IMaGe: Iterative Multilevel Probabilistic Graphical Model for Detection and Segmentation of Multiple Sclerosis Lesions in Brain MRI

  • Nagesh Subbanna
  • Doina Precup
  • Douglas Arnold
  • Tal Arbel
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9123)

Abstract

In this paper, we present IMaGe, a new, iterative two-stage probabilistic graphical model for detection and segmentation of Multiple Sclerosis (MS) lesions. Our model includes two levels of Markov Random Fields (MRFs). At the bottom level, a regular grid voxel-based MRF identifies potential lesion voxels, as well as other tissue classes, using local and neighbourhood intensities and class priors. Contiguous voxels of a particular tissue type are grouped into regions. A higher, non-lattice MRF is then constructed, in which each node corresponds to a region, and edges are defined based on neighbourhood relationships between regions. The goal of this MRF is to evaluate the probability of candidate lesions, based on group intensity, texture and neighbouring regions. The inferred information is then propagated to the voxel-level MRF. This process of iterative inference between the two levels repeats as long as desired. The iterations suppress false positives and refine lesion boundaries. The framework is trained on 660 MRI volumes of MS patients enrolled in clinical trials from 174 different centres, and tested on a separate multi-centre clinical trial data set with 535 MRI volumes. All data consists of T1, T2, PD and FLAIR contrasts. In comparison to other MRF methods, such as [5, 9], and a traditional MRF, IMaGe is much more sensitive (with slightly better PPV). It outperforms its nearest competitor by around 20 % when detecting very small lesions (3–10 voxels). This is a significant result, as such lesions constitute around 40 % of the total number of lesions.

References

  1. 1.
    MacDonald, I.W., et al.: Recommended diagnostic criteria for multiple sclerosis: guidelines from the international panel on the diagnosis of multiple sclerosis. Ann. Neurol. 50(1), 121–127 (2001)CrossRefGoogle Scholar
  2. 2.
    Garcia-Lorenzo, D., et al.: Review of automatic segmentation methods of multiple sclerosis white matter lesions on conventional magnetic resonance imaging. Med. Image Anal. 17(1), 1–18 (2013)CrossRefGoogle Scholar
  3. 3.
    von Leemput, K., et al.: Automated segmentationo of multiple sclerosis lesions by model outlier detection. IEEE Trans. Med. Imag. 20(8), 677–688 (2001)CrossRefGoogle Scholar
  4. 4.
    Souplet, J., et al.: An automatic segmentation of T2-FLAIR Multiple Sclerosis lesions. In: Midas Jounal (2008)Google Scholar
  5. 5.
    Schmidt, P., et al.: An automated tool for detection of FLAIR-hyperintense white-matter lesions in multiple sclerosis. NeuroImage 59, 3774–3783 (2012)CrossRefGoogle Scholar
  6. 6.
    Subbanna, N., et al.: Existence conditions for non canonical multiwindow gabor functions. Trans. Signal Process. 55(11), 5112–5117 (2007)MathSciNetGoogle Scholar
  7. 7.
    Weiss, N., Rueckert, D., Rao, A.: Multiple sclerosis lesion segmentation using dictionary learning and sparse coding. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013, Part I. LNCS, vol. 8149, pp. 735–742. Springer, Heidelberg (2013) CrossRefGoogle Scholar
  8. 8.
    Harmouche, R., et al.: Bayesian MS Lesion classification modelling regional and local spatial information. In: Proceedings of ICPR 2006, pp. 984–987 (2006)Google Scholar
  9. 9.
    Subbanna, N., et al.: Adapted MRF Segmentation of MS Lesions uisng Local Contextual Information. In: Proceedings of MIUA 2011, pp. 445–450 (2011)Google Scholar
  10. 10.
    Wu, Y., et al.: Automated segmentation of multiple sclerosis subtypes with multichannel MRI. NeuroImage 32, 1205–1215 (2006)CrossRefGoogle Scholar
  11. 11.
    Khayati, R., et al.: Fully automatic segmentation of multiple sclerosis lesions in brain MR FLAIR images using adaptive mixtures method and Markov Random field model. Comput. Bio. Med. 38, 379–390 (2008)CrossRefGoogle Scholar
  12. 12.
    Karimaghaloo, Z., Rivaz, H., Arnold, D.L., Collins, D.L., Arbel, T.: Adaptive voxel, texture and temporal conditional random field for detection of gad-enhancing multiple sclerosis lesions in brain MRI. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) Proceedings MICCAI 2013, Part I. LNCS, vol. 8149, pp. 543–550. Springer, Heidelberg (2013) CrossRefGoogle Scholar
  13. 13.
    Subbanna, N.K., Precup, D., Collins, D.L., Arbel, T.: Hierarchical probabilistic gabor and MRF segmentation of brain tumours in MRI volumes. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013, part i. LNCS, vol. 8149, pp. 751–758. Springer, Heidelberg (2013) CrossRefGoogle Scholar
  14. 14.
    Sled, J.G., Pike, G.B.: Correction for b(1) and b(0) variations in quantitative T(2) measurements using MRI. Magn. Reson. Med. 43(4), 589–593 (2000)CrossRefGoogle Scholar
  15. 15.
    Collins, D.L., et al.: Automatic 3D model based neuro-anatomical segmentation. Hum. Brain Mapp. 3, 190–208 (1995)CrossRefGoogle Scholar
  16. 16.
    Smith, S.M.: Fast robust automated brain extraction. Hum. Brain Mapp. 17(3), 143–155 (2002)CrossRefGoogle Scholar
  17. 17.
    Nyl, L.G., et al.: New variants of a method of MRI scale standardization. IEEE Trans. Med. Imag. 19(2), 143–150 (2000)CrossRefGoogle Scholar
  18. 18.
    Subbanna, N., et al.: Iterative multilevel MRF leveraging context and voxel information for brain tumour segmentation in MRI. In: Proceedings of Computer Vision and Pattern Recognition 2014, Columbus, June 2014Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Nagesh Subbanna
    • 1
  • Doina Precup
    • 1
  • Douglas Arnold
    • 1
  • Tal Arbel
    • 1
  1. 1.McGill UniversityMontrealCanada

Personalised recommendations