Survey statistics of automated segmentations applied to optical imaging of mammalian cells

ESQmodel: biologically informed evaluation of 2-D cell segmentation quality in multiplexed tissue images

MOTIVATION

Single cell segmentation is critical in the processing of spatial omics data to accurately perform cell type identification and analyze spatial expression patterns. Segmentation methods often rely on semi-supervised annotation or labeled training data which are highly dependent on user expertise. To ensure the quality of segmentation, current evaluation strategies quantify accuracy by assessing cellular masks or through iterative inspection by pathologists. While these strategies each address either the statistical or biological aspects of segmentation, there lacks a unified approach to evaluating segmentation accuracy.

RESULTS

In this article, we present ESQmodel, a Bayesian probabilistic method to evaluate single cell segmentation using expression data. By using the extracted cellular data from segmentation and a prior belief of cellular composition as input, ESQmodel computes per cell entropy to assess segmentation quality by how consistent cellular expression profiles match with cell type expectations.

AVAILABILITY AND IMPLEMENTATION

Source code is available on Github at: https://github.com/Roth-Lab/ESQmodel.

A Compound Loss Function With Shape Aware Weight Map for Microscopy Cell Segmentation

Microscopy cell segmentation is a crucial step in biological image analysis and a challenging task. In recent years, deep learning has been widely used to tackle this task, with promising results. A critical aspect of training complex neural networks for this purpose is the selection of the loss function, as it affects the learning process. In the field of cell segmentation, most of the recent research in improving the loss function focuses on addressing the problem of inter-class imbalance. Despite promising achievements, more work is needed, as the challenge of cell segmentation is not only the inter-class imbalance but also the intra-class imbalance (the cost imbalance between the false positives and false negatives of the inference model), the segmentation of cell minutiae, and the missing annotations. To deal with these challenges, in this paper, we propose a new compound loss function employing a shape aware weight map. The proposed loss function is inspired by Youden's J index to handle the problem of inter-class imbalance and uses a focal cross-entropy term to penalize the intra-class imbalance and weight easy/hard samples. The proposed shape aware weight map can handle the problem of missing annotations and facilitate valid segmentation of cell minutiae. Results of evaluations on all ten 2D+time datasets from the public cell tracking challenge demonstrate 1) the superiority of the proposed loss function with the shape aware weight map, and 2) that the performance of recent deep learning-based cell segmentation methods can be improved by using the proposed compound loss function.

Impact of Training Data, Ground Truth and Shape Variability in the Deep Learning-Based Semantic Segmentation of HeLa Cells Observed with Electron Microscopy

This paper investigates the impact of the amount of training data and the shape variability on the segmentation provided by the deep learning architecture U-Net. Further, the correctness of ground truth (GT) was also evaluated. The input data consisted of a three-dimensional set of images of HeLa cells observed with an electron microscope with dimensions 8192×8192×517. From there, a smaller region of interest (ROI) of 2000×2000×300 was cropped and manually delineated to obtain the ground truth necessary for a quantitative evaluation. A qualitative evaluation was performed on the 8192×8192 slices due to the lack of ground truth. Pairs of patches of data and labels for the classes nucleus, nuclear envelope, cell and background were generated to train U-Net architectures from scratch. Several training strategies were followed, and the results were compared against a traditional image processing algorithm. The correctness of GT, that is, the inclusion of one or more nuclei within the region of interest was also evaluated. The impact of the extent of training data was evaluated by comparing results from 36,000 pairs of data and label patches extracted from the odd slices in the central region, to 135,000 patches obtained from every other slice in the set. Then, 135,000 patches from several cells from the 8192×8192 slices were generated automatically using the image processing algorithm. Finally, the two sets of 135,000 pairs were combined to train once more with 270,000 pairs. As would be expected, the accuracy and Jaccard similarity index improved as the number of pairs increased for the ROI. This was also observed qualitatively for the 8192×8192 slices. When the 8192×8192 slices were segmented with U-Nets trained with 135,000 pairs, the architecture trained with automatically generated pairs provided better results than the architecture trained with the pairs from the manually segmented ground truths. This suggests that the pairs that were extracted automatically from many cells provided a better representation of the four classes of the various cells in the 8192×8192 slice than those pairs that were manually segmented from a single cell. Finally, the two sets of 135,000 pairs were combined, and the U-Net trained with these provided the best results.

