Leemput, K.V., Maes, F., Vandermeulen, D., Suetens, P. (1999). Automated model-based tissue classification of MR images of the brain. IEEE Transactions on Medical Imaging, 18(10), 897–908.PubMedCrossRefGoogle Scholar
  41. Li, C., Goldgof, D., Hall, L. (1993). Knowledge-based classification and tissue labeling of MR images of human brain. IEEE Transactions on Medical Imaging, 12(4), 740–750.PubMedCrossRefGoogle Scholar
  42. Li, H., & Fan, Y. (2012). Label propagation with robust initialization for brain tumor segmentation. In IEEE international symposium on biomedical imaging (ISBI’12) (pp. 1715–1718).Google Scholar
  43. Li, Z., & Fan, J. (2008). 3D MRI brain image segmentation based on region restricted EM algorithm In: Proceedings of SPIE (Vol. 6914, pp. 69,1400.1–69,140.8).Google Scholar
  44. Liang P., & Jordan M. (2008). An asymptotic analysis of generative, discriminative, and pseudo-likelihood estimators. In Proceedings of international conference on machine learning (ICML’08) (pp. 584–591).Google Scholar
  45. Loncaric, S. (1998). A survey of shape analysis techniques. Pattern Recognition, 31(8), 983–1001.CrossRefGoogle Scholar
  46. Luo, Y., & Chung, A.C.S. (2011). An atlas-based deep brain structure segmentation method: from coarse positioning to fine shaping. In IEEE international conference on acoustics, speech and signal processing (ICASSP’11) (pp. 1085–1088).Google Scholar
  47. Menze, B.H., Leemput, K.V., Lashkari, D., Weber, M.A., Ayache, N., Golland, P. (2010). A generative model for brain tumorsegmentation in multi-modal images. In Proceedings of international conference on medical image computing and computer assisted intervention (MICCAI’10), Part II (Vol. 6362, pp. 151–159).Google Scholar
  48. Morra, J.H., Tu, Z., Apostolova, L., Green, A.E., Toga, A., Thompson, P. (2010). Comparison of adaboost and support vector machines for detecting Alzheimer’ss disease through automated hippocampal segmentation. IEEE Transactions on Medical Imaging, 29(1), 30–43.PubMedCrossRefGoogle Scholar
  49. Ng A., & Jordan M. (2002). On discriminative vs. generative classifiers: a comparison of logistic regression and naive Bayes. In Advances in neural information processing systems (NIPS’02) (Vol. 14, pp. 841–848).Google Scholar
  50. Pham, D., & Prince, J. (1999). Adaptive fuzzy segmentation of magnetic resonance images. IEEE Transactions on Medical Imaging, 18(9), 737–752.PubMedCrossRefGoogle Scholar
  51. Pieper, S., Lorensen, B., Schroeder, W., Kikinis, R. (2006). The NA-MIC kit: ITK, VTK, pipelines, grids and 3D slicer as an open platform for the medical image computing community. In Proceedings of IEEE international symposium on biomedical imaging (ISBI’06) (pp. 698–701).Google Scholar
  52. Pizer, S.M., & et al. (2003). Deformable m-reps for 3D medical image segmentation.International Journal of Computer Vision, 55(2), 85–106.PubMedCrossRefGoogle Scholar
  53. Pohl, K., Fisher, J., Kikinis, R., Grimson, W., Wells, W. (2006). A Bayesian model for joint segmentation and registration. NeuroImage, 31(1), 228–239.PubMedCrossRefGoogle Scholar
  54. Prastawa, M., Bullitt, E., Moon, N., Leemput, K.V., Gerig, G. (2003). Automatic brain tumor segmentation by subject specific modification of atlas priors. Academic Radiology, 10(12), 134–1348.CrossRefGoogle Scholar
  55. Quddus, A., Fieguth, P., Basir, O. (2005). Adaboost and support vector machines for white matter lesion segmentation in MR images. In IEEE annual conference on engineering in medicine and biology (EMBS’05).Google Scholar
  56. Raina, R., Shen, Y., Ng, A., McCallum, A. (2003). Classification with hybrid generative/discriminative models. In Advances in neural information processing systems (NIPS’03) (Vol. 16, pp. 545–552).Google Scholar
  57. Sabuncu, M., Yeo, B., Leemput, K.V., Fischl, B., Golland, P. (2010). A generative model for image segmentation based on label fusion. IEEE Transactions on Medical Imaging, 29(10), 1714–1729.PubMedCrossRefGoogle Scholar
