Detecting Synapse Location and Connectivity by Signed Proximity Estimation and Pruning with Deep Nets

  • Toufiq ParagEmail author
  • Daniel Berger
  • Lee Kamentsky
  • Benedikt Staffler
  • Donglai Wei
  • Moritz Helmstaedter
  • Jeff W. Lichtman
  • Hanspeter Pfister
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11134)


Synaptic connectivity detection is a critical task for neural reconstruction from Electron Microscopy (EM) data. Most of the existing algorithms for synapse detection do not identify the cleft location and direction of connectivity simultaneously. The few methods that computes direction along with contact location have only been demonstrated to work on either dyadic (most common in vertebrate brain) or polyadic (found in fruit fly brain) synapses, but not on both types. In this paper, we present an algorithm to automatically predict the location as well as the direction of both dyadic and polyadic synapses. The proposed algorithm first generates candidate synaptic connections from voxelwise predictions of signed proximity generated by a 3D U-net. A second 3D CNN then prunes the set of candidates to produce the final detection of cleft and connectivity orientation. Experimental results demonstrate that the proposed method outperforms the existing methods for determining synapses in both rodent and fruit fly brain. (Code at:


  1. 1.
    Jain, V., Seung, S., Turaga, S.: Machine that learn to segment images: a crucial technology for connectomics. Curr. Opinion Neurobiol. 20, 653–666 (2010)CrossRefGoogle Scholar
  2. 2.
    Helmstaedter, M.: The mutual inspirations of machine learning and neuroscience. Neuron 86(1), 25–28 (2015)CrossRefGoogle Scholar
  3. 3.
    Funke, J., Tschopp, F.D., Grisaitis, W., Singh, C., Saalfeld, S., Turaga, S.C.: A deep structured learning approach towards automating connectome reconstruction from 3D electron micrographs. arXiv:1709.02974 (2017)
  4. 4.
    Lee, K., Zung, J., Li, P., Jain, V., Seung, H.S.: Superhuman accuracy on the SNEMI3D connectomics challenge. arXiv:1706.00120 (2017)
  5. 5.
    Januszewski, M., Maitin-Shepard, J., Li, P., Kornfeld, J., Denk, W., Jain, V.: Flood-filling networks. arXiv:1611.00421 (2016)
  6. 6.
    Parag, T., Ciresan, D.C., Giusti, A.: Efficient classifier training to minimize false merges in electron microscopy segmentation. In: The IEEE International Conference on Computer Vision (ICCV), December 2015Google Scholar
  7. 7.
    Liu, T., Zhang, M., Javanmardi, M., Ramesh, N., Tasdizen, T.: SSHMT: semi-supervised hierarchical merge tree for electron microscopy image segmentation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 144–159. Springer, Cham (2016). Scholar
  8. 8.
    Parag, T., Plaza, S., Scheffer, L.: Small sample learning of superpixel classifiers for EM segmentation. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.) MICCAI 2014. LNCS, vol. 8673, pp. 389–397. Springer, Cham (2014). Scholar
  9. 9.
    Beier, T., Pape, C., Rahaman, N., Prange, T., Berg, S.E., et al.: Multicut brings automated neurite segmentation closer to human performance. Nat. Methods 14, 101–102 (2017)CrossRefGoogle Scholar
  10. 10.
    Morgan, J.L., Lichtman, J.W.: Why not connectomics? Nat. Methods 10(6), 494–500 (2013)CrossRefGoogle Scholar
  11. 11.
    Denk, W., Briggman, K.L., Helmstaedter, M.: Structural neurobiology: missing link to a mechanistic understanding of neural computation. Nat. Rev. Neurosci. 13(5), 351–358 (2011)CrossRefGoogle Scholar
  12. 12.
    Lichtman, J.W., Pfister, H., Shavit, N.: The big data challenges of connectomics. Nat. Neurosci. 17(11), 1448–1454 (2014)CrossRefGoogle Scholar
