International Conference on Medical Image Computing and Computer-Assisted Intervention

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015 pp 123-131 | Cite as

Corpus Callosum Segmentation in MS Studies Using Normal Atlases and Optimal Hybridization of Extrinsic and Intrinsic Image Cues

  • Lisa Y. W. Tang
  • Ghassan Hamarneh
  • Anthony Traboulsee
  • David Li
  • Roger Tam
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9351)


The corpus callosum (CC) is a key brain structure and change in its size and shape is a focal point in the study of neurodegenerative diseases like multiple sclerosis (MS). A number of automatic methods have been proposed for CC segmentation in magnetic resonance images (MRIs) that can be broadly classified as intensity-based and template-based. Imaging artifacts and signal changes due to pathology often cause errors in intensity-based methods. Template-based methods have been proposed to alleviate these problems. However, registration inaccuracies (local mismatch) can occur when the template image has large intensity and morphological differences from the scan to be segmented, such as when using publicly available normal templates for a diseased population. Accordingly, we propose a novel hybrid segmentation framework that performs optimal, spatially variant fusion of multi-atlas-based and intensity-based priors. Our novel coupled graph-labeling formulation effectively optimizes, on a per-voxel basis, the weights that govern the choice of priors so that intensity priors derived from the subject image are emphasized when spatial priors derived from the registered templates are deemed less trustworthy. This stands in contrast to existing hybrid methods that either ignore local registration errors or alternate between the optimization of fusion weights and segmentation results in an expectation-maximization fashion. We evaluated our method using a public dataset and two large in-house MS datasets and found that it gave more accurate results than those achieved by existing methods for CC segmentation.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Wang, et al.: 3D vs. 2D surface shape analysis of the corpus callosum in premature neonates. In: MICCAI: Workshop on Paediatric and Perinatal Imaging (2012)Google Scholar
  2. 2.
    Kang, et al.: Corpus callosum atrophy in a large SPMS cohort and its correlation with PASAT as a cognitive marker. In: ECTRIMS (2013)Google Scholar
  3. 3.
    Mitchell, et al.: Reliable callosal measurement: population normative data confirm sex-related differences. American Journal of Neuroradiology 24(3), 410–418 (2003)Google Scholar
  4. 4.
    Herron, et al.: Automated measurement of the human corpus callosum using MRI. Frontiers in neuroinformatics 6 (2012)Google Scholar
  5. 5.
    Ardekani, et al.: Multi-atlas corpus callosum segmentation with adaptive atlas selection. In: Proc. Int. Soc. Magn. Reson. Med. Melbourne, Australia, Abstract, vol. 2564 (2012)Google Scholar
  6. 6.
    Adamson, et al.: Software pipeline for midsagittal corpus callosum thickness profile processing. Neuroinformatics, 595–614 (2014)Google Scholar
  7. 7.
    McIntosh, Hamarneh: Medial-based deformable models in nonconvex shape-spaces for medical image segmentation. IEEE Trans. Medical Imaging 31(1), 33–50 (2012)CrossRefGoogle Scholar
  8. 8.
    Vachet, et al.: Automatic corpus callosum segmentation using a deformable active Fourier contour model. In: SPIE Medical Imaging, pp. 831707–831707 (2012)Google Scholar
  9. 9.
    Changizi, N., Hamarneh, G., Ishaq, O., Ward, A., Tam, R.: Extraction of the Plane of Minimal Cross-Sectional Area of the Corpus Callosum Using Template-Driven Segmentation. In: Jiang, T., Navab, N., Pluim, J.P.W., Viergever, M.A. (eds.) MICCAI 2010, Part III. LNCS, vol. 6363, pp. 17–24. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  10. 10.
    Meyer: Multi-atlas Based Segmentation of Corpus Callosum on MRIs of Multiple Sclerosis Patients. In: Pattern Recognition: 36th German Conference, pp. 729–735 (2014)Google Scholar
  11. 11.
    Wu, et al.: A generative probability model of joint label fusion for multi-atlas based brain segmentation. Medical Image Analysis, 881–890 (2014)Google Scholar
  12. 12.
    Lötjönen, et al.: Fast and robust multi-atlas segmentation of brain magnetic resonance images. NeuroImage, 2352–2365 (2010)Google Scholar
  13. 13.
    Sanroma, et al.: Learning-based atlas selection for multiple-atlas segmentation. In: IEEE CVPR, pp. 3111–3117 (2014)Google Scholar
  14. 14.
    Aljabar, et al.: Multi-atlas based segmentation of brain images: atlas selection and its effect on accuracy. NeuroImage 46, 726–738 (2009)CrossRefGoogle Scholar
  15. 15.
    Wang, et al.: Multi-atlas segmentation with joint label fusion. TPAMI, 611–623 (2013)Google Scholar
  16. 16.
    Grady, L.: Multilabel random walker image segmentation using prior models. In: CVPR, vol. 1, pp. 763–770. IEEE (2005)Google Scholar
  17. 17.
    Zhang, Z., Zhu, Q., Xie, Y.: A novel image matting approach based on naive Bayes classifier. In: Huang, D.-S., Jiang, C., Bevilacqua, V., Figueroa, J.C. (eds.) ICIC 2012. LNCS, vol. 7389, pp. 433–441. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  18. 18.
    Heinrich, et al.: MIND: Modality independent neighbourhood descriptor for multi-modal deformable registration. Medical Image Analysis 16, 1423–1435 (2012)CrossRefGoogle Scholar
  19. 19.
    Tang, L.Y.W., Hamarneh, G.: Random walks with efficient search and contextually adapted image similarity for deformable registration. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013, Part II. LNCS, vol. 8150, pp. 43–50. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  20. 20.
    Hammers, et al.: Three-dimensional maximum probability atlas of the human brain, with particular reference to the temporal lobe. Human Brain Mapping 19, 224–247 (2003)CrossRefGoogle Scholar
  21. 21.
    Avants, et al.: A reproducible evaluation of ANTs similarity metric performance in brain image registration. NeuroImage 52, 2033–2044 (2011)CrossRefGoogle Scholar
  22. 22.
    Heinrich, M.P., Jenkinson, M., Brady, S.M., Schnabel, J.A.: Globally optimal deformable registration on a minimum spanning tree using dense displacement sampling. In: Ayache, N., Delingette, H., Golland, P., Mori, K. (eds.) MICCAI 2012, Part III. LNCS, vol. 7512, pp. 115–122. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  23. 23.
    Cardoso, et al.: STEPS: Similarity and Truth Estimation for Propagated Segmentations and its application to hippocampal segmentation and brain parcelation. Medical Image Analysis 17(6), 671–684 (2013)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Lisa Y. W. Tang
    • 1
  • Ghassan Hamarneh
    • 2
  • Anthony Traboulsee
    • 1
  • David Li
    • 1
  • Roger Tam
    • 1
  1. 1.University of British ColumbiaVancouverCanada
  2. 2.Medical Image Analysis Lab.Simon Fraser UniversityBurnabyCanada

Personalised recommendations