  58. Scherrer, B., Dojat, M., Forbes, F., Garbay, C. (2007). LOCUS: local cooperative unified segmentation of MRI brain scans. In Medical image computing and computer assisted intervention (MICCAI’07), Part I (pp. 219–227).Google Scholar
  59. Scherrer, B., Forbes, F., Garbay, C., Dojat, M. (2009). Distributed local MRF models for tissue and structure brain segmentation. IEEE Transactions on Medical Imaging, 28, 1278–1295.PubMedCrossRefGoogle Scholar
  60. Schuff, N., Tosun, D., Insel, P., Chiang, G., Truran, D., Aisen, P., Jack, C.J., Weiner, M.A.D.N. (2012). Initiative: nonlinear time course of brain volume loss in cognitively normal and impaired elders. Neurobiology of Aging, 33, 845–855.PubMedCrossRefGoogle Scholar
  61. Shattuck, D., Sandor-Leahy, S., Schaper, K., Rottenberg, D., Leahy, R. (2001). Magnetic resonance image tissue classification using a partial volume model. NeuroImage, 13, 856–876.PubMedCrossRefGoogle Scholar
  62. Shattuck, D.W., & et al. (2008). Construction of a 3D probabilistic atlas of human cortical structures. NeuroImage, 39, 1064–1080.PubMedCrossRefGoogle Scholar
  63. Simpson, I.J.A., Woolrich, M.W., Groves, A.R., Schnabel, J.A. (2011). Longitudinal brain MRI analysis with uncertain registration uncertain registration. In Proceedings of international conference on medical image computing and computer assisted intervention (MICCAI’11), Part II (Vol. 6892, pp. 647–654).Google Scholar
  64. Sled, J., Zijdenbos, A., Evans, A. (1998). A nonparametric method for automatic correction of intensity non-uniformity in MRI data. IEEE Transactions on Medical Imaging, 17, 87–97.PubMedCrossRefGoogle Scholar
  65. Smith, S. (2002). Fast robust automated brain extraction. Human Brain Mapping, 17, 143–155.PubMedCrossRefGoogle Scholar
  66. Tibshirani, R. (1996). Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society, 58(1), 267–288.Google Scholar
  67. Tu, Z. (2007). Learning generative models via discriminative approaches. In IEEE conference on computer vision and pattern recognition (CVPR’07) (pp. 1–8).Google Scholar
  68. Tu Z., & Bai X. (2010). Auto-context and its application to high-level vision tasks and 3D brain image segmentation. IEEE Transactions on PAMI, 32(10), 1744–1757.CrossRefGoogle Scholar
  69. Tu, Z., Narr, K., Dollar, P., Dinov, I., Thompson, P., Toga, A. (2008). Brain anatomical structure segmentation by hybrid discriminative/generative models. IEEE Transactions on Medical Imaging, 27, 495–508.PubMedCrossRefGoogle Scholar
  70. Unay, D., Ekin, A., Jasinschi, R. (2008). Medical image search and retrieval using local binary patterns and KLT feature points. In IEEE conference on image processing (ICIP’08) (pp. 997–1000).Google Scholar
  71. Vapnik, V. (1982). Estimation of dependences based on empirical data. Berlin: Springer.Google Scholar
  72. Vapnik, V. (1998). Statistical learning theory. New York: Wiley.Google Scholar
  73. Verma, R., Zacharaki, E.I., Ou, Y., Cai, H., Chawl, S., Lee, S.K., Melhem, E.R., Wolf, R., Davatzikos, C. (2008). Multi-parametric tissue characterization of brain neoplasms and their recurrence using pattern classification of MR images. Academic Radiology, 15(8), 966–977.PubMedCrossRefGoogle Scholar
  74. Wang, H., Das, S., Suh, J., Altinay, M., Pluta, J., Craige, C., Avants, B., Yushkevich, P. (2011). The Alzheimer’s disease neuroimaging initiative: a learning-based wrapper method to correct systematic errors in automatic image segmentation: consistently improved performance in hippocampus, cortex and brain segmentation. NeuroImage, 55(3), 968–985.PubMedCrossRefGoogle Scholar
  75. Wells, W., Kikinis, R., Grimson, W., Jolesz, F. (1996). Adaptive segmentation of MRI data. IEEE Transactions on Medical Imaging, 15(4), 429–442.PubMedCrossRefGoogle Scholar
  76. Wels, M., Zheng, Y., Carneiro, G., Huber, M., Hornegger, J., Comaniciu, D. (2009). Fast and robust 3-D MRI brain structure segmentation. In Proceedings of international conference on medical image computing and computer assisted intervention (MICCAI’09), Part II (pp. 575–583).Google Scholar
