Subject Specific Sparse Dictionary Learning for Atlas Based Brain MRI Segmentation

  • Snehashis Roy
  • Aaron Carass
  • Jerry L. Prince
  • Dzung L. Pham
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8679)


Quantitative measurements from segmentations of soft tissues from magnetic resonance images (MRI) of human brains provide important biomarkers for normal aging, as well as disease progression. In this paper, we propose a patch-based tissue classification method from MR images using sparse dictionary learning from an atlas. Unlike most atlas-based classification methods, deformable registration from the atlas to the subject is not required. An “atlas” consists of an MR image, its tissue probabilities, and the hard segmentation. The “subject” consists of the MR image and the corresponding affine registered atlas probabilities (or priors). A subject specific patch dictionary is created by learning relevant patches from the atlas. Then the subject patches are modeled as sparse combinations of learned atlas patches. The same sparse combination is applied to the segmentation patches of the atlas to generate tissue memberships of the subject. The novel combination of prior probabilities in the example patches enables us to distinguish tissues having similar intensities but having different spatial location. We show that our method outperforms two state-of-the-art whole brain tissue segmentation methods. We experimented on 12 subjects having manual tissue delineations, obtaining mean Dice coefficients of 0.91 and 0.87 for cortical gray matter and cerebral white matter, respectively. In addition, experiments on subjects with ventriculomegaly shows significantly better segmentation using our approach than the competing methods.


Image synthesis intensity normalization hallucination patches 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Ashburner, J., Friston, K.J.: Unified segmentation. NeuroImage 26(3), 839–851 (2005)CrossRefGoogle Scholar
  2. 2.
    Shiee, N., Bazin, P., Ozturk, A., Reich, D.S., Calabresi, P.A., Pham, D.L.: A Topology-Preserving Approach to the Segmentation of Brain Images with Multiple Sclerosis Lesions. NeuroImage (2009)Google Scholar
  3. 3.
    Dale, A.M., Fischl, B., Sereno, M.I.: Cortical Surface-Based Analysis I: Segmentation and Surface Reconstruction. NeuroImage 9(2), 179–194 (1999)CrossRefGoogle Scholar
  4. 4.
    Leemput, K.V., Maes, F., Vandermeulen, D., Suetens, P.: Automated Model-Based Tissue Classification of MR Images of the Brain. IEEE Trans. on Med. Imag. 18(10), 897–908 (1999)CrossRefGoogle Scholar
  5. 5.
    Coupé, P., Eskildsen, S.F., Manjón, J.V., Fonov, V.S., Collins, D.L.: The Alzheimer’s disease Neuroimaging Initiative: Simultaneous segmentation and grading of anatomical structures for patient’s classification: application to Alzheimer’s disease. NeuroImage 59(4), 3736–3747 (2012)CrossRefGoogle Scholar
  6. 6.
    Tong, T., Wolz, R., Coupe, P., Hajnal, J.V., Rueckert, D.: The Alzheimer’s Disease Neuroimaging Initiative: Segmentation of MR images via discriminative dictionary learning and sparse coding: Application to hippocampus labeling. NeuroImage 76(1), 11–23 (2013)CrossRefGoogle Scholar
  7. 7.
    Roy, S., Carass, A., Prince, J.: Magnetic Resonance Image Example Based Contrast Synthesis. IEEE Trans. Med. Imag. 32(12), 2348–2363 (2013)CrossRefGoogle Scholar
  8. 8.
    Cao, T., Zach, C., Modla, S., Powell, D., Czymmek, K., Niethammer, M.: Registration for correlative microscopy using image analogies. In: Dawant, B.M., Christensen, G.E., Fitzpatrick, J.M., Rueckert, D. (eds.) WBIR 2012. LNCS, vol. 7359, pp. 296–306. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  9. 9.
    Aharon, M., Elad, M., Bruckstein, A.M.: K-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation. IEEE Trans. Sig. Proc. 54(11), 4311–4322 (2006)CrossRefGoogle Scholar
  10. 10.
    Shiee, N., Bazin, P.-L., Cuzzocreo, J.L., Blitz, A., Pham, D.L.: Segmentation of brain images using adaptive atlases with application to ventriculomegaly. In: Székely, G., Hahn, H.K. (eds.) IPMI 2011. LNCS, vol. 6801, pp. 1–12. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  11. 11.
    Carass, A., Cuzzocreo, J., Wheeler, M.B., Bazin, P.L., Resnick, S.M., Prince, J.L.: Simple paradigm for extra-cerebral tissue removal: Algorithm and analysis. NeuroImage 56(4), 1982–1992 (2011)CrossRefGoogle Scholar
  12. 12.
    Sled, J.G., Zijdenbos, A.P., Evans, A.C.: A non-parametric method for automatic correction of intensity non-uniformity in MRI data. IEEE Trans. on Med. Imag. 17(1), 87–97 (1998)CrossRefGoogle Scholar
  13. 13.
    Pham, D.L., Prince, J.L.: An Adaptive Fuzzy C-Means Algorithm for Image Segmentation in the Presence of Intensity Inhomogeneities. Pattern Recog. Letters 20(1), 57–68 (1999)CrossRefzbMATHGoogle Scholar
  14. 14.
    Klein, A., et al.: Evaluation of 14 nonlinear deformation algorithms applied to human brain MRI registration. NeuroImage 46(3), 786–802 (2009)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Snehashis Roy
    • 1
  • Aaron Carass
    • 2
  • Jerry L. Prince
    • 2
  • Dzung L. Pham
    • 1
  1. 1.Center for Neuroscience and Regenerative MedicineHenry Jackson FoundationUSA
  2. 2.Department of Electrical and Computer EngineeringJohns Hopkins UniversityUSA

Personalised recommendations