Understanding the phase contrast optics to restore artifact-free microscopy images for segmentation

Single-image phase retrieval for off-the-shelf Zernike phase-contrast microscopes

Quantitative phase imaging (QPI), such as digital holography, is considered a promising tool in the field of life science due to its noninvasive and quantitative visualization capabilities without the need for fluorescence labeling. However, the popularity of QPI systems is limited due to the cost and complexity of their hardware. In contrast, Zernike phase-contrast microscopy (ZPM) has been widely used in practical scenarios but has not been categorized as QPI, owing to halo and shade-off artifacts and the weak phase condition. Here, we present a single-image phase retrieval method for ZPM that addresses these issues without requiring hardware modifications. By employing a rigorous physical model of ZPM and a gradient descent algorithm for its inversion, we achieve single-shot QPI with an off-the-shelf ZPM system. Our approach is validated in simulations and experiments, demonstrating QPI of a polymer microbead and biological cells. The quantitative nature of our method for single-cell imaging is confirmed through comparisons with observations from an established QPI technique conducted through digital holography. This study paves the way for transforming non-QPI ZPM systems into QPI systems.

Deep learning to overcome Zernike phase-contrast nanoCT artifacts for automated micro-nano porosity segmentation in bone

Bone material contains a hierarchical network of micro- and nano-cavities and channels, known as the lacuna-canalicular network (LCN), that is thought to play an important role in mechanobiology and turnover. The LCN comprises micrometer-sized lacunae, voids that house osteocytes, and submicrometer-sized canaliculi that connect bone cells. Characterization of this network in three dimensions is crucial for many bone studies. To quantify X-ray Zernike phase-contrast nanotomography data, deep learning is used to isolate and assess porosity in artifact-laden tomographies of zebrafish bones. A technical solution is proposed to overcome the halo and shade-off domains in order to reliably obtain the distribution and morphology of the LCN in the tomographic data. Convolutional neural network (CNN) models are utilized with increasing numbers of images, repeatedly validated by `error loss' and `accuracy' metrics. U-Net and Sensor3D CNN models were trained on data obtained from two different synchrotron Zernike phase-contrast transmission X-ray microscopes, the ANATOMIX beamline at SOLEIL (Paris, France) and the P05 beamline at PETRA III (Hamburg, Germany). The Sensor3D CNN model with a smaller batch size of 32 and a training data size of 70 images showed the best performance (accuracy 0.983 and error loss 0.032). The analysis procedures, validated by comparison with human-identified ground-truth images, correctly identified the voids within the bone matrix. This proposed approach may have further application to classify structures in volumetric images that contain non-linear artifacts that degrade image quality and hinder feature identification.

Roadmap on Label-Free Super-Resolution Imaging

Label-free super-resolution (LFSR) imaging relies on light-scattering processes in nanoscale objects without a need for fluorescent (FL) staining required in super-resolved FL microscopy. The objectives of this Roadmap are to present a comprehensive vision of the developments, the state-of-the-art in this field, and to discuss the resolution boundaries and hurdles which need to be overcome to break the classical diffraction limit of the LFSR imaging. The scope of this Roadmap spans from the advanced interference detection techniques, where the diffraction-limited lateral resolution is combined with unsurpassed axial and temporal resolution, to techniques with true lateral super-resolution capability which are based on understanding resolution as an information science problem, on using novel structured illumination, near-field scanning, and nonlinear optics approaches, and on designing superlenses based on nanoplasmonics, metamaterials, transformation optics, and microsphere-assisted approaches. To this end, this Roadmap brings under the same umbrella researchers from the physics and biomedical optics communities in which such studies have often been developing separately. The ultimate intent of this paper is to create a vision for the current and future developments of LFSR imaging based on its physical mechanisms and to create a great opening for the series of articles in this field.

An introduction to representation learning for single-cell data analysis

Single-cell-resolved systems biology methods, including omics- and imaging-based measurement modalities, generate a wealth of high-dimensional data characterizing the heterogeneity of cell populations. Representation learning methods are routinely used to analyze these complex, high-dimensional data by projecting them into lower-dimensional embeddings. This facilitates the interpretation and interrogation of the structures, dynamics, and regulation of cell heterogeneity. Reflecting their central role in analyzing diverse single-cell data types, a myriad of representation learning methods exist, with new approaches continually emerging. Here, we contrast general features of representation learning methods spanning statistical, manifold learning, and neural network approaches. We consider key steps involved in representation learning with single-cell data, including data pre-processing, hyperparameter optimization, downstream analysis, and biological validation. Interdependencies and contingencies linking these steps are also highlighted. This overview is intended to guide researchers in the selection, application, and optimization of representation learning strategies for current and future single-cell research applications.

BNP-Track: A framework for superresolved tracking

Assessing dynamic processes at single molecule scales is key toward capturing life at the level of its molecular actors. Widefield superresolution methods, such as STORM, PALM, and PAINT, provide nanoscale localization accuracy, even when distances between fluorescently labeled single molecules ("emitters") fall below light's diffraction limit. However, as these superresolution methods rely on rare photophysical events to distinguish emitters from both each other and background, they are largely limited to static samples. In contrast, here we leverage spatiotemporal correlations of dynamic widefield imaging data to extend superresolution to simultaneous multiple emitter tracking without relying on photodynamics even as emitter distances from one another fall below the diffraction limit. We simultaneously determine emitter numbers and their tracks (localization and linking) with the same localization accuracy per frame as widefield superresolution does for immobilized emitters under similar imaging conditions (≈50nm). We demonstrate our results for both in cellulo data and, for benchmarking purposes, on synthetic data. To this end, we avoid the existing tracking paradigm relying on completely or partially separating the tasks of emitter number determination, localization of each emitter, and linking emitter positions across frames. Instead, we develop a fully joint posterior distribution over the quantities of interest, including emitter tracks and their total, otherwise unknown, number within the Bayesian nonparametric paradigm. Our posterior quantifies the full uncertainty over emitter numbers and their associated tracks propagated from origins including shot noise and camera artefacts, pixelation, stochastic background, and out-of-focus motion. Finally, it remains accurate in more crowded regimes where alternative tracking tools cannot be applied.