  77. Wels, M., Zheng, Y., Huber, M., Hornegger, J., Comaniciu, D. (2011). A discriminative model-constrained EM approach to 3D MRI brain tissue classification and intensity non-uniformity correction. Physics in Medicine and Biology, 56(11), 3269–3300.PubMedCrossRefGoogle Scholar
  78. Wolz R., Aljabar P., Rueckert D., Heckemann R., Hammers A. (2009). Segmentation of subcortical structures and the hippocampus in brain MRI using graph-cuts and subject–specific a-priori information. In Proceedings of IEEE international symposium on biomedical imaging (ISBI’09) (pp. 470–473).Google Scholar
  79. Woods, R., Mazziotta, J., Cherry, S. (1993). MRI-PET registration with automated algorithm. Journal of Computer Assisted Tomography, 17, 536–546.PubMedCrossRefGoogle Scholar
  80. Woolrich, M., & Behrens, T. (2006). Variational Bayes inference of spatial mixture models for segmentation. IEEE Transactions on Medical Imaging, 2(10), 1380–1391.CrossRefGoogle Scholar
  81. Wu, J., & Chung, A. (2005). A new solver for Markov random field modeling and applications to medical image segmentation. In Proceedings of international conference on medical image computing and computer assisted intervention (MICCAI’05), Part I (pp. 229–237).Google Scholar
  82. Wu J., & Chung A. (2008). Markov dependence tree-based segmentation of deep brain structures. In Proceedings of international conference on medical image computing and computer assisted intervention (MICCAI’08), Part II (Vol. 5242, pp. 1092–1100).Google Scholar
  83. Wu, J., & Chung, A. (2009). A novel framework for segmentation of deep brain structures based on Markov dependence tree. NeuroImage, 49, 1027–1036.CrossRefGoogle Scholar
  84. Yang, F., Shan, Z.Y., Kruggel, F. (2010). White matter lesion segmentation based on feature joint occurrence probability and χ 2 random field theory from magnetic resonance (MR) images. Pattern Recognition Letters, 31(9), 781–790.CrossRefGoogle Scholar
  85. Yang, J., Staib, L., Duncan, J. (2004). Neighbor-constrained segmentation with level set based 3D deformable models. IEEE Transactions on Medical Imaging, 23(8), 940–948.PubMedCrossRefGoogle Scholar
  86. Yaqub, M., Javaid, M.K., Cooper, C., Noble, J.A. (2011). Improving the classification accuracy of the classic rf method by intelligent feature selection and weighted voting of trees with application to medical image segmentation. In International conference on machine learning in medical imaging (MLMI’11) (pp. 184–192).Google Scholar
  87. Yi, Z., Criminisi, A., Shotton, J., Blake, A. (2009). Discriminative, semantic segmentation of brain tissue in MR images. In Proceedings of international conference on medical image computing and computer assisted intervention (MICCAI’09), Part II (Vol. 5762, pp. 558–565).Google Scholar
  88. Yushkevich, P.A., Piven, J., Hazlett, H.C., Smith, R.G., Ho, S., Gee, J.C., Gerig, G. (2006). User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability. NeuroImage, 31(3), 1116–1128.PubMedCrossRefGoogle Scholar
  89. Zhang, N., Ruan, S., Lebonvallet, S., Liao, Q., Zhu, Y. (2009). Multi-kernel SVM based classification for brain tumor segmentation of MRI multi-sequence. In IEEE international conference on image processing (ICIP’09) (pp. 3373–3376).Google Scholar
  90. Zhou, J., & Rajapakse, J. (2005). Segmentation of subcortical brain structures using fuzzy templates. NeuroImage, 28(4), 915–924.PubMedCrossRefGoogle Scholar
  91. Zhu S., & Yuille A. (1996). Region competition: unifying snake/balloon, region growing and Bayes/MDL/energy for multi-band image segmentation. IEEE Transactions on PAMI, 18(9), 884–900.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  • Cheng-Yi Liu
    • 1
  • Juan Eugenio Iglesias
    • 2
  • Zhuowen Tu
    • 1
  • for The Alzheimer’s Disease Neuroimaging Initiative
  1. 1.Laboratory of Neuro Imaging Department of NeurologyUCLA School of MedicineLos AngelesUSA
  2. 2.Department of RadiologyMassachusetts General HospitalCharlestownUSA

Personalised recommendations