Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
. 2019 Dec;16(12):1226-1232.
doi: 10.1038/s41592-019-0582-9. Epub 2019 Sep 30.

ilastik: interactive machine learning for (bio)image analysis

Stuart Berg  1 , Dominik Kutra  2   3 , Thorben Kroeger  2 , Christoph N Straehle  2 , Bernhard X Kausler  2 , Carsten Haubold  2 , Martin Schiegg  2 , Janez Ales  2 , Thorsten Beier  2 , Markus Rudy  2 , Kemal Eren  2 , Jaime I Cervantes  2 , Buote Xu  2 , Fynn Beuttenmueller  2   3 , Adrian Wolny  2 , Chong Zhang  2 , Ullrich Koethe  2 , Fred A Hamprecht  4 , Anna Kreshuk  5   6
Affiliations
Review

ilastik: interactive machine learning for (bio)image analysis

Stuart Berg et al. Nat Methods. 2019 Dec.

Abstract

We present ilastik, an easy-to-use interactive tool that brings machine-learning-based (bio)image analysis to end users without substantial computational expertise. It contains pre-defined workflows for image segmentation, object classification, counting and tracking. Users adapt the workflows to the problem at hand by interactively providing sparse training annotations for a nonlinear classifier. ilastik can process data in up to five dimensions (3D, time and number of channels). Its computational back end runs operations on-demand wherever possible, allowing for interactive prediction on data larger than RAM. Once the classifiers are trained, ilastik workflows can be applied to new data from the command line without further user interaction. We describe all ilastik workflows in detail, including three case studies and a discussion on the expected performance.

PubMed Disclaimer

References

    1. Simpson, R., Page, K. R. & De Roure, D. Zooniverse: observing the world’s largest citizen science platform. In Proc. 23rd International Conference on World Wide Web. 1049–1054 (ACM, 2014).
    1. Hughes, A. J. et al. Gartner. Quanti.us: a tool for rapid, flexible, crowd-based annotation of images. Nat. Methods 15, 587–590 (2018). - DOI
    1. Sommer, C., Straehle, C., Köthe, U. & Hamprecht, F. A. ilastik: interactive learning and segmentation toolkit. In Proc. 8th IEEE International Symposium on Biomedical Imaging. 230–233 (IEEE, 2011).
    1. Erickson, B. J., Korfiatis, P., Akkus, Z. & Kline, T. L. Machine learning for medical imaging. RadioGraphics 37, 505–515 (2017). - DOI
    1. Geurts, P., Irrthum, A. & Wehenkel, L. Supervised learning with decision tree-based methods in computational and systems biology. Mol. BioSyst. 5, 1593–1605 (2009). - DOI

Publication types

MeSH terms

Substances