GEMA-An Automatic Segmentation Method for Real-Time Analysis of Mammalian Cell Growth in Microfluidic Devices

Nowadays, image analysis has a relevant role in most scientific and research areas. This process is used to extract and understand information from images to obtain a model, knowledge, and rules in the decision process. In the case of biological areas, images are acquired to describe the behavior of a biological agent in time such as cells using a mathematical and computational approach to generate a system with automatic control. In this paper, MCF7 cells are used to model their growth and death when they have been injected with a drug. These mammalian cells allow understanding of behavior, gene expression, and drug resistance to breast cancer. For this, an automatic segmentation method called GEMA is presented to analyze the apoptosis and confluence stages of culture by measuring the increase or decrease of the image area occupied by cells in microfluidic devices. In vitro, the biological experiments can be analyzed through a sequence of images taken at specific intervals of time. To automate the image segmentation, the proposed algorithm is based on a Gabor filter, a coefficient of variation (CV), and linear regression. This allows the processing of images in real time during the evolution of biological experiments. Moreover, GEMA has been compared with another three representative methods such as gold standard (manual segmentation), morphological gradient, and a semi-automatic algorithm using FIJI. The experiments show promising results, due to the proposed algorithm achieving an accuracy above 90% and a lower computation time because it requires on average 1 s to process each image. This makes it suitable for image-based real-time automatization of biological lab-on-a-chip experiments.

Quantitative, traceable determination of cell viability using absorbance microscopy

Cell viability, an essential measurement for cell therapy products, lacks traceability. One of the most common cell viability tests is trypan blue dye exclusion where blue-stained cells are counted via brightfield imaging. Typically, live and dead cells are classified based on their pixel intensities which may vary arbitrarily making it difficult to compare results. Herein, a traceable absorbance microscopy method to determine the intracellular uptake of trypan blue is demonstrated. The intensity pixels of the brightfield images are converted to absorbance images which are used to calculate moles of trypan blue per cell. Trypan blue cell viability measurements, where trypan blue content in each cell is quantified, enable traceable live-dead classifications. To implement the absorbance microscopy method, we developed an open-source AbsorbanceQ application that generates quantitative absorbance images. The validation of absorbance microscopy is demonstrated using neutral density filters. Results from four different microscopes demonstrate a mean absolute deviation of 3% from the expected optical density values. When assessing trypan blue-stained Jurkat cells, the difference in intracellular uptake of trypan blue in heat-shock-killed cells using two different microscopes is 3.8%. Cells killed with formaldehyde take up ~50% less trypan blue as compared to the heat-shock-killed cells, suggesting that the killing mechanism affects trypan blue uptake. In a test mixture of approximately 50% live and 50% dead cells, 53% of cells were identified as dead (±6% standard deviation). Finally, to mimic batches of low-viability cells that may be encountered during a cell manufacturing process, viability was assessed for cells that were 1) overgrown in the cell culture incubator for five days or 2) incubated in DPBS at room temperature for five days. Instead of making live-dead classifications using arbitrary intensity values, absorbance imaging yields traceable units of moles that can be compared, which is useful for assuring quality for biomanufacturing processes.