Phase Contrast Image Restoration by Formulating Its Imaging Principle and Reversing the Formulation With Deep Neural Networks

Phase contrast microscopy, as a noninvasive imaging technique, has been widely used to monitor the behavior of transparent cells without staining or altering them. Due to the optical principle of the specifically-designed microscope, phase contrast microscopy images contain artifacts such as halo and shade-off which hinder the cell segmentation and detection tasks. Some previous works developed simplified computational imaging models for phase contrast microscopes by linear approximations and convolutions. The approximated models do not exactly reflect the imaging principle of the phase contrast microscope and accordingly the image restoration by solving the corresponding deconvolution process is not perfect. In this paper, we revisit the optical principle of the phase contrast microscope to precisely formulate its imaging model without any approximation. Based on this model, we propose an image restoration procedure by reversing this imaging model with a deep neural network, instead of mathematically deriving the inverse operator of the model which is technically impossible. Extensive experiments are conducted to demonstrate the superiority of the newly derived phase contrast microscopy imaging model and the power of the deep neural network on modeling the inverse imaging procedure. Moreover, the restored images enable that high quality cell segmentation task can be easily achieved by simply thresholding methods. Implementations of this work are publicly available at https://github.com/LiangHann/Phase-Contrast-Microscopy-Image-Restoration.

Magnetically Actuated Hydrogel Stamping-Assisted Cellular Mechanical Analyzer for Stored Blood Quality Detection

Cellular mechanical property analysis reflecting the physiological and pathological states of cells plays a crucial role in assessing the quality of stored blood. However, its complex equipment needs, operation difficulty, and clogging issues hinder automated and rapid biomechanical testing. Here, we propose a promising biosensor assisted by magnetically actuated hydrogel stamping to fulfill it. The flexible magnetic actuator triggers the collective deformation of multiple cells in the light-cured hydrogel, and it allows for on-demand bioforce stimulation with the advantages of portability, cost-effectiveness, and simplicity of operation. The magnetically manipulated cell deformation processes are captured by the integrated miniaturized optical imaging system, and the cellular mechanical property parameters are extracted from the captured images for real-time analysis and intelligent sensing. In this work, 30 clinical blood samples with different storage durations (<14 days and >14 days) were tested. A deviation of 3.3% in the differentiation of blood storage durations by this system compared to physician annotation demonstrated its feasibility. This system should broaden the application of cellular mechanical assays in diverse clinical settings.

Analysis of Morphological Changes in the Nucleus and Vacuoles of Acanthamoeba castellanii following Giant Virus Infection

Acanthamoeba castellanii medusavirus is a member of the phylum Nucleocytoviricota, also known as giant viruses, and has a unique strategy of infecting Acanthamoeba castellanii and replicating viral genes in the host nucleus. Here, we show time series changes in the intracellular morphology, including the nucleus, of host cells infected with four types of giant viruses, including medusavirus, using time-lapse phase-contrast microscopy and image analysis. We updated our phase-contrast-based kinetic analysis algorithm for amoebae (PKA3) to use multiple microscopic images with different focus positions to allow a more detailed analysis of their intracellular structures. Image analysis using PKA3 revealed that as medusavirus infection progressed, the host nucleus increased in size and the number of vacuoles decreased. In addition, infected host cells are known to become smaller and rounder at later stages of infection, but here they were found to be larger than uninfected cells at earlier stages. These results suggested that the propagation mechanism of medusavirus includes the formation of empty virus particles in the host cytoplasm, packaging of the viral genome replicated in the host nucleus, and then the release of viral particles. IMPORTANCE In this study, we quantitatively revealed how long the increase in host cell size or the increase in host nucleus size occurs after infection with giant viruses, especially medusavirus. To understand the underlying mechanism, we performed image analysis and determined that the host cell size increased at approximately 6 h postinfection (hpi) and the host nucleus enlarged at approximately 22 hpi, pointing to the importance of biochemical experiments. In addition, we showed that the intracellular structures could be quantitatively analyzed using multiple phase-contrast microscopy images with different focus positions at the same time point. Hence, morphological analyses of intracellular structures using phase-contrast microscopy, which have wide applications in live-cell observations, may be useful in studying various organisms that infect or are symbiotic with A. castellanii.

Synthetic Micrographs of Bacteria (SyMBac) allows accurate segmentation of bacterial cells using deep neural networks

BACKGROUND

Deep-learning-based image segmentation models are required for accurate processing of high-throughput timelapse imaging data of bacterial cells. However, the performance of any such model strictly depends on the quality and quantity of training data, which is difficult to generate for bacterial cell images. Here, we present a novel method of bacterial image segmentation using machine learning models trained with Synthetic Micrographs of Bacteria (SyMBac).

RESULTS

We have developed SyMBac, a tool that allows for rapid, automatic creation of arbitrary amounts of training data, combining detailed models of cell growth, physical interactions, and microscope optics to create synthetic images which closely resemble real micrographs, and is capable of training accurate image segmentation models. The major advantages of our approach are as follows: (1) synthetic training data can be generated virtually instantly and on demand; (2) these synthetic images are accompanied by perfect ground truth positions of cells, meaning no data curation is required; (3) different biological conditions, imaging platforms, and imaging modalities can be rapidly simulated, meaning any change in one's experimental setup no longer requires the laborious process of manually generating new training data for each change. Deep-learning models trained with SyMBac data are capable of analysing data from various imaging platforms and are robust to drastic changes in cell size and morphology. Our benchmarking results demonstrate that models trained on SyMBac data generate more accurate cell identifications and precise cell masks than those trained on human-annotated data, because the model learns the true position of the cell irrespective of imaging artefacts. We illustrate the approach by analysing the growth and size regulation of bacterial cells during entry and exit from dormancy, which revealed novel insights about the physiological dynamics of cells under various growth conditions.

CONCLUSIONS

The SyMBac approach will help to adapt and improve the performance of deep-learning-based image segmentation models for accurate processing of high-throughput timelapse image data.

