EPySeg: a coding-free solution for automated segmentation of epithelia using deep learning

Benoît Aigouy; Claudio Cortes; Shanda Liu; Benjamin Prud'homme

doi:10.1242/dev.194589

journal article Open Access Jan 01, 2020

EPySeg: a coding-free solution for automated segmentation of epithelia using deep learning

Benoît Aigouy

Claudio Cortes Shanda Liu Benjamin Prud'homme

Development · The Company of Biologists

View at Publisher Save 10.1242/dev.194589

Abstract

Epithelia are dynamic tissues that self-remodel during their development. During morphogenesis, the tissue-scale organization of epithelia is obtained through a sum of individual contributions of the cells constituting the tissue. Therefore, understanding any morphogenetic event first requires a thorough segmentation of its constituent cells. This task, however, usually implies extensive manual correction, even with semi-automated tools. Here we present EPySeg, an open-source, coding-free software that uses deep learning to segment membrane-stained epithelial tissues automatically and very efficiently. EPySeg, which comes with a straightforward graphical user interface, can be used as a python package on a local computer, or on the cloud via Google Colab for users not equipped with deep-learning compatible hardware. By substantially reducing human input in image segmentation, EPySeg accelerates and improves the characterization of epithelial tissues for all developmental biologists.

Topics

No keywords indexed for this article. Browse by subject →

References

26

[1]

Abadi "TensorFlow: large-scale machine learning on heterogeneous distributed systems" (2016)

[2]

Aigouy "Segmentation and Quantitative Analysis of Epithelial Tissues" (2016) 10.1007/978-1-4939-6371-3_13

[3]

Buchholz "DenoiSeg: joint denoising and segmentation" arXiv (2020)

[4]

Cavey "A two-tiered mechanism for stabilization and immobilization of E-cadherin" Nature (2008) 10.1038/nature06953

[5]

Chaurasia "LinkNet: Exploiting encoder representations for efficient semantic segmentation" (2017) 10.1109/vcip.2017.8305148

[6]

Cilla "Segmentation and tracking of adherens junctions in 3D for the analysis of epithelial tissue morphogenesis" PLoS Comput. Biol. (2015) 10.1371/journal.pcbi.1004124

[7]

Cortes "Epithelial properties of the second heart field" Circ. Res. (2018) 10.1161/circresaha.117.310838

[8]

Farrell "SEGGA: a toolset for rapid automated analysis of epithelial cell polarity and dynamics" Development (2017) 10.1242/dev.146837

[9]

Francou "Epithelial tension in the second heart field promotes mouse heart tube elongation" Nat. Commun. (2017) 10.1038/ncomms14770

[10]

Gómez-De-Mariscal "DeepImageJ: A user-friendly plugin to run deep learning models in ImageJ" bioRxiv (2019) 10.1101/799270

[11]

Heller "EpiTools: an open-source image analysis toolkit for quantifying epithelial growth dynamics" Dev. Cell (2016) 10.1016/j.devcel.2015.12.012

[12]

Kingma "Adam: a method for stochastic optimization" arXiv (2017)

[13]

Madhavan "Morphogenesis of the epidermis of adult abdomen of Drosophila" (1980)

[14]

Rahman "Optimizing Intersection-Over-Union in Deep Neural Networks for Image Segmentation" Advances in Visual Computing (2016)

[15]

Fiji: an open-source platform for biological-image analysis

Johannes Schindelin, Ignacio Arganda-Carreras, Erwin Frise et al.

Nature Methods 2012 10.1038/nmeth.2019

[16]

Schmidt (2018)

[17]

NIH Image to ImageJ: 25 years of image analysis

Caroline A Schneider, Wayne S Rasband, Kevin W Eliceiri

Nature Methods 2012 10.1038/nmeth.2089

[18]

Simonyan "Very deep convolutional networks for large-scale image recognition" (2015)

[19]

Stringer "Cellpose: a generalist algorithm for cellular segmentation" Nat. Methods (2020)

[20]

Tepass "The development of cellular junctions in the drosophila embryo" Dev. Biol. (1994) 10.1006/dbio.1994.1054

[21]

Truong Quang "Principles of E-cadherin supramolecular organization in vivo" Curr. Biol. (2013) 10.1016/j.cub.2013.09.015

[22]

Ulman "An objective comparison of cell-tracking algorithms" Nat. Methods (2017) 10.1038/nmeth.4473

[23]

Watersheds in digital spaces: an efficient algorithm based on immersion simulations

L. Vincent, P. Soille

IEEE Transactions on Pattern Analysis and Machine... 1991 10.1109/34.87344

[24]

von Chamier (2020) 10.1101/2020.03.20.000133

[25]

Weigert "Content-aware image restoration: pushing the limits of fluorescence microscopy" Nat. Methods (2018) 10.1038/s41592-018-0216-7

[26]

Willis "Cell size and growth regulation in the Arabidopsis thaliana apical stem cell niche" Proc. Natl Acad. Sci. USA (2016) 10.1073/pnas.1616768113

Metrics

51

Citations

26

References

Details

Published: Jan 01, 2020
License: View

Authors

B

Benoît Aigouy

Aix Marseille Univ, CNRS, IBDM, Marseille, France

C

Claudio Cortes

Aix Marseille Univ, CNRS, IBDM, Marseille, France

S

Shanda Liu

Max Planck Institute for Plant Breeding Research, Köln, Germany

B

Benjamin Prud'homme

Aix Marseille Univ, CNRS, IBDM, Marseille, France

Funding

Centre National de la Recherche Scientifique

European Research Council

Seventh Framework Programme Award: 615789

Fondation Leducq Award: 15CVD01

Max Planck Core

France-BioImaging/PICsL infrastructure Award: ANR-10-INSB-04-01

Cite This Article

Benoît Aigouy, Claudio Cortes, Shanda Liu, et al. (2020). EPySeg: a coding-free solution for automated segmentation of epithelia using deep learning. Development. https://doi.org/10.1242/dev.194589

EPySeg: a coding-free solution for automated segmentation of epithelia using deep learning

You May Also Like