Cells/colony motion of oral keratinocytes determined by non-invasive and quantitative measurement using optical flow predicts epithelial regenerative capacity

Cells/colony motion determined by non-invasive, quantitative measurements using the optical flow (OF) algorithm can indicate the oral keratinocyte proliferative capacity in early-phase primary cultures. This study aimed to determine a threshold for the cells/colony motion index to detect substandard cell populations in a subsequent subculture before manufacturing a tissue-engineered oral mucosa graft and to investigate the correlation with the epithelial regenerative capacity. The distinctive proliferating pattern of first-passage [passage 1 (p1)] cells reveals the motion of p1 cells/colonies, which can be measured in a non-invasive, quantitative manner using OF with fewer full-screen imaging analyses and cell segmentations. Our results demonstrate that the motion index lower than 40 μm/h reflects cellular damages by experimental metabolic challenges although this value shall only apply in case of our culture system. Nonetheless, the motion index can be used as the threshold to determine the quality of cultured cells while it may be affected by any different culture conditions. Because the p1 cells/colony motion index is correlated with epithelial regenerative capacity, it is a reliable index for quality control of oral keratinocytes.

ChipSeg: An Automatic Tool to Segment Bacterial and Mammalian Cells Cultured in Microfluidic Devices

Extracting quantitative measurements from time-lapse images is necessary in external feedback control applications, where segmentation results are used to inform control algorithms. We describe ChipSeg, a computational tool that segments bacterial and mammalian cells cultured in microfluidic devices and imaged by time-lapse microscopy, which can be used also in the context of external feedback control. The method is based on thresholding and uses the same core functions for both cell types. It allows us to segment individual cells in high cell density microfluidic devices, to quantify fluorescent protein expression over a time-lapse experiment, and to track individual mammalian cells. ChipSeg enables robust segmentation in external feedback control experiments and can be easily customized for other experimental settings and research aims.

Diagnosis of Glioma Molecular Markers by Terahertz Technologies

This review considers glioma molecular markers in brain tissues and body fluids, shows the pathways of their formation, and describes traditional methods of analysis. The most important optical properties of glioma markers in the terahertz (THz) frequency range are also presented. New metamaterial-based technologies for molecular marker detection at THz frequencies are discussed. A variety of machine learning methods, which allow the marker detection sensitivity and differentiation of healthy and tumor tissues to be improved with the aid of THz tools, are considered. The actual results on the application of THz techniques in the intraoperative diagnosis of brain gliomas are shown. THz technologies’ potential in molecular marker detection and defining the boundaries of the glioma’s tissue is discussed.

Deep learning for cellular image analysis

Recent advances in computer vision and machine learning underpin a collection of algorithms with an impressive ability to decipher the content of images. These deep learning algorithms are being applied to biological images and are transforming the analysis and interpretation of imaging data. These advances are positioned to render difficult analyses routine and to enable researchers to carry out new, previously impossible experiments. Here we review the intersection between deep learning and cellular image analysis and provide an overview of both the mathematical mechanics and the programming frameworks of deep learning that are pertinent to life scientists. We survey the field's progress in four key applications: image classification, image segmentation, object tracking, and augmented microscopy. Last, we relay our labs' experience with three key aspects of implementing deep learning in the laboratory: annotating training data, selecting and training a range of neural network architectures, and deploying solutions. We also highlight existing datasets and implementations for each surveyed application.

Segmentation and Modelling of the Nuclear Envelope of HeLa Cells Imaged with Serial Block Face Scanning Electron Microscopy

This paper describes an unsupervised algorithm, which segments the nuclear envelope of HeLa cells imaged by Serial Block Face Scanning Electron Microscopy. The algorithm exploits the variations of pixel intensity in different cellular regions by calculating edges, which are then used to generate superpixels. The superpixels are morphologically processed and those that correspond to the nuclear region are selected through the analysis of size, position, and correspondence with regions detected in neighbouring slices. The nuclear envelope is segmented from the nuclear region. The three-dimensional segmented nuclear envelope is then modelled against a spheroid to create a two-dimensional (2D) surface. The 2D surface summarises the complex 3D shape of the nuclear envelope and allows the extraction of metrics that may be relevant to characterise the nature of cells. The algorithm was developed and validated on a single cell and tested in six separate cells, each with 300 slices of 2000 × 2000 pixels. Ground truth was available for two of these cells, i.e., 600 hand-segmented slices. The accuracy of the algorithm was evaluated with two similarity metrics: Jaccard Similarity Index and Mean Hausdorff distance. Jaccard values of the first/second segmentation were 93%/90% for the whole cell, and 98%/94% between slices 75 and 225, as the central slices of the nucleus are more regular than those on the extremes. Mean Hausdorff distances were 9/17 pixels for the whole cells and 4/13 pixels for central slices. One slice was processed in approximately 8 s and a whole cell in 40 min. The algorithm outperformed active contours in both accuracy and time.