Machine-Learning-Aided Quantification of Area Coverage of Adherent Cells from Phase-Contrast Images

The advances in machine learning (ML) software availability, efficiency, and friendliness, combined with the increase in the computation power of personal computers, are harnessed to rapidly and (relatively) effortlessly analyze time-lapse image series of adherent cell cultures, taken with phase-contrast microscopy (PCM). Since PCM is arguably the most widely used technique to visualize adherent cells in a label-free, noninvasive, and nondisruptive manner, the ability to easily extract quantitative information on the area covered by cells, should provide a valuable tool for investigation. We demonstrate two cases, in one we monitor the shrinking of cells in response to a toxicant, and in the second we measure the proliferation curve of mesenchymal stem cells (MSCs).

Ingrained: An Automated Framework for Fusing Atomic-Scale Image Simulations into Experiments

To fully leverage the power of image simulation to corroborate and explain patterns and structures in atomic resolution microscopy, an initial correspondence between the simulation and experimental image must be established at the outset of further high accuracy simulations or calculations. Furthermore, if simulation is to be used in context of highly automated processes or high-throughput optimization, the process of finding this correspondence itself must be automated. In this work, "ingrained," an open-source automation framework which solves for this correspondence and fuses atomic resolution image simulations into the experimental images to which they correspond, is introduced. Herein, the overall "ingrained" workflow, focusing on its application to interface structure approximations, and the development of an experimentally rationalized forward model for scanning tunneling microscopy simulation are described.

Wide-Field Mid-Infrared Hyperspectral Imaging by Snapshot Phase Contrast Measurement of Optothermal Excitation

Vibrational microscopy methods based on Raman scattering or infrared absorption provide a label-free approach for chemical-contrast imaging, but employ point-by-point scanning and impose a compromise between the imaging speed and field-of-view (FOV). Optothermal microscopy has been proposed as a promising imaging modality to avoid this compromise, although at restrictively small FOVs capable of imaging only few cells. Here, we present wide-field optothermal mid-infrared microscopy (WOMiM) for wide-field chemical-contrast imaging based on snapshot pump–probe detection of optothermal signal, using a custom-made condenser-free phase contrast microscopy to capture the phase change of samples after mid-infrared irradiation. We achieved chemical contrast for FOVs up to 180 μm in diameter, yielding 10-fold larger imaging areas than the state-of-the-art, at imaging speeds of 1 ms/frame. The maximum possible imaging speed of WOMiM was determined by the relaxation time of optothermal heat, measured to be 32.8 μs in water, corresponding to a frame rate of ∼30 kHz. This proof-of-concept demonstrates that vibrational imaging can be achieved at an unprecedented imaging speed and large FOV with the potential to significantly facilitate label-free imaging of cellular dynamics.

Kinetic Analysis of Acanthamoeba castellanii Infected with Giant Viruses Quantitatively Revealed Process of Morphological and Behavioral Changes in Host Cells

Most virus-infected cells show morphological and behavioral changes, which are called cytopathic effects. Acanthamoeba castellanii, an abundant, free-living protozoan, serves as a laboratory host for some viruses of the phylum Nucleocytoviricota-the giant viruses. Many of these viruses cause cell rounding in the later stages of infection in the host cells. Here, we show the changes that lead to cell rounding in the host cells through time-lapse microscopy and image analysis. Time-lapse movies of A. castellanii cells infected with Mimivirus shirakomae, kyotovirus, medusavirus, or Pandoravirus japonicus were generated using a phase-contrast microscope. We updated our phase-contrast-based kinetic analysis algorithm for amoebae (PKA3) and used it to analyze these time-lapse movies. Image analysis revealed that the process leading to cell rounding varies among the giant viruses; for example, M. shirakomae infection did not cause changes for some time after the infection, kyotovirus infection caused an early decrease in the number of cells with typical morphologies, and medusavirus and P. japonicus infection frequently led to the formation of intercellular bridges and rotational behavior of host cells. These results suggest that in the case of giant viruses, the putative reactions of host cells against infection and the putative strategies of virus spread are diverse. IMPORTANCE Quantitative analysis of the infection process is important for a better understanding of viral infection strategies and virus-host interactions. Here, an image analysis of the phase-contrast time-lapse movies displayed quantitative differences in the process of cytopathic effects due to the four giant viruses in Acanthamoeba castellanii, which were previously unclear. It was revealed that medusavirus and Pandoravirus japonicus infection led to the formation of a significant number of elongated particles related to intercellular bridges, emphasizing the importance of research on the interaction of viruses with host cell nuclear function. Mimivirus shirakomae infection did not cause any changes in the host cells initially, so it is thought that the infected cells can actively move and spread over a wider area, emphasizing the importance of observation in a wider area and analysis of infection efficiency. These results suggest that a kinetic analysis using the phase-contrast-based kinetic analysis algorithm for amoebae (PKA3) reveals the infection strategies of each giant virus.

Identification of pollen taxa by different microscopy techniques

Melissopalynology is an important analytical method to identify botanical origin of honey. Pollen grain recognition is commonly performed by visual inspection by a trained person. An alternative method for visual inspection is automated pollen analysis based on the image analysis technique. Image analysis transfers visual information to mathematical descriptions. In this work, the suitability of three microscopic techniques for automatic analysis of pollen grains was studied. 2D and 3D morphological characteristics, textural and colour features, and extended depth of focus characteristics were used for the pollen discrimination. In this study, 7 botanical taxa and a total of 2482 pollen grains were evaluated. The highest correct classification rate of 93.05% was achieved using the phase contrast microscopy, followed by the dark field microscopy reaching 91.02%, and finally by the light field microscopy reaching 88.88%. The most significant discriminant characteristics were morphological (2D and 3D) and colour characteristics. Our results confirm the potential of using automatic pollen analysis to discriminate pollen taxa in honey. This work provides the basis for further research where the taxa dataset will be increased, and new descriptors will be studied.

Advances in sperm analysis: techniques, discoveries and applications

Infertility affects one in six couples worldwide, and fertility continues to deteriorate globally, partly owing to a decline in semen quality. Sperm analysis has a central role in diagnosing and treating male factor infertility. Many emerging techniques, such as digital holography, super-resolution microscopy and next-generation sequencing, have been developed that enable improved analysis of sperm motility, morphology and genetics to help overcome limitations in accuracy and consistency, and improve sperm selection for infertility treatment. These techniques have also improved our understanding of fundamental sperm physiology by enabling discoveries in sperm behaviour and molecular structures. Further progress in sperm analysis and integrating these techniques into laboratories and clinics requires multidisciplinary collaboration, which will increase discovery and improve clinical outcomes.

