Atlas of Classifiers for Brain MRI Segmentation

  • Boris KodnerEmail author
  • Shiri Gordon
  • Jacob Goldberger
  • Tammy Riklin Raviv
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10541)


We present a conceptually novel framework for brain tissue segmentation based on an Atlas of Classifiers (AoC). The AoC allows a statistical summary of the annotated datasets taking into account both the imaging data and the corresponding labels. It is therefore more informative than the classical probabilistic atlas and more economical than the popular multi-atlas approaches, which require large memory consumption and high computational complexity for each segmentation. Specifically, we consider an AoC as a spatial map of voxel-wise multinomial logistic regression (LR) functions learned from the labeled data. Upon convergence, the resulting fixed LR weights (a few for each voxel) represent the training dataset, which might be huge. Segmentation of a new image is therefore immediate and only requires the calculation of the LR outputs based on the respective voxel-wise features. Moreover, the AoC construction is independent of the test images, providing the flexibility to train it on the available labeled data and use it for the segmentation of images from different datasets and modalities.

The proposed method has been applied to publicly available datasets for the segmentation of brain MRI tissues and is shown to outreach commonly used methods. Promising results were obtained also for multi-modal, cross-modality MRI segmentation.



This study was partially supported by the Israel Science Foundation (1638/16 T.R.R) and IDF Medical Corps (T.R.R.).


  1. 1.
    Ashburner, J., Friston, K.J.: Unified segmentation. Neuroimage 26(3), 839–851 (2005)CrossRefGoogle Scholar
  2. 2.
    Bishop, C.M.: Pattern recognition. Mach. Learn. 128, 1–58 (2006)Google Scholar
  3. 3.
    Fischl, et al.: Whole brain segmentation: automated labeling of neuroanatomical structures in the human brain. Neuron 33(3), 341–355 (2002)Google Scholar
  4. 4.
    Goldberger, J., Greenspan, H.: Context-based segmentation of image sequences. TPAMI 28(3), 463–468 (2006)CrossRefGoogle Scholar
  5. 5.
    Gupta, L., Sortrakul, T.: A gaussian-mixture-based image segmentation algorithm. Pattern Recogn. 31(3), 315–325 (1998)CrossRefGoogle Scholar
  6. 6.
    Iglesias, J.E., Sabuncu, M.R.: Multi-atlas segmentation of biomedical images: a survey. MEDIA 24(1), 205–219 (2015)Google Scholar
  7. 7.
    Leemput, V., et al.: Automated model-based tissue classification of MR images of the brain. TMI 18(10), 897–908 (1999)Google Scholar
  8. 8.
    Mendrik, et al.: MRBrainS challenge: Online evaluation framework for brain image segmentation in 3T MRI scans. Comput. Intelll. Neurosci. 2015, 16 (2015)Google Scholar
  9. 9.
    Moeskops, P., et al.: Automatic segmentation of MR brain images with a convolutional neural network. TMI 35(5), 1252–1261 (2016)Google Scholar
  10. 10.
    Pohl, K.M., et al.: A hierarchical algorithm for MR brain image parcellation. TMI 26(9), 1201–1212 (2007)Google Scholar
  11. 11.
    Rohlfing, T.: Image similarity and tissue overlaps as surrogates for image registration accuracy: widely used but unreliable. TMI 31(2), 153–163 (2012)Google Scholar
  12. 12.
    Valverde, S., et al.: Comparison of 10 brain tissue segmentation methods using revisited IBSR annotations. J. Magn. Res. Imaging 41(1), 93–101 (2015)CrossRefGoogle Scholar
  13. 13.
    Vercauteren, T., et al.: Diffeomorphic demons: efficient non-parametric image registration. NeuroImage 45, S61–S72 (2009)CrossRefGoogle Scholar
  14. 14.
    Wachinger, C., Golland, P.: Spectral label fusion. In: Ayache, N., Delingette, H., Golland, P., Mori, K. (eds.) MICCAI 2012. LNCS, vol. 7512, pp. 410–417. Springer, Heidelberg (2012). doi: 10.1007/978-3-642-33454-2_51 CrossRefGoogle Scholar
  15. 15.
    Wang, L., et al.: LINKS: learning-based multi-source integration framework for segmentation of infant brain images. NeuroImage 108, 160–172 (2015)CrossRefGoogle Scholar
  16. 16.
    Wells, W.M., et al.: Adaptive segmentation of MRI data. TMI 15(4), 429–442 (1996)Google Scholar
  17. 17.
    Yaqub, M., et al.: Investigation of the role of feature selection and weighted voting in random forests for 3-d volumetric segmentation. IEEE Trans. Med. Imaging 33(2), 258–271 (2014)CrossRefGoogle Scholar
  18. 18.
    Zhang, Y., et al.: Segmentation of brain MR images through a hidden markov random field model and the expectation-maximization algorithm. TMI 20(1), 45–57 (2001)Google Scholar
  19. 19.
    Zhang, W., et al.: Deep convolutional neural networks for multi-modality isointense infant brain image segmentation. NeuroImage 108, 214–224 (2015)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Boris Kodner
    • 1
    • 2
    Email author
  • Shiri Gordon
    • 1
    • 2
  • Jacob Goldberger
    • 3
  • Tammy Riklin Raviv
    • 1
    • 2
  1. 1.Department of Electrical and Computer EngineeringBen-Gurion University of the NegevBeershebaIsrael
  2. 2.The Zlotowski Center for NeuroscienceBen-Gurion University of the NegevBeershebaIsrael
  3. 3.Faculty of EngineeringBar-Ilan UniversityRamat GanIsrael

Personalised recommendations