Automated sensing and splitting of stem cell colonies on microraft arrays

Human induced pluripotent stem cells (hiPSCs) are widely used for disease modeling, tissue engineering, and clinical applications. Although the development of new disease-relevant or customized hiPSC lines is of high importance, current automated hiPSC isolation technologies rely largely on the fluorescent labeling of cells, thus limiting the cell line development from many applications. The objective of this research was to develop a platform for high-throughput hiPSC cytometry and splitting that utilized a label-free cell sensing approach. An image analysis pipeline utilizing background subtraction and standard deviation projections was implemented to detect hiPSC colonies from bright-field microscopy data. The pipeline was incorporated into an automated microscopy system coupling quad microraft cell-isolation arrays, computer-based vision, and algorithms for smart decision making and cell sorting. The pipeline exhibited a hiPSC detection specificity of 98% and a sensitivity of 88%, allowing for the successful tracking of growth for hundreds of microcolonies over 7 days. The automated platform split 170 mother colonies from a microarray within 80 min, and the harvested daughter biopsies were expanded into viable hiPSC colonies suitable for downstream assays, such as polymerase chain reaction (PCR) or continued culture. Transmitted light microscopy offers an alternative, label-free modality for isolating hiPSCs, yet its low contrast and specificity for adherent cells remain a challenge for automation. This novel approach to label-free sensing and microcolony subsampling with the preservation of the mother colony holds the potential for hiPSC colony screening based on a wide range of properties including those measurable only by a cell destructive assay.

Three-Dimensional Segmentation and Reconstruction of Neuronal Nuclei in Confocal Microscopic Images

The detailed architectural examination of the neuronal nuclei in any brain region, using confocal microscopy, requires quantification of fluorescent signals in three-dimensional stacks of confocal images. An essential prerequisite to any quantification is the segmentation of the nuclei which are typically tightly packed in the tissue, the extreme being the hippocampal dentate gyrus (DG), in which nuclei frequently appear to overlap due to limitations in microscope resolution. Segmentation in DG is a challenging task due to the presence of a significant amount of image artifacts and densely packed nuclei. Accordingly, we established an algorithm based on continuous boundary tracing criterion aiming to reconstruct the nucleus surface and to separate the adjacent nuclei. The presented algorithm neither uses a pre-built nucleus model, nor performs image thresholding, which makes it robust against variations in image intensity and poor contrast. Further, the reconstructed surface is used to study morphology and spatial arrangement of the nuclear interior. The presented method is generally dedicated to segmentation of crowded, overlapping objects in 3D space. In particular, it allows us to study quantitatively the architecture of the neuronal nucleus using confocal-microscopic approach.

Practical Considerations in Particle and Object Tracking and Analysis

The rapid advancement of live-cell imaging technologies has enabled biologists to generate high-dimensional data to follow biological movement at the microscopic level. Yet, the "perceived" ease of use of modern microscopes has led to challenges whereby sub-optimal data are commonly generated that cannot support quantitative tracking and analysis as a result of various ill-advised decisions made during image acquisition. Even optimally acquired images often require further optimization through digital processing before they can be analyzed. In writing this article, we presume our target audience to be biologists with a foundational understanding of digital image acquisition and processing, who are seeking to understand the essential steps for particle/object tracking experiments. It is with this targeted readership in mind that we review the basic principles of image-processing techniques as well as analysis strategies commonly used for tracking experiments. We conclude this technical survey with a discussion of how movement behavior can be mathematically modeled and described. © 2019 by John Wiley & Sons, Inc.