Weakly supervised cell instance segmentation under various conditions

Cell instance segmentation is important in biomedical research. For living cell analysis, microscopy images are captured under various conditions (e.g., the type of microscopy and type of cell). Deep-learning-based methods can be used to perform instance segmentation if sufficient annotations of individual cell boundaries are prepared as training data. Generally, annotations are required for each condition, which is very time-consuming and labor-intensive. To reduce the annotation cost, we propose a weakly supervised cell instance segmentation method that can segment individual cell regions under various conditions by only using rough cell centroid positions as training data. This method dramatically reduces the annotation cost compared with the standard annotation method of supervised segmentation. We demonstrated the efficacy of our method on various cell images; it outperformed several of the conventional weakly-supervised methods on average. In addition, we demonstrated that our method can perform instance cell segmentation without any manual annotation by using pairs of phase contrast and fluorescence images in which cell nuclei are stained as training data.

PySTACHIO: Python Single-molecule TrAcking stoiCHiometry Intensity and simulatiOn, a flexible, extensible, beginner-friendly and optimized program for analysis of single-molecule microscopy data

As camera pixel arrays have grown larger and faster, and optical microscopy techniques ever more refined, there has been an explosion in the quantity of data acquired during routine light microscopy. At the single-molecule level, analysis involves multiple steps and can rapidly become computationally expensive, in some cases intractable on office workstations. Complex bespoke software can present high activation barriers to entry for new users. Here, we redevelop our quantitative single-molecule analysis routines into an optimized and extensible Python program, with GUI and command-line implementations to facilitate use on local machines and remote clusters, by beginners and advanced users alike. We demonstrate that its performance is on par with previous MATLAB implementations but runs an order of magnitude faster. We tested it against challenge data and demonstrate its performance is comparable to state-of-the-art analysis platforms. We show the code can extract fluorescence intensity values for single reporter dye molecules and, using these, estimate molecular stoichiometries and cellular copy numbers of fluorescently-labeled biomolecules. It can evaluate 2D diffusion coefficients for the characteristically short single-particle tracking data. To facilitate benchmarking we include data simulation routines to compare different analysis programs. Finally, we show that it works with 2-color data and enables colocalization analysis based on overlap integration, to infer interactions between differently labelled biomolecules. By making this freely available we aim to make complex light microscopy single-molecule analysis more democratized.

Matrix-Assisted Laser Desorption Ionization Mass Spectrometry Imaging by Freeze-Spot Deposition of the Matrix

Imaging mass spectrometry has emerged as a powerful metabolite measurement approach to capture the spatial dimension of metabolite distribution in a biological sample. In matrix-assisted laser desorption ionization-mass spectrometry imaging (MALDI-MSI), deposition of the chemical-matrix onto the sample serves to simultaneously extract biomolecules to the sample surface and concurrently render the sample amenable to MALDI. However, matrix application may mobilize sample metabolites and will dictate the efficiency of matrix crystallization, together limiting the lateral resolution which may be optimally achieved by MSI. Here, we describe a matrix application technique, herein referred to as the "freeze-spot" method, conceived as a low-cost preparative approach requiring minimal amounts of chemical matrix while maintaining the spatial dimension of sample metabolites for MALDI-MSI. Matrix deposition was achieved by pipette spot application of the matrix-solubilized within a solvent solution with a freezing point above that of a chilled sample stage to which the sample section is mounted. The matrix solution freezes on contact with the sample and the solvent is removed by sublimation, leaving a fine crystalline matrix on the sample surface. Freeze-spotting is quick to perform, found particularly useful for MALDI-MSI of small sample sections, and well suited to efficient and cost-effective method development pipelines, while capable of maintaining the lateral resolution required by MSI.

Pseudo-nuclear staining of cells by deep learning improves the accuracy of automated cell counting in a label-free cellular population

Deep learning has emerged as a breakthrough tool for the segmentation of images without supporting human experts. Here, we propose an automated approach that uses deep learning to generate pseudo-nuclear staining of cells from phase contrast images. Our proposed approach, which has the feature to generate pseudo-nuclear stained images by simple DNN, showed remarkable advantages over existing approaches in the cell-detection and the detection of the relative position of cells for various cell densities, as well as in counting the exact cell numbers. Pseudo-nuclear staining of cells by deep learning will improve the accuracy of automated cell counting in a label-free cellular population on phase contrast images.

Kinetic Analysis of the Motility of Giant Virus-Infected Amoebae Using Phase-Contrast Microscopic Images

Tracking cell motility is a useful tool for the study of cell physiology and microbiology. Although phase-contrast microscopy is commonly used, the existence of optical artifacts called “halo” and “shade-off” have inhibited image analysis of moving cells. Here we show kinetic image analysis of Acanthamoeba motility using a newly developed computer program named “Phase-contrast-based Kinetic Analysis Algorithm for Amoebae (PKA3),” which revealed giant-virus-infected amoebae-specific motilities and aggregation profiles using time-lapse phase-contrast microscopic images. This program quantitatively detected the time-dependent, sequential changes in cellular number, size, shape, and direction and distance of cell motility. This method expands the potential of kinetic analysis of cultured cells using versatile phase-contrast images. Furthermore, this program could be a useful tool for investigating detailed kinetic mechanisms of cell motility, not only in virus-infected amoebae but also in other cells, including cancer cells, immune response cells, and neurons.

Automated Classification of Apoptosis in Phase Contrast Microscopy Using Capsule Network

Automatic and accurate classification of apoptosis, or programmed cell death, will facilitate cell biology research. The state-of-the-art approaches in apoptosis classification use deep convolutional neural networks (CNNs). However, these networks are not efficient in encoding the part-whole relationships, thus requiring a large number of training samples to achieve robust generalization. This paper proposes an efficient variant of capsule networks (CapsNets) as an alternative to CNNs. Extensive experimental results demonstrate that the proposed CapsNets achieve competitive performances in target cell apoptosis classification, while significantly outperforming CNNs when the number of training samples is small. To utilize temporal information within microscopy videos, we propose a recurrent CapsNet constructed by stacking a CapsNet and a bi-directional long short-term recurrent structure. Our experiments show that when considering temporal constraints, the recurrent CapsNet achieves 93.8% accuracy and makes significantly more consistent prediction than NNs.

