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:

OMERO.searcher: content-based image search for microscope images

Nature Methods volume 9, pages 633–634 (2012)Cite this article

Subjects

To the Editor:

Fluorescence microscopy is growing dramatically both in terms of technical capabilities and the volume of images generated. Online repositories have been created to provide public access to images and opportunities for joint research for many scientists1. This has reintroduced challenges faced when sequence and structure databases were being established: developing fast and effective means of searching for records (images) either by context (such as which protein is labeled) or content (such as which pattern it displays). Image databases normally contain context descriptors in the form of annotations that describe the source of the sample, the protocol used to prepare it, the instrument settings used and the laboratory where it was produced. Searches can readily be done on one or more of these annotations, but incomplete or inconsistent annotation remains a problem. Searching for images based on their contents is much less developed. Some content annotations may be provided in the form of labels (such as Gene Ontology terms) resulting from either visual or automated analysis, and therefore images can be retrieved using them in the same way as context terms. However, these are limited by the 'resolution' of the terms used and do not facilitate discovery of new patterns or of similarities between known patterns that were not previously recognized. Content-based image retrieval (also known as 'query by image content') was proposed many years ago to address this issue; this method takes one or more images as a query and retrieves the most similar images in terms of numerically computed features2. However, current fluorescence microscopy image databases do not provide these search methods. Here we present a content-based image searcher for microscope images, OMERO.searcher (http://murphylab.web.cmu.edu/software/searcher/), that can be used with any OMERO database (http://openmicroscopy.org/)3.

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: Results of retrieval performance tests.

References

  1. Swedlow, J.R. Nat. Cell Biol. 13, 183 (2011).

    Article  CAS  Google Scholar 

  2. Faloutsos, C. et al. J. Intell. Inf. Syst. 3, 231–262 (1994).

    Article  Google Scholar 

  3. Allan, C. et al. Nat. Methods 9, 245–253 (2012).

    Article  CAS  Google Scholar 

  4. Glory, E. & Murphy, R.F. Dev. Cell 12, 7–16 (2007).

    Article  CAS  Google Scholar 

  5. Wu, L., Faloutsos, C., Sycara, K.P. & Payne, T.R. in Proc. 26th Int. Conf. Very Large Data Bases (eds., Abbadi, A.E. et al.) 297–306 (Morgan Kaufmann, 2000).

    Google Scholar 

  6. Huang, K., Lin, J., Gajnak, J.A. & Murphy, R.F. in Proc. 2002 IEEE Int. Symp. Biomed. Imaging, 325–328 (2002).

    Google Scholar 

Download references

Acknowledgements

This research was supported in part by US National Institutes of Health grants GM075205, EB008516 and GM092708 and by grant 095931 from the Wellcome Trust. B.H.C. was supported by a postdoctoral fellowship from the Korea Research Foundation Grant (KRF-2008-D00316). We thank K. Eliceiri, J. Swedlow, J. Moore, D. Orloff, L. Wu and C. Faloutsos for helpful discussions.

Author information

Authors and Affiliations

  1. Lane Center for Computational Biology, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA

    Baek Hwan Cho, Ivan Cao-Berg & Robert F Murphy

  2. Center for Bioimage Informatics, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA

    Jennifer Ann Bakal & Robert F Murphy

  3. Department of Biological Sciences, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA

    Robert F Murphy

  4. Department of Machine Learning, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA

    Robert F Murphy

  5. Freiburg Institute for Advanced Studies, Albert Ludwig University of Freiburg, Germany

    Robert F Murphy

Authors
  1. Baek Hwan Cho
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ivan Cao-Berg
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jennifer Ann Bakal
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Robert F Murphy
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Robert F Murphy.

Ethics declarations

Competing interests

The authors declare no competing financial interests.

Supplementary information

Supplementary Text and Figures

Supplementary Figures 1 and 2, Supplementary Methods and Supplementary Note (PDF 1301 kb)

Supplementary Software

OMERO.searcher client software and example images (ZIP 89473 kb)

Rights and permissions

Reprints and permissions

About this article

Cite this article

Cho, B., Cao-Berg, I., Bakal, J. et al. OMERO.searcher: content-based image search for microscope images. Nat Methods 9, 633–634 (2012). https://doi.org/10.1038/nmeth.2086

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/nmeth.2086

This article is cited by

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

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