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
. 2018 Oct 3;19(1):365.
doi: 10.1186/s12859-018-2375-z.

A deep learning-based algorithm for 2-D cell segmentation in microscopy images

Yousef Al-Kofahi  1 , Alla Zaltsman  2 , Robert Graves  2 , Will Marshall  2 , Mirabela Rusu  3   4
Affiliations

A deep learning-based algorithm for 2-D cell segmentation in microscopy images

Yousef Al-Kofahi et al. BMC Bioinformatics. .

Abstract

Background: Automatic and reliable characterization of cells in cell cultures is key to several applications such as cancer research and drug discovery. Given the recent advances in light microscopy and the need for accurate and high-throughput analysis of cells, automated algorithms have been developed for segmenting and analyzing the cells in microscopy images. Nevertheless, accurate, generic and robust whole-cell segmentation is still a persisting need to precisely quantify its morphological properties, phenotypes and sub-cellular dynamics.

Results: We present a single-channel whole cell segmentation algorithm. We use markers that stain the whole cell, but with less staining in the nucleus, and without using a separate nuclear stain. We show the utility of our approach in microscopy images of cell cultures in a wide variety of conditions. Our algorithm uses a deep learning approach to learn and predict locations of the cells and their nuclei, and combines that with thresholding and watershed-based segmentation. We trained and validated our approach using different sets of images, containing cells stained with various markers and imaged at different magnifications. Our approach achieved a 86% similarity to ground truth segmentation when identifying and separating cells.

Conclusions: The proposed algorithm is able to automatically segment cells from single channel images using a variety of markers and magnifications.

Keywords: 2-D cells segmentation; Deep learning; Microscopy images; Watershed segmentation.

PubMed Disclaimer

Conflict of interest statement

Ethics approval and consent to participate

Not applicable.

Consent for publication

Not applicable.

Competing interests

At the time of the submission, all of the authors of the paper were employees or contractors of General Electric. The presented algorithm was tested in a product development environment at GE Healthcare, in which several data sets were used to assess the performance of the algorithm. The datasets used for the testing and validation of the algorithm prior to the submission of the paper are provided as a supplementary material. Additional datasets were tested post submission, yet their results are beyond the scope of the current manuscript.

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Figures

Fig. 1
Fig. 1
Various channel markers allow the visualization of cells a,b dsRed, c TexasRed, and d Cy5. A large variability exists in the appearance of cells, based on the utilized marker and magnification
Fig. 2
Fig. 2
Overview of the 2-D cell segmentation algorithm. Labeled images are used as training set for deep learning. The unseen images are passed through the inference engine to create the probability maps for the nuclear seeds and cytoplasm. Multiple steps are required for the nuclear seed prediction and the cell segmentation
Fig. 3
Fig. 3
Prediction and segmentation step-by-step outcome. a Input image. b Nuclei (Yellow-Red) and Cells (Blue-Cyan) prediction map. c Segmented Nuclei (seeds), d Segmented Cells
Fig. 4
Fig. 4
Examples of segmentation results from Experiment 1. a-c Different stains and cell cultures. Right column: segmentation results using our deep learning-based approach. Left column: semi-automated ground truth segmentation. Bottom row shows close-ups of the area in the white box. Different cell contours are shown in different colors
Fig. 5
Fig. 5
a Experiment 1: Histogram of the cell-level quality scores, for a total of 1666 segmented cells. The overall (average) quality score is ∼0.87. b Experiment 2: Receiver Operating Curve for a 10-fold cross validation the proposed approach
Fig. 6
Fig. 6
Segmentation examples from Experiment 3. Right column: segmentation results using our deep learning-based approach. Left column: semi-automated ground truth segmentation. Bottom row shows close-ups of the area in the white box. Different cell contours are shown in different colors
See this image and copyright information in PMC

References

    1. Chaffer CL, Weinberg RA. A perspective on cancer cell metastasis. Science. 2011;331(6024):1559–64. doi: 10.1126/science.1203543. - DOI - PubMed
    1. Zhou X, Wong STC. High content cellular imaging for drug development. IEEE Signal Proc Mag. 2006;23(2):170–4. doi: 10.1109/MSP.2006.1598095. - DOI
    1. Vonesch C, Aguet F, Vonesch JL, Unser M. The colored revolution of bioimaging. IEEE Signal Proc Mag. 2006;23(3):20–31. doi: 10.1109/MSP.2006.1628875. - DOI
    1. Deshmukh BS, Mankar VH. Segmentation of microscopic images: A survey. In: 2014 International Conference on Electronic Systems, Signal Processing and Computing Technologies: 2014. p. 362–4.
    1. Meijering E. Cell Segmentation: 50 Years Down the Road. IEEE Signal Proc Mag. 2012;29(5):140–5. doi: 10.1109/MSP.2012.2204190. - DOI

LinkOut - more resources