Cell segmentation methods for label-free contrast microscopy: review and comprehensive comparison

BACKGROUND

Because of its non-destructive nature, label-free imaging is an important strategy for studying biological processes. However, routine microscopic techniques like phase contrast or DIC suffer from shadow-cast artifacts making automatic segmentation challenging. The aim of this study was to compare the segmentation efficacy of published steps of segmentation work-flow (image reconstruction, foreground segmentation, cell detection (seed-point extraction) and cell (instance) segmentation) on a dataset of the same cells from multiple contrast microscopic modalities.

RESULTS

We built a collection of routines aimed at image segmentation of viable adherent cells grown on the culture dish acquired by phase contrast, differential interference contrast, Hoffman modulation contrast and quantitative phase imaging, and we performed a comprehensive comparison of available segmentation methods applicable for label-free data. We demonstrated that it is crucial to perform the image reconstruction step, enabling the use of segmentation methods originally not applicable on label-free images. Further we compared foreground segmentation methods (thresholding, feature-extraction, level-set, graph-cut, learning-based), seed-point extraction methods (Laplacian of Gaussians, radial symmetry and distance transform, iterative radial voting, maximally stable extremal region and learning-based) and single cell segmentation methods. We validated suitable set of methods for each microscopy modality and published them online.

CONCLUSIONS

We demonstrate that image reconstruction step allows the use of segmentation methods not originally intended for label-free imaging. In addition to the comprehensive comparison of methods, raw and reconstructed annotated data and Matlab codes are provided.

Quantitative Determination of Cellular-and Neurite Motility Speed in Dense Cell Cultures

Mobility quantification of single cells and cellular processes in dense cultures is a challenge, because single cell tracking is impossible. We developed a software for cell structure segmentation and implemented 2 algorithms to measure motility speed. Complex algorithms were tested to separate cells and cellular components, an important prerequisite for the acquisition of meaningful motility data. Plasma membrane segmentation was performed to measure membrane contraction dynamics and organelle trafficking. The discriminative performance and sensitivity of the algorithms were tested on different cell types and calibrated on computer-simulated cells to obtain absolute values for cellular velocity. Both motility algorithms had advantages in different experimental setups, depending on the complexity of the cellular movement. The correlation algorithm (COPRAMove) performed best under most tested conditions and appeared less sensitive to variable cell densities, brightness and focus changes than the differentiation algorithm (DiffMove). In summary, our software can be used successfully to analyze and quantify cellular and subcellular movements in dense cell cultures.

Label-free classification of cells based on supervised machine learning of subcellular structures

It is demonstrated that cells can be classified by pattern recognition of the subcellular structure of non-stained live cells, and the pattern recognition was performed by machine learning. Human white blood cells and five types of cancer cell lines were imaged by quantitative phase microscopy, which provides morphological information without staining quantitatively in terms of optical thickness of cells. Subcellular features were then extracted from the obtained images as training data sets for the machine learning. The built classifier successfully classified WBCs from cell lines (area under ROC curve = 0.996). This label-free, non-cytotoxic cell classification based on the subcellular structure of QPM images has the potential to serve as an automated diagnosis of single cells.

Automated noninvasive epithelial cell counting in phase contrast microscopy images with automated parameter selection

Cell counting is commonly used to determine proliferation rates in cell cultures and for adherent cells it is often a ‘destructive’ process requiring disruption of the cell monolayer resulting in the inability to follow cell growth longitudinally. This process is time consuming and utilises significant resource. In this study a relatively inexpensive, rapid and widely applicable phase contrast microscopy‐based technique has been developed that emulates the contrast changes taking place when bright field microscope images of epithelial cell cultures are defocused. Processing of the resulting images produces an image that can be segmented using a global threshold; the number of cells is then deduced from the number of segmented regions and these cell counts can be used to generate growth curves. The parameters of this method were tuned using the discrete mereotopological relations between ground truth and processed images. Cell count accuracy was improved using linear discriminant analysis to identify spurious noise regions for removal.

The proposed cell counting technique was validated by comparing the results with a manual count of cells in images, and subsequently applied to generate growth curves for oral keratinocyte cultures supplemented with a range of concentrations of foetal calf serum. The approach developed has broad applicability and utility for researchers with standard laboratory imaging equipment.

Multicell migration tracking within angiogenic networks by deep learning-based segmentation and augmented Bayesian filtering

Cell migration is a key feature for living organisms. Image analysis tools are useful in studying cell migration in three-dimensional (3-D) in vitro environments. We consider angiogenic vessels formed in 3-D microfluidic devices (MFDs) and develop an image analysis system to extract cell behaviors from experimental phase-contrast microscopy image sequences. The proposed system initializes tracks with the end-point confocal nuclei coordinates. We apply convolutional neural networks to detect cell candidates and combine backward Kalman filtering with multiple hypothesis tracking to link the cell candidates at each time step. These hypotheses incorporate prior knowledge on vessel formation and cell proliferation rates. The association accuracy reaches 86.4% for the proposed algorithm, indicating that the proposed system is able to associate cells more accurately than existing approaches. Cell culture experiments in 3-D MFDs have shown considerable promise for improving biology research. The proposed system is expected to be a useful quantitative tool for potential microscopy problems of MFDs.

Real-time halo correction in phase contrast imaging

As a label-free, nondestructive method, phase contrast is by far the most popular microscopy technique for routine inspection of cell cultures. However, features of interest such as extensions near cell bodies are often obscured by a glow, which came to be known as the halo. Advances in modeling image formation have shown that this artifact is due to the limited spatial coherence of the illumination. Nevertheless, the same incoherent illumination is responsible for superior sensitivity to fine details in the phase contrast geometry. Thus, there exists a trade-off between high-detail (incoherent) and low-detail (coherent) imaging systems. In this work, we propose a method to break this dichotomy, by carefully mixing corrected low-frequency and high-frequency data in a way that eliminates the edge effect. Specifically, our technique is able to remove halo artifacts at video rates, requiring no manual interaction or a priori point spread function measurements. To validate our approach, we imaged standard spherical beads, sperm cells, tissue slices, and red blood cells. We demonstrate real-time operation with a time evolution study of adherent neuron cultures whose neurites are revealed by our halo correction. We show that with our novel technique, we can quantify cell growth in large populations, without the need for thresholds and system variant calibration.

