Deep Segmentation of Bacteria at Different Stages of the Life Cycle

Conference paper
Part of the Informatik aktuell book series (INFORMAT)


Segmentation of bacteria in live cell microscopy image sequences is a crucial task to gain insights into molecular processes. A main challenge is that some bacteria strongly change their appearance during the life cycle as response to fluctuations in environmental conditions. We present a novel deep learning method with shape-based weighting of the loss function to accurately segment bacteria during different stages of the life cycle. We evaluate the performance of the method for live cell microscopy images of Bacillus subtilis bacteria with strong changes during the life cycle.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Battenberg E, Bischofs-Pfeifer I. A system for automatic cell segmentation of bacterial microscopy images. Arkin Laboratory for Dynamical Genomics, Lawrence Berkeley National Laboratory; 2006.Google Scholar
  2. 2.
    Chowdhury S, Kandhavelu M, Yli-Harja O, et al. Cell segmentation by multiresolution analysis and maximum likelihood estimation (MAMLE). BMC Bioinformatics. 2013 Aug;14(10):S8.Google Scholar
  3. 3.
    Liluashvili V, Bergeest JP, Harder N, et al. Automatic single-Cell segmentation and tracking of bacterial cells in fluorescence microscopy images. In: BVM; 2015. p. 239–244.Google Scholar
  4. 4.
    Stylianidou S, Brennan C, Nissen SB, et al. SuperSegger: robust image segmentation, analysis and lineage tracking of bacterial cells. Mol Microbiol. 2016 Aug;102(4):690–700.Google Scholar
  5. 5.
    Sadanandan SK, Baltekin, Magnusson KEG, et al. Segmentation and trackanalysis in time-lapse imaging of bacteria. IEEE J Sel Top Signal Process. 2016 Feb;10(1):174–184.Google Scholar
  6. 6.
    Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. In: MICCAI; 2015. p. 234–241.Google Scholar
  7. 7.
    Hernandez CX, Sultan MM, Pande VS. Using deep learning for segmentation and counting within microscopy data. arXiv. 2018;/1802.10548.Google Scholar
  8. 8.
    Arbelle A, Raviv TR. Microscopy cell segmentation via convolutional LSTM networks. In: IEEE 16th ISBI; 2019. p. 1008–1012.Google Scholar
  9. 9.
    Hay EA, Parthasarathy R. Performance of convolutional neural networks for identification of bacteria in 3D microscopy datasets. PLOS Comput Biol. 2018 12;14(12):1–17.Google Scholar
  10. 10.
    He K, Zhang X, Ren S, et al. Deep residual learning for image recognition. In: IEEE CVPR; 2016. p. 770–778.Google Scholar

Copyright information

© Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature 2020

Authors and Affiliations

  1. 1.Biomedical Computer Vision Group, BioQuant, IPMBHeidelberg University Im Neuenheimer Feld 267HeidelbergDeutschland
  2. 2.BioQuant, Center for Molecular Biology (ZMBH),Heidelberg UniversityHeidelbergDeutschland
  3. 3.Max Planck Institute for Terrestrial MicrobiologyMarburgDeutschland

Personalised recommendations