Separating Touching Cells Using Pixel Replicated Elliptical Shape Models

One of the most important and error-prone tasks in biological image analysis is the segmentation of touching or overlapping cells. Particularly for optical microscopy, including transmitted light and confocal fluorescence microscopy, there is often no consistent discriminative information to separate cells that touch or overlap. It is desired to partition touching foreground pixels into cells using the binary threshold image information only, and optionally incorporating gradient information. The most common approaches for segmenting touching and overlapping cells in these scenarios are based on the watershed transform. We describe a new approach called pixel replication for the task of segmenting elliptical objects that touch or overlap. Pixel replication uses the image Euclidean distance transform in combination with Gaussian mixture models to better exploit practically effective optimization for delineating objects with elliptical decision boundaries. Pixel replication improves significantly on commonly used methods based on watershed transforms, or based on fitting Gaussian mixtures directly to the thresholded image data. Pixel replication works equivalently on both 2-D and 3-D image data, and naturally combines information from multi-channel images. The accuracy of the proposed technique is measured using both the segmentation accuracy on simulated ellipse data and the tracking accuracy on validated stem cell tracking results extracted from hundreds of live-cell microscopy image sequences. Pixel replication is shown to be significantly more accurate compared with other approaches. Variance relationships are derived, allowing a more practically effective Gaussian mixture model to extract cell boundaries for data generated from the threshold image using the uniform elliptical distribution and from the distance transform image using the triangular elliptical distribution.

Strategies for robust and accurate experimental approaches to quantify nanomaterial bioaccumulation across a broad range of organisms

One of the key components for environmental risk assessment of engineered nanomaterials (ENMs) is data on bioaccumulation potential. Accurately measuring bioaccumulation can be critical for regulatory decision making regarding material hazard and risk, and for understanding the mechanism of toxicity. This perspective provides expert guidance for performing ENM bioaccumulation measurements across a broad range of test organisms and species. To accomplish this aim, we critically evaluated ENM bioaccumulation within three categories of organisms: single-celled species, multicellular species excluding plants, and multicellular plants. For aqueous exposures of suspended single-celled and small multicellular species, it is critical to perform a robust procedure to separate suspended ENMs and small organisms to avoid overestimating bioaccumulation. For many multicellular organisms, it is essential to differentiate between the ENMs adsorbed to external surfaces or in the digestive tract and the amount absorbed across epithelial tissues. For multicellular plants, key considerations include how exposure route and the role of the rhizosphere may affect the quantitative measurement of uptake, and that the efficiency of washing procedures to remove loosely attached ENMs to the roots is not well understood. Within each organism category, case studies are provided to illustrate key methodological considerations for conducting robust bioaccumulation experiments for different species within each major group. The full scope of ENM bioaccumulation measurements and interpretations are discussed including conducting the organism exposure, separating organisms from the ENMs in the test media after exposure, analytical methods to quantify ENMs in the tissues or cells, and modeling the ENM bioaccumulation results. One key finding to improve bioaccumulation measurements was the critical need for further analytical method development to identify and quantify ENMs in complex matrices. Overall, the discussion, suggestions, and case studies described herein will help improve the robustness of ENM bioaccumulation studies.

Quantitative morphometric analysis of adult teleost fish by X-ray computed tomography

Vertebrate models provide indispensable paradigms to study development and disease. Their analysis requires a quantitative morphometric study of the body, organs and tissues. This is often impeded by pigmentation and sample size. X-ray micro-computed tomography (micro-CT) allows high-resolution volumetric tissue analysis, largely independent of sample size and transparency to visual light. Importantly, micro-CT data are inherently quantitative. We report a complete pipeline of high-throughput 3D data acquisition and image analysis, including tissue preparation and contrast enhancement for micro-CT imaging down to cellular resolution, automated data processing and organ or tissue segmentation that is applicable to comparative 3D morphometrics of small vertebrates. Applied to medaka fish, we first create an annotated anatomical atlas of the entire body, including inner organs as a quantitative morphological description of an adult individual. This atlas serves as a reference model for comparative studies. Using isogenic medaka strains we show that comparative 3D morphometrics of individuals permits identification of quantitative strain-specific traits. Thus, our pipeline enables high resolution morphological analysis as a basis for genotype-phenotype association studies of complex genetic traits in vertebrates.