Phase contrast cell detection using multilevel classification

In this paper, we propose a fully automated learning-based approach for detecting cells in time-lapse phase contrast images. The proposed system combines 2 machine learning approaches to achieve bottom-up image segmentation. We apply pixel-wise classification using random forests (RF) classifiers to determine the potential location of the cells. Each pixel is classified into 4 categories (cell, mitotic cell, halo effect, and background noise). Various image features are extracted at different scales to train the RF classifier. The resulting probability map is partitioned using the k-means algorithm to form potential cell regions. These regions are expanded into the neighboring areas to recover some missing or broken cell regions. To validate the cell regions, another machine learning method based on the bag-of-features and spatial pyramid encoding is proposed. The result of the second classifier can be a validated cell, a merged cell, or a noncell. In the case that the cell region is classified as a merged cell, it is split by using the seeded watershed method. The proposed method is demonstrated on several phase contrast image datasets, ie, U2OS, HeLa, and NIH 3T3. In comparison to state-of-the-art cell detection techniques, the proposed method shows improved performance, particularly in dealing with noise interference and drastic shape variations.

Segmentation Approach Towards Phase-Contrast Microscopic Images of Activated Sludge to Monitor the Wastewater Treatment

Image processing and analysis is an effective tool for monitoring and fault diagnosis of activated sludge (AS) wastewater treatment plants. The AS image comprise of flocs (microbial aggregates) and filamentous bacteria. In this paper, nine different approaches are proposed for image segmentation of phase-contrast microscopic (PCM) images of AS samples. The proposed strategies are assessed for their effectiveness from the perspective of microscopic artifacts associated with PCM. The first approach uses an algorithm that is based on the idea that different color space representation of images other than red-green-blue may have better contrast. The second uses an edge detection approach. The third strategy, employs a clustering algorithm for the segmentation and the fourth applies local adaptive thresholding. The fifth technique is based on texture-based segmentation and the sixth uses watershed algorithm. The seventh adopts a split-and-merge approach. The eighth employs Kittler's thresholding. Finally, the ninth uses a top-hat and bottom-hat filtering-based technique. The approaches are assessed, and analyzed critically with reference to the artifacts of PCM. Gold approximations of ground truth images are prepared to assess the segmentations. Overall, the edge detection-based approach exhibits the best results in terms of accuracy, and the texture-based algorithm in terms of false negative ratio. The respective scenarios are explained for suitability of edge detection and texture-based algorithms.

Segmentation of phase contrast microscopy images based on multi-scale local Basic Image Features histograms

Phase contrast microscopy (PCM) is routinely used for the inspection of adherent cell cultures in all fields of biology and biomedicine. Key decisions for experimental protocols are often taken by an operator based on typically qualitative observations. However, automated processing and analysis of PCM images remain challenging due to the low contrast between foreground objects (cells) and background as well as various imaging artefacts. We propose a trainable pixel-wise segmentation approach whereby image structures and symmetries are encoded in the form of multi-scale Basic Image Features local histograms, and classification of them is learned by random decision trees. This approach was validated for segmentation of cell versus background, and discrimination between two different cell types. Performance close to that of state-of-the-art specialised algorithms was achieved despite the general nature of the method. The low processing time ( < 4 s per 1280 × 960 pixel images) is suitable for batch processing of experimental data as well as for interactive segmentation applications.

Halo-free Phase Contrast Microscopy

We present a new approach for retrieving halo-free phase contrast microscopy (hfPC) images by upgrading the conventional PC microscope with an external interferometric module, which generates sufficient data for reversing the halo artifact. Acquiring four independent intensity images, our approach first measures haloed phase maps of the sample. We solve for the halo-free sample transmission function by using a physical model of the image formation under partial spatial coherence. Using this halo-free sample transmission, we can numerically generate artifact-free PC images. Furthermore, this transmission can be further used to obtain quantitative information about the sample, e.g., the thickness with known refractive indices, dry mass of live cells during their cycles. We tested our hfPC method on various control samples, e.g., beads, pillars and validated its potential for biological investigation by imaging live HeLa cells, red blood cells, and neurons.

A multi-stage random forest classifier for phase contrast cell segmentation

We present a machine learning based approach to automatically detect and segment cells in phase contrast images. The proposed method consists of a multi-stage classification scheme based on random forest (RF) classifier. Both low level and mid level image features are used to determine meaningful cell regions. Pixel-wise RF classification is first carried out to categorize pixels into 4 classes (dark cell, bright cell, halo artifact, and background) and generate a probability map for cell regions. K-means clustering is then applied on the probability map to group similar pixels into candidate cell regions. Finally, cell validation is performed by another RF to verify the candidate cell regions. The proposed method has been tested on U2-OS human osteosarcoma phase contrast images. The experimental results show better performance of the proposed method with precision 92.96% and recall 96.63% compared to a state-of-the-art segmentation technique.

Runout error correction in tomographic reconstruction by intensity summation method

An alignment method for correction of the axial and radial runout errors of the rotation stage in X-ray phase-contrast computed tomography has been developed. Only intensity information was used, without extra hardware or complicated calculation. Notably, the method, as demonstrated herein, can utilize the halo artifact to determine displacement.

