Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Correspondence
  • Published:

Multicut brings automated neurite segmentation closer to human performance

Nature Methods volume 14, pages 101–102 (2017)Cite this article

Subjects

To the Editor:

The connectomics community is acquiring volumetric electron microscopy (EM) images of the brain at an unprecedented rate with the aim of mapping out and understanding in detail the physical correlates of information processing in animals. Reliable automatic segmentation is urgently needed for upcoming whole-brain data sets (>100 terabytes (TB) per volume). Manual analysis, despite impressive progress in collaborative annotation1, will not scale to this massive task. We present an algorithm and software package to segment such data sets with low error rates. The software is made available open source in the Supplementary Software and at online repositories, and we also provide precompiled binaries (see Supplementary Note 1).

This is a preview of subscription content, access via your institution

Relevant articles

Open Access articles citing this article.

Access options

Buy this article

  • Purchase on Springer Link
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

Figure 1: The automated neurite segmentation pipeline and the influence of its components on performance.

References

  1. Kim, J.S. et al. Nature 509, 331–336 (2014).

    Article  CAS  Google Scholar 

  2. Arganda-Carreras, I. et al. Front. Neuroanat. 9, 142 (2015).

    Article  Google Scholar 

  3. Keuper, M. et al. In Intl. Conf. Comp. Vision, 1751–1759 (2015).

    Google Scholar 

  4. Andres, B. et al. Europ. Conf. Comp. Vision, Part III, (Eds. Fitzgibbon, A., Lazebnik, S. et al.) 778–791 (2012).

    Google Scholar 

  5. Beier, T. et al. IEEE Conf. Comp. Vision Patt. Recog., 3507–3516 (2015).

Download references

Acknowledgements

The authors would like to thank I. Arganda-Carreras for running all the blind evaluations on the ISBI2012 challenge and the SNEMI3D data and B. Andres for open-source code on the lifted multicut. We acknowledge support by DFG HA4364/6-1 and 8-1, SFB 1129, SFB 1134, RTG 1653, HGS MathComp and CellNetworks (F.A.H.).

Author information

Authors and Affiliations

  1. IWR, Heidelberg University, Heidelberg, Germany

    Thorsten Beier, Constantin Pape, Nasim Rahaman, Timo Prange, Ullrich Koethe, Anna Kreshuk & Fred A Hamprecht

  2. HHMI Janelia Research Campus, Ashburn, Virginia, USA

    Stuart Berg, Davi D Bock, Albert Cardona, Stephen M Plaza, Louis K Scheffer, Anna Kreshuk & Fred A Hamprecht

  3. BioEM, EPF Lausanne, Lausanne, Switzerland

    Graham W Knott

Authors
  1. Thorsten Beier
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Constantin Pape
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Nasim Rahaman
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Timo Prange
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Stuart Berg
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Davi D Bock
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Albert Cardona
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Graham W Knott
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Stephen M Plaza
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Louis K Scheffer
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Ullrich Koethe
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Anna Kreshuk
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Fred A Hamprecht
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Fred A Hamprecht.

Ethics declarations

Competing interests

The authors declare no competing financial interests.

Supplementary information

Supplementary Text and Figures

Supplementary Notes 1–9 (PDF 2340 kb)

Supplementary Software

Multicut Software (ZIP 3476 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Beier, T., Pape, C., Rahaman, N. et al. Multicut brings automated neurite segmentation closer to human performance. Nat Methods 14, 101–102 (2017). https://doi.org/10.1038/nmeth.4151

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/nmeth.4151

This article is cited by

Search

Advanced search

Quick links

Nature Briefing AI and Robotics

Sign up for the Nature Briefing: AI and Robotics newsletter — what matters in AI and robotics research, free to your inbox weekly.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing: AI and Robotics