Deep Learning Automates the Quantitative Analysis of Individual Cells in Live-Cell Imaging Experiments
By D. V. Valen, Takamasa Kudo, Keara M. Lane, Derek N. Macklin, N. Quach, Mialy Defelice, Inbal Maayan, Yu Tanouchi, Euan A. Ashley, Markus W. Covert. 2016
531 citations recorded by the source corpus.
Live-cell imaging has opened an exciting window into the role cellular heterogeneity plays in dynamic, living systems. A major critical challenge for this class of experiments is the problem of image segmentation, or determining which parts of a microscope image correspond to which individual cells. Current approaches require many hours of manual curation and depend on approaches that are difficult to share between labs. They are also unable to robustly segment the cytoplasms of mammalian cells. Here, we show that deep convolutional neural networks, a supervised machine learning method, can solve this challenge for multiple cell types across the domains of life. We demonstrate that this approach can robustly segment fluorescent images of cell nuclei as well as phase images of the cytoplasms of individual bacterial and mammalian cells from phase contrast images without the need for a fluorescent cytoplasmic marker. These networks also enable the simultaneous segmentation and identification of different mammalian cell types grown in co-culture. A quantitative comparison with prior methods demonstrates that convolutional neural networks have improved accuracy and lead to a significant reduction in curation time. We relay our experience in designing and optimizing deep convolutional neural networks for this task and outline several design rules that we found led to robust performance. We conclude that deep convolutional neural networks are an accurate method that require less curation time, are generalizable to a multiplicity of cell types, from bacteria to mammalian cells, and expand live-cell imaging capabilities to include multi-cell type systems.
Subfields: Atomic and Molecular Physics, and Optics, Biophysics, Media Technology, Medical Imaging, Computational Biology & Bioinformatics
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Atomic and Molecular Physics, and Optics
In Biophysics
- C. Stringer
- Marius Pachitariu
- Shantanu Singh
- Juan C. Caicedo
- Anne E Carpenter
- Casey S. Greene
- G. Way
- Faisal Mahmood
In Media Technology
- Marius Pachitariu
- C. Stringer
- Shantanu Singh
- Juan C. Caicedo
- Xin Gao
- Zhiyong Lu
- Anton Osokin
- Uwe Schmidt
In Medical Imaging
- C. Stringer
- Shantanu Singh
- Marius Pachitariu
- Juan C. Caicedo
- Peter Naylor
- Anne E Carpenter
- Thomas Walter
- Richard J. Chen
In Computational Biology & Bioinformatics
- Xin Gao
- Yu Li
- Brett K. Beaulieu-Jones
- Shantanu Singh
- Gail L. Rosen
- Zhiyong Lu
- Juan C. Caicedo
- Anne E Carpenter
Citations in the corpus
- Opportunities and obstacles for deep learning in biology and medicine (2017, background): “Given the dramatic successes of deep learning in biological imaging, we simply refer to articles that review recent advancements [16,202,203].”
- Segmentation of Nuclei in Histopathology Images by Deep Regression of the Distance Map (2019, methodology): “segmentation [31], [32] of nuclei in H&E images and other imaging modalities [33], [34]; see [35] for a comprehensive”
- In silico labeling: Predicting fluorescent labels in unlabeled images (2018, background): “Prior workusingdeeplearningtoanalyzemicroscopyimageshasbeen limited, often relying on known cell locations (Held et al., 2010; Zhongetal.,2012)ortheimpositionofspecialandsomewhatarti-ficialsample preparationprocedures,such as therequirementfor low-plating density (Held et al., 2010; Van Valen et al.,”
- Star-convex Polyhedra for 3D Object Detection and Segmentation in Microscopy (2019, background): “More recently, methods based on deep learning have been shown to vastly improve results for natural and biomedical images alike [11, 24, 25].”
- Evaluation of Deep Learning Strategies for Nucleus Segmentation in Fluorescence Images (2018, methodology): “(17), which was demonstrated to be accurate on a variety of cell segmentation tasks, including mammalian cell segmentation and nuclei.”
- GANs for Biological Image Synthesis (2017, background): “Although the field has only recently embraced deep learning, neural networks are now starting to make a splash, mainly in classical discriminative settings [45].”
- Attention-Based Transformers for Instance Segmentation of Cells in Microstructures (2020, background): “Instance segmentation is a major bottleneck in quantifying single-cell microscopy data and manual analysis is prohibitively labour intensive [9], [11], [16], [18], [19].”
- Deep Adversarial Training for Multi-Organ Nuclei Segmentation in Histopathology Images (2018, methodology): “This problem has previously been mitigated by contour prediction [31, 62, 63], concave point detection [64] and distance map regression [65].”
- State-of-the-art review on deep learning in medical imaging. (2019, methodology): “The DL framework implemented here was CNN architecture (51).”
- Deep learning in bioinformatics: introduction, application, and perspective in big data era (2019, methodology): “Biomedical image processing and diagnosis CT images, PET images, MRI images 2D data CNN, GAN [35, 66, 41, 22, 160]”
- An introduction to spatial transcriptomics for biomedical research (2022, methodology): “There are numerous published segmentation methods using different approaches such as manual segmentation, prior information from nuclear staining [73], deep neural networks [74], gene expression signatures from true single-cell references generated by scRNA-seq [73, 75], and some workflows such as s”