LeftyA decreases Actin Polymerization and Stiffness in Human Endometrial Cancer Cells

LeftyA, a cytokine regulating stemness and embryonic differentiation, down-regulates cell proliferation and migration. Cell proliferation and motility require actin reorganization, which is under control of ras-related C3 botulinum toxin substrate 1 (Rac1) and p21 protein-activated kinase 1 (PAK1). The present study explored whether LeftyA modifies actin cytoskeleton, shape and stiffness of Ishikawa cells, a well differentiated endometrial carcinoma cell line. The effect of LeftyA on globular over filamentous actin ratio was determined utilizing Western blotting and flow cytometry. Rac1 and PAK1 transcript levels were measured by qRT-PCR as well as active Rac1 and PAK1 by immunoblotting. Cell stiffness (quantified by the elastic modulus), cell surface area and cell volume were studied by atomic force microscopy (AFM). As a result, 2 hours treatment with LeftyA (25 ng/ml) significantly decreased Rac1 and PAK1 transcript levels and activity, depolymerized actin, and decreased cell stiffness, surface area and volume. The effect of LeftyA on actin polymerization was mimicked by pharmacological inhibition of Rac1 and PAK1. In the presence of the Rac1 or PAK1 inhibitor LeftyA did not lead to significant further actin depolymerization. In conclusion, LeftyA leads to disruption of Rac1 and Pak1 activity with subsequent actin depolymerization, cell softening and cell shrinkage.

Segmentation Method of Time-Lapse Microscopy Images with the Focus on Biocompatibility Assessment

Biocompatibility testing of new materials is often performed in vitro by measuring the growth rate of mammalian cancer cells in time-lapse images acquired by phase contrast microscopes. The growth rate is measured by tracking cell coverage, which requires an accurate automatic segmentation method. However, cancer cells have irregular shapes that change over time, the mottled background pattern is partially visible through the cells and the images contain artifacts such as halos. We developed a novel algorithm for cell segmentation that copes with the mentioned challenges. It is based on temporal differences of consecutive images and a combination of thresholding, blurring, and morphological operations. We tested the algorithm on images of four cell types acquired by two different microscopes, evaluated the precision of segmentation against manual segmentation performed by a human operator, and finally provided comparison with other freely available methods. We propose a new, fully automated method for measuring the cell growth rate based on fitting a coverage curve with the Verhulst population model. The algorithm is fast and shows accuracy comparable with manual segmentation. Most notably it can correctly separate live from dead cells.

Quantitative phase imaging of weakly scattering objects using partially coherent illumination

In this paper, we extend our recent work on partially coherent quantitative phase imaging (pcQPI) from two-dimensional (2D) to three-dimensional (3D) imaging of weakly scattering samples. Due to the mathematical complexity, most theoretical modeling of quantitative phase image formation under partial coherence has focused on thin, well-focused samples. It is unclear how these abberations are affected by defocusing. Also, as 3D QPI techniques continue to develop, a better model needs to be developed to understand and quantify these aberrations when imaging thicker samples. Here, using the first order Born's approximation, we derived a mathematical framework that provides an intuitive model of image formation under varying degrees of coherence. Our description provides a clear connection between the halo effect and phase underestimation, defocusing and the 3D structure of the sample under investigation. Our results agree very well with the experiments and show that the microscope objective defines the sectioning ability of the imaging system while the condenser lens is responsible for the halo effect.

Automated single particle detection and tracking for large microscopy datasets

Recent advances in optical microscopy have enabled the acquisition of very large datasets from living cells with unprecedented spatial and temporal resolutions. Our ability to process these datasets now plays an essential role in order to understand many biological processes. In this paper, we present an automated particle detection algorithm capable of operating in low signal-to-noise fluorescence microscopy environments and handling large datasets. When combined with our particle linking framework, it can provide hitherto intractable quantitative measurements describing the dynamics of large cohorts of cellular components from organelles to single molecules. We begin with validating the performance of our method on synthetic image data, and then extend the validation to include experiment images with ground truth. Finally, we apply the algorithm to two single-particle-tracking photo-activated localization microscopy biological datasets, acquired from living primary cells with very high temporal rates. Our analysis of the dynamics of very large cohorts of 10 000 s of membrane-associated protein molecules show that they behave as if caged in nanodomains. We show that the robustness and efficiency of our method provides a tool for the examination of single-molecule behaviour with unprecedented spatial detail and high acquisition rates.

Algorithm for the precise detection of single and cluster cells in microfluidic applications

Recent advances in imaging flow cytometry and microfluidic applications have led to the development of suitable mathematical algorithms capable of detecting and identifying targeted cells in images. In contrast to currently existing algorithms, we herein proposed the identification and reconstruction of cell edges based on original approaches that overcome frequent detection limitations such as halos, noise, and droplet boundaries in microfluidic applications. Reconstructed cells are then discriminated between single cells and clusters of round-shaped cells, and cell information such as the area and location of a cell in an image is output. Using this method, 76% of cells detected in an image had an error <5% of the cell area size and 41% of the image had an error <1% of the cell area size (n = 1,000). The method developed in the present study is the first image processing algorithm designed to be flexible in use (i.e. independent of the size of an image, using a microfluidic droplet system or not, and able to recognize cell clusters in an image) and provides the scientific community with a very accurate imaging algorithm in the field of microfluidic applications. © 2016 International Society for Advancement of Cytometry.

Interactive Cell Segmentation Based on Active and Semi-Supervised Learning

Automatic cell segmentation can hardly be flawless due to the complexity of image data particularly when time-lapse experiments last for a long time without biomarkers. To address this issue, we propose an interactive cell segmentation method by classifying feature-homogeneous superpixels into specific classes, which is guided by human interventions. Specifically, we propose to actively select the most informative superpixels by minimizing the expected prediction error which is upper bounded by the transductive Rademacher complexity, and then query for human annotations. After propagating the user-specified labels to the remaining unlabeled superpixels via an affinity graph, the error-prone superpixels are selected automatically and request for human verification on them; once erroneous segmentation is detected and subsequently corrected, the information is propagated efficiently over a gradually-augmented graph to un-labeled superpixels such that the analogous errors are fixed meanwhile. The correction propagation step is efficiently conducted by introducing a verification propagation matrix rather than rebuilding the affinity graph and re-performing the label propagation from the beginning. We repeat this procedure until most superpixels are classified into a specific category with high confidence. Experimental results performed on three types of cell populations validate that our interactive cell segmentation algorithm quickly reaches high quality results with minimal human interventions and is significantly more efficient than alternative methods, since the most informative samples are selected for human annotation/verification early.

