Candidate Sampling for Neuron Reconstruction from Anisotropic Electron Microscopy Volumes

  • Jan Funke
  • Julien N. P. Martel
  • Stephan Gerhard
  • Bjoern Andres
  • Dan C. Cireşan
  • Alessandro Giusti
  • Luca M. Gambardella
  • Jürgen Schmidhuber
  • Hanspeter Pfister
  • Albert Cardona
  • Matthew Cook
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8673)

Abstract

The automatic reconstruction of neurons from stacks of electron microscopy sections is an important computer vision problem in neuroscience. Recent advances are based on a two step approach: First, a set of possible 2D neuron candidates is generated for each section independently based on membrane predictions of a local classifier. Second, the candidates of all sections of the stack are fed to a neuron tracker that selects and connects them in 3D to yield a reconstruction. The accuracy of the result is currently limited by the quality of the generated candidates. In this paper, we propose to replace the heuristic set of candidates used in previous methods with samples drawn from a conditional random field (CRF) that is trained to label sections of neural tissue. We show on a stack of Drosophila melanogaster neural tissue that neuron candidates generated with our method produce 30% less reconstruction errors than current candidate generation methods. Two properties of our CRF are crucial for the accuracy and applicability of our method: (1) The CRF models the orientation of membranes to produce more plausible neuron candidates. (2) The interactions in the CRF are restricted to form a bipartite graph, which allows a great sampling speed-up without loss of accuracy.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Cardona, A.: Towards Semi-Automatic Reconstruction of Neural Circuits. Neuroinformatics 11, 31–33 (2012)CrossRefGoogle Scholar
  2. 2.
    Yuriy, M.: Automation of 3D reconstruction of neural tissue from large volume of conventional serial section transmission electron micrographs. Journal of Neuroscience Methods 176(2), 276–289 (2009)CrossRefGoogle Scholar
  3. 3.
    Jurrus, E., Paiva, A.R., Watanabe, S., Anderson, J.R., Jones, B.W., Whitaker, R.T., Jorgensen, E.M., Marc, R.E., Tasdizen, T.: Detection of neuron membranes in electron microscopy images using a serial neural network architecture. Medical Image Analysis 14(6), 770–783 (2010)CrossRefGoogle Scholar
  4. 4.
    Kaynig, V., Fuchs, T.J., Buhmann, J.M.: Geometrical Consistent 3D Tracing of Neuronal Processes in ssTEM Data. In: Jiang, T., Navab, N., Pluim, J.P.W., Viergever, M.A. (eds.) MICCAI 2010, Part II. LNCS, vol. 6362, pp. 209–216. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  5. 5.
    Kaynig, V., Fuchs, T., Buhmann, J.M.: Neuron Geometry Extraction by Perceptual Grouping in ssTEM Images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Los Alamitos, CA, USA, pp. 2902–2909 (2010)Google Scholar
  6. 6.
    Vitaladevuni, S.N.P., Basri, R.: Co-Clustering of Image Segments Using Convex Optimization Applied to EM Neuronal Reconstruction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2203–2210 (2010)Google Scholar
  7. 7.
    Vazquez-Reina, A., Huang, D., Gelbart, M., Lichtman, J., Miller, E., Pfister, H.: Segmentation Fusion for Connectomics. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), Barcelona, Spain. IEEE (2011)Google Scholar
  8. 8.
    Funke, J., Andres, B., Hamprecht, F.A., Cardona, A., Cook, M.: Efficient Automatic 3D-Reconstruction of Branching Neurons from EM Data. In: CVPR, pp. 1004–1011 (2012)Google Scholar
  9. 9.
    Ciresan, D., Giusti, A., Gambardella, L.M., Schmidhuber, J.: Deep neural networks segment neuronal membranes in electron microscopy images. In: Pereira, F., Burges, C., Bottou, L., Weinberger, K. (eds.) NIPS, vol. 25, pp. 2843–2851. Curran Associates, Inc. (2012)Google Scholar
  10. 10.
    Kaynig, V., Vazquez-Reina, A., Knowles-Barley, S., Roberts, M., Jones, T.R., Kasthuri, N., Miller, E., Lichtman, J., Pfister, H.: Large-Scale Automatic Reconstruction of Neuronal Processes from Electron Microscopy Images. ArXiv e-prints (March 2013)Google Scholar
  11. 11.
    Geman, S., Geman, D.: Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images. IEEE Transactions on Pattern Analysis and Machine Intelligence 6 (6), 721–741 (1984)CrossRefMATHGoogle Scholar
  12. 12.
    Sutton, C., McCallum, A.: An Introduction to Conditional Random Fields for Relational Learning. Technical report, Department of Computer Science University of Massachusetts (2006)Google Scholar
  13. 13.
    Gonzalez, J., Low, Y., Gretton, A., Guestrin, C.: Parallel Gibbs Sampling: From Colored Fields to Thin Junction Trees. In: Artificial Intelligence and Statistics (AISTATS), Ft. Lauderdale, FL (May 2011)Google Scholar
  14. 14.
    Gerhard, S., Funke, J., Martel, J., Cardona, A., Fetter, R.: Segmented anisotropic ssTEM dataset of neural tissue (2013), http://dx.doi.org/10.6084/m9.figshare.856713
  15. 15.
    Jones, R.: Component Trees for Image Filtering and Segmentation. In: Proceedings of the 1997 IEEE Workshop on Nonlinear Signal and Image Processing, Mackinac Island (1997)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Jan Funke
    • 1
    • 2
  • Julien N. P. Martel
    • 1
  • Stephan Gerhard
    • 1
    • 4
  • Bjoern Andres
    • 2
  • Dan C. Cireşan
    • 3
  • Alessandro Giusti
    • 3
  • Luca M. Gambardella
    • 3
  • Jürgen Schmidhuber
    • 3
  • Hanspeter Pfister
    • 2
  • Albert Cardona
    • 4
  • Matthew Cook
    • 1
  1. 1.Institute of NeuroinformaticsUZH/ETHZürichSwitzerland
  2. 2.School of Engineering and Applied ScienceHarvard UniversiyUSA
  3. 3.IDSIALuganoSwitzerland
  4. 4.HHMI JaneliaAshburn (VA)USA

Personalised recommendations