Automatic Quantitative Segmentation of Myotubes Reveals Single-cell Dynamics of S6 Kinase Activation

Automatic cell segmentation is a powerful method for quantifying signaling dynamics at single-cell resolution in live cell fluorescence imaging. Segmentation methods for mononuclear and round shape cells have been developed extensively. However, a segmentation method for elongated polynuclear cells, such as differentiated C2C12 myotubes, has yet to be developed. In addition, myotubes are surrounded by undifferentiated reserve cells, making it difficult to identify background regions and subsequent quantification. Here we developed an automatic quantitative segmentation method for myotubes using watershed segmentation of summed binary images and a two-component Gaussian mixture model. We used time-lapse fluorescence images of differentiated C2C12 cells stably expressing Eevee-S6K, a fluorescence resonance energy transfer (FRET) biosensor of S6 kinase (S6K). Summation of binary images enhanced the contrast between myotubes and reserve cells, permitting detection of a myotube and a myotube center. Using a myotube center instead of a nucleus, individual myotubes could be detected automatically by watershed segmentation. In addition, a background correction using the two-component Gaussian mixture model permitted automatic signal intensity quantification in individual myotubes. Thus, we provide an automatic quantitative segmentation method by combining automatic myotube detection and background correction. Furthermore, this method allowed us to quantify S6K activity in individual myotubes, demonstrating that some of the temporal properties of S6K activity such as peak time and half-life of adaptation show different dose-dependent changes of insulin between cell population and individuals.Key words: time lapse images, cell segmentation, fluorescence resonance energy transfer, C2C12, myotube.

Modeling, validation and verification of three-dimensional cell-scaffold contacts from terabyte-sized images

Background

Cell-scaffold contact measurements are derived from pairs of co-registered volumetric fluorescent confocal laser scanning microscopy (CLSM) images (z-stacks) of stained cells and three types of scaffolds (i.e., spun coat, large microfiber, and medium microfiber). Our analysis of the acquired terabyte-sized collection is motivated by the need to understand the nature of the shape dimensionality (1D vs 2D vs 3D) of cell-scaffold interactions relevant to tissue engineers that grow cells on biomaterial scaffolds.

Results

We designed five statistical and three geometrical contact models, and then down-selected them to one from each category using a validation approach based on physically orthogonal measurements to CLSM. The two selected models were applied to 414 z-stacks with three scaffold types and all contact results were visually verified. A planar geometrical model for the spun coat scaffold type was validated from atomic force microscopy images by computing surface roughness of 52.35 nm ±31.76 nm which was 2 to 8 times smaller than the CLSM resolution. A cylindrical model for fiber scaffolds was validated from multi-view 2D scanning electron microscopy (SEM) images. The fiber scaffold segmentation error was assessed by comparing fiber diameters from SEM and CLSM to be between 0.46% to 3.8% of the SEM reference values. For contact verification, we constructed a web-based visual verification system with 414 pairs of images with cells and their segmentation results, and with 4968 movies with animated cell, scaffold, and contact overlays. Based on visual verification by three experts, we report the accuracy of cell segmentation to be 96.4% with 94.3% precision, and the accuracy of cell-scaffold contact for a statistical model to be 62.6% with 76.7% precision and for a geometrical model to be 93.5% with 87.6% precision.

