Machine Learning: Advanced Image Segmentation Using ilastik

  • Anna Kreshuk
  • Chong Zhang
Part of the Methods in Molecular Biology book series (MIMB, volume 2040)


Segmentation is one of the most ubiquitous problems in biological image analysis. Here we present a machine learning-based solution to it as implemented in the open source ilastik toolkit. We give a broad description of the underlying theory and demonstrate two workflows: Pixel Classification and Autocontext. We illustrate their use on a challenging problem in electron microscopy image segmentation. After following this walk-through, we expect the readers to be able to apply the necessary steps to their own data and segment their images by either workflow.

Key words

Machine learning ilastik Semantic segmentation Random forest 


  1. 1.
    Myers G (2012) Why bioimage informatics matters. Nat Methods 9(7):659–660CrossRefGoogle Scholar
  2. 2.
    Meijering E, Carpenter AE, Peng H et al (2016) Imagining the future of bioimage analysis. Nat Biotechnol 34(12):1250–1255CrossRefGoogle Scholar
  3. 3.
    Coelho L, Glory-Afshar E, Kangas J et al (2010) Principles of bioimage informatics: focus on machine learning of cell patterns. In: Blaschke C, Shatkay H (eds) ISBM/ECCB, 2010. Lecture notes in bioinformatics, vol 6004, pp 8–18Google Scholar
  4. 4.
    Sommer C, Gerlich D (2013) Machine learning in cell biology-teaching computers to recognize phenotypes. J Cell Sci 126(24):5529–5539CrossRefGoogle Scholar
  5. 5.
    Kan A (2017) Machine learning applications in cell image analysis. Immunol Cell Biol 95:525–530CrossRefGoogle Scholar
  6. 6.
    Sommer C, Straele C, Koethe U et al (2011) ilastik: interactive learning and segmentation toolkit. 8th IEEE International Symposium on Biomedical Imaging (ISBI). Proceedings, p 230–233Google Scholar
  7. 7.
    LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444CrossRefGoogle Scholar
  8. 8.
    ilastik website (2018).
  9. 9.
  10. 10.
  11. 11.
    Breiman L (2001) Random forests. Mach Learn 45:5–32CrossRefGoogle Scholar
  12. 12.
    Tu Z, Bai X (2009) Auto-context and its application to high-level vision tasks and 3D brain image segmentation. Trans Pattern Anal Mach Intelligence 32(10):1744–1757Google Scholar
  13. 13.
    Haubold C, Schiegg M, Kreshuk A et al (2016) Segmenting and tracking multiple dividing targets using ilastik. Focus on bio-image informatics, p 199–229Google Scholar
  14. 14.
    Straehle CN, Köthe U, Knott G et al (2011) Carving: scalable interactive segmentation of neural volume electron microscopy images. In: Fichtinger G, Martel A, Peters T (eds) Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2011. Lecture notes in computer science, vol 6891. Springer, Berlin Heidelberg, pp 653–660Google Scholar
  15. 15.
    Beier T, Pape C, Rahaman N et al (2017) Multicut brings automated neurite segmentation closer to human performance. Nat Methods 14(2):101–102CrossRefGoogle Scholar
  16. 16.
    Arganda-Carreras I, Kaynig V, Rueden C et al (2017) Trainable Weka segmentation: a machine learning tool for microscopy pixel classification. Bioinformatics 33(15):2424–2426CrossRefGoogle Scholar
  17. 17.
    Li X, Zhou Z, Keller P et al (2015) Interactive exemplar-based segmentation toolkit for biomedical image analysis. In: IEEE 12th International Symposium on Biomedical Imaging, p 168–171Google Scholar
  18. 18.
    Marée R, Rollus L, Stévens B et al (2016) Collaborative analysis of multi-gigapixel imaging data using Cytomine. Bioinformatics 32(9):1395–1401CrossRefGoogle Scholar
  19. 19.
    Hilsenbeck O, Schwarzfischer M, Loeffler D et al (2017) fastER: a user-friendly tool for ultrafast and robust cell segmentation in large-scale microscopy. Bioinformatics 33(13):2020–2028CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  • Anna Kreshuk
    • 1
  • Chong Zhang
    • 2
  1. 1.EMBLHeidelbergGermany
  2. 2.BCN-MedTech, DTICUniversitat Pompeu FabraBarcelonaSpain

Personalised recommendations