  13. 13.
    Dorkenwald, S., et al.: Automated synaptic connectivity inference for volume electron microscopy. Nat. Methods 14(4), 435–442 (2017)CrossRefGoogle Scholar
  14. 14.
    Staffler, B., Berning, M., Boergens, K.M., Gour, A., Smagt, P.V.D., Helmstaedter, M.: SynEM, automated synapse detection for connectomics. eLife 6, e26414 (2017)CrossRefGoogle Scholar
  15. 15.
    Kreshuk, A., Funke, J., Cardona, A., Hamprecht, F.A.: Who Is talking to whom: synaptic partner detection in anisotropic volumes of insect brain. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9349, pp. 661–668. Springer, Cham (2015). Scholar
  16. 16.
    Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). Scholar
  17. 17.
    Kreshuk, A., et al.: Automated detection and segmentation of synaptic contacts in nearly isotropic serial electron microscopy images. PLoS ONE 6(10), e24899 (2011)CrossRefGoogle Scholar
  18. 18.
    Becker, C., Ali, K., Knott, G., Fua, P.: Learning context cues for synapse segmentation. IEEE Trans. Med. Imaging 32(10), 1864–1877 (2013)CrossRefGoogle Scholar
  19. 19.
    Kreshuk, A., Koethe, U., Pax, E., Bock, D.D., Hamprecht, F.A.: Automated detection of synapses in serial section transmission electron microscopy image stacks. PLoS ONE 9(2), e87351 (2014)CrossRefGoogle Scholar
  20. 20.
    Plaza, S.M., Parag, T., Huang, G.B., Olbris, D.J., Saunders, M.A., Rivlin, P.K.: Annotating synapses in large EM datasets. arXiv:1409.1801 (2014)
  21. 21.
    Jagadeesh, V., Anderson, J., Jones, B., Marc, R., Fisher, S., Manjunath, B.: Synapse classification and localization in electron micrographs. Pattern Recognit. Lett. 43, 17–24 (2014)CrossRefGoogle Scholar
  22. 22.
    Huang, G.B., Plaza, S.: Identifying synapses using deep and wide multiscale recursive networks. arXiv: 1409.1789 (2014)
  23. 23.
    Roncal, W.G., et al.: VESICLE: volumetric evaluation of synaptic interfaces using computer vision at large scale. arXiv:1403.3724 (2014)
  24. 24.
    Huang, G.B., Scheffer, L.K., Plaza, S.M.: Fully-automatic synapse prediction and validation on a large data set. arXiv:1604.03075 (2016)
  25. 25.
    Hou, L., Samaras, D., Kurc, T., Gao, Y., Saltz, J.: ConvNets with smooth adaptive activation functions for regression. In: Proceedings of the 20th AISTATS (2017)Google Scholar
  26. 26.
    Mobahi, H.: Training recurrent neural networks by diffusion. arXiv:1601.04114 (2016)
  27. 27.
    He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: ICCV (2015)Google Scholar
  28. 28.
    He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)Google Scholar
  29. 29.
    Funke, J., Saalfeld, S., Bock, D., Turaga, S., Perlman, E.: Cremi challenge.
  30. 30.
    Parag, T., et al.: Anisotropic EM segmentation by 3D affinity learning and agglomeration. arXiv:1707.08935 (2017)
  31. 31.
    Kasthuri, N., Hayworth, K., Berger, D., Schalek, R., et al.: Saturated reconstruction of a volume of neocortex. Cell 162(3), 648–661 (2015)CrossRefGoogle Scholar
  32. 32.
    Arganda-Carreras, I., Seung, H.S., Vishwanathan, A., Berger, D.R.: Snemi challenge.

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Toufiq Parag
    • 1
    Email author
  • Daniel Berger
    • 2
  • Lee Kamentsky
    • 1
  • Benedikt Staffler
    • 3
  • Donglai Wei
    • 1
  • Moritz Helmstaedter
    • 3
  • Jeff W. Lichtman
    • 2
  • Hanspeter Pfister
    • 1
  1. 1.SEASHarvard UniversityCambridgeUSA
  2. 2.MCBHarvard UniversityCambridgeUSA
  3. 3.Max Planck Institute for Brain ResearchFrankfurtGermany

Personalised recommendations