Conclusions

The novelty of our approach lies in (1) representing cell-scaffold contact sites with statistical intensity and geometrical shape models, (2) designing a methodology for validating 3D geometrical contact models and (3) devising a mechanism for visual verification of hundreds of 3D measurements. The raw and processed data are publicly available from https://isg.nist.gov/deepzoomweb/data/ together with the web -based verification system.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-017-1928-x) contains supplementary material, which is available to authorized users.

A novel measure and significance testing in data analysis of cell image segmentation

Background

Cell image segmentation (CIS) is an essential part of quantitative imaging of biological cells. Designing a performance measure and conducting significance testing are critical for evaluating and comparing the CIS algorithms for image-based cell assays in cytometry. Many measures and methods have been proposed and implemented to evaluate segmentation methods. However, computing the standard errors (SE) of the measures and their correlation coefficient is not described, and thus the statistical significance of performance differences between CIS algorithms cannot be assessed.

Results

We propose the total error rate (TER), a novel performance measure for segmenting all cells in the supervised evaluation. The TER statistically aggregates all misclassification error rates (MER) by taking cell sizes as weights. The MERs are for segmenting each single cell in the population. The TER is fully supported by the pairwise comparisons of MERs using 106 manually segmented ground-truth cells with different sizes and seven CIS algorithms taken from ImageJ. Further, the SE and 95% confidence interval (CI) of TER are computed based on the SE of MER that is calculated using the bootstrap method. An algorithm for computing the correlation coefficient of TERs between two CIS algorithms is also provided. Hence, the 95% CI error bars can be used to classify CIS algorithms. The SEs of TERs and their correlation coefficient can be employed to conduct the hypothesis testing, while the CIs overlap, to determine the statistical significance of the performance differences between CIS algorithms.

Conclusions

A novel measure TER of CIS is proposed. The TER’s SEs and correlation coefficient are computed. Thereafter, CIS algorithms can be evaluated and compared statistically by conducting the significance testing.

Characterising live cell behaviour: Traditional label-free and quantitative phase imaging approaches

Label-free imaging uses inherent contrast mechanisms within cells to create image contrast without introducing dyes/labels, which may confound results. Quantitative phase imaging is label-free and offers higher content and contrast compared to traditional techniques. High-contrast images facilitate generation of individual cell metrics via more robust segmentation and tracking, enabling formation of a label-free dynamic phenotype describing cell-to-cell heterogeneity and temporal changes. Compared to population-level averages, individual cell-level dynamic phenotypes have greater power to differentiate between cellular responses to treatments, which has clinical relevance e.g. in the treatment of cancer. Furthermore, as the data is obtained label-free, the same cells can be used for further assays or expansion, of potential benefit for the fields of regenerative and personalised medicine.

Deep Learning Automates the Quantitative Analysis of Individual Cells in Live-Cell Imaging Experiments

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.

Automated Measurement of Cobblestone Morphology for Characterizing Stem Cell Derived Retinal Pigment Epithelial Cell Cultures

PURPOSE

Assessing the morphologic properties of cells in microscopy images is an important task to evaluate cell health, identity, and purity. Typically, subjective visual assessments are accomplished by an experienced researcher. This subjective human step makes transfer of the evaluation process from the laboratory to the cell manufacturing facility difficult and time consuming.

METHODS

Automated image analysis can provide rapid, objective measurements of cultured cells, greatly aiding manufacturing, regulatory, and research goals. Automated algorithms for classifying images based on appearance characteristics typically either extract features from the image and use those features for classification or use the images directly as input to the classification algorithm. In this study we have developed both feature and nonfeature extraction methods for automatically measuring "cobblestone" structure in human retinal pigment epithelial (RPE) cell cultures.

RESULTS

A new approach using image compression combined with a Kolmogorov complexity-based distance metric enables robust classification of microscopy images of RPE cell cultures. The automated measurements corroborate determinations made by experienced cell biologists. We have also developed an approach for using steerable wavelet filters for extracting features to characterize the individual cellular junctions.

CONCLUSIONS

Two image analysis techniques enable robust and accurate characterization of the cobblestone morphology that is indicative of viable RPE cultures for therapeutic applications.