A review of progress in single particle tracking: from methods to biophysical insights

Optical microscopy has for centuries been a key tool to study living cells with minimum invasiveness. The advent of single molecule techniques over the past two decades has revolutionized the field of cell biology by providing a more quantitative picture of the complex and highly dynamic organization of living systems. Amongst these techniques, single particle tracking (SPT) has emerged as a powerful approach to study a variety of dynamic processes in life sciences. SPT provides access to single molecule behavior in the natural context of living cells, thereby allowing a complete statistical characterization of the system under study. In this review we describe the foundations of SPT together with novel optical implementations that nowadays allow the investigation of single molecule dynamic events with increasingly high spatiotemporal resolution using molecular densities closer to physiological expression levels. We outline some of the algorithms for the faithful reconstruction of SPT trajectories as well as data analysis, and highlight biological examples where the technique has provided novel insights into the role of diffusion regulating cellular function. The last part of the review concentrates on different theoretical models that describe anomalous transport behavior and ergodicity breaking observed from SPT studies in living cells.

Automatic neuron segmentation and neural network analysis method for phase contrast microscopy images

Phase Contrast Microscopy (PCM) is an important tool for the long term study of living cells. Unlike fluorescence methods which suffer from photobleaching of fluorophore or dye molecules, PCM image contrast is generated by the natural variations in optical index of refraction. Unfortunately, the same physical principles which allow for these studies give rise to complex artifacts in the raw PCM imagery. Of particular interest in this paper are neuron images where these image imperfections manifest in very different ways for the two structures of specific interest: cell bodies (somas) and dendrites. To address these challenges, we introduce a novel parametric image model using the level set framework and an associated variational approach which simultaneously restores and segments this class of images. Using this technique as the basis for an automated image analysis pipeline, results for both the synthetic and real images validate and demonstrate the advantages of our approach.

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

BACKGROUND

The goal of this survey paper is to overview cellular measurements using optical microscopy imaging followed by automated image segmentation. The cellular measurements of primary interest are taken from mammalian cells and their components. They are denoted as two- or three-dimensional (2D or 3D) image objects of biological interest. In our applications, such cellular measurements are important for understanding cell phenomena, such as cell counts, cell-scaffold interactions, cell colony growth rates, or cell pluripotency stability, as well as for establishing quality metrics for stem cell therapies. In this context, this survey paper is focused on automated segmentation as a software-based measurement leading to quantitative cellular measurements.

METHODS

We define the scope of this survey and a classification schema first. Next, all found and manually filteredpublications are classified according to the main categories: (1) objects of interests (or objects to be segmented), (2) imaging modalities, (3) digital data axes, (4) segmentation algorithms, (5) segmentation evaluations, (6) computational hardware platforms used for segmentation acceleration, and (7) object (cellular) measurements. Finally, all classified papers are converted programmatically into a set of hyperlinked web pages with occurrence and co-occurrence statistics of assigned categories.

RESULTS

The survey paper presents to a reader: (a) the state-of-the-art overview of published papers about automated segmentation applied to optical microscopy imaging of mammalian cells, (b) a classification of segmentation aspects in the context of cell optical imaging, (c) histogram and co-occurrence summary statistics about cellular measurements, segmentations, segmented objects, segmentation evaluations, and the use of computational platforms for accelerating segmentation execution, and (d) open research problems to pursue.

CONCLUSIONS

The novel contributions of this survey paper are: (1) a new type of classification of cellular measurements and automated segmentation, (2) statistics about the published literature, and (3) a web hyperlinked interface to classification statistics of the surveyed papers at https://isg.nist.gov/deepzoomweb/resources/survey/index.html.

Computational Image Analysis Reveals Intrinsic Multigenerational Differences between Anterior and Posterior Cerebral Cortex Neural Progenitor Cells

Time-lapse microscopy can capture patterns of development through multiple divisions for an entire clone of proliferating cells. Images are taken every few minutes over many days, generating data too vast to process completely by hand. Computational analysis of this data can benefit from occasional human guidance. Here we combine improved automated algorithms with minimized human validation to produce fully corrected segmentation, tracking, and lineaging results with dramatic reduction in effort. A web-based viewer provides access to data and results. The improved approach allows efficient analysis of large numbers of clones. Using this method, we studied populations of progenitor cells derived from the anterior and posterior embryonic mouse cerebral cortex, each growing in a standardized culture environment. Progenitors from the anterior cortex were smaller, less motile, and produced smaller clones compared to those from the posterior cortex, demonstrating cell-intrinsic differences that may contribute to the areal organization of the cerebral cortex.

•

Open-source automated software designed to track stem/progenitor clones in time-lapse movies

•

Software tools for easy data validation and visualization greatly improve efficiency

•

Lineage tree reconstruction from hundreds of embryonic mouse forebrain clones

•

Intrinsic differences in progenitor behavior from anterior/posterior cerebral cortex

Cell Detection From Redundant Candidate Regions Under Nonoverlapping Constraints

Cell detection in microscopy images is essential for automated cell behavior analysis including cell shape analysis and cell tracking. Robust cell detection in high-density and low-contrast images is still challenging since cells often touch and partially overlap, forming a cell cluster with blurry intercellular boundaries. In such cases, current methods tend to detect multiple cells as a cluster. If the control parameters are adjusted to separate the touching cells, other problems often occur: a single cell may be segmented into several regions, and cells in low-intensity regions may not be detected. To solve these problems, we first detect redundant candidate regions, which include many false positives but in turn very few false negatives, by allowing candidate regions to overlap with each other. Next, the score for how likely the candidate region contains the main part of a single cell is computed for each cell candidate using supervised learning. Then we select an optimal set of cell regions from the redundant regions under nonoverlapping constraints, where each selected region looks like a single cell and the selected regions do not overlap. We formulate this problem of optimal region selection as a binary linear programming problem under nonoverlapping constraints. We demonstrated the effectiveness of our method for several types of cells in microscopy images. Our method performed better than five representative methods, achieving an F-measure of over 0.9 for all data sets. Experimental application of the proposed method to 3-D images demonstrated that also works well for 3-D cell detection.

Cell-sensitive phase contrast microscopy imaging by multiple exposures

We propose a novel way of imaging live cells in a Petri dish by the phase contrast microscope. By taking multiple exposures of phase contrast microscopy images on the same cell dish, we estimate a cell-sensitive camera response function which responds to cells' irradiance signals but generates a constant on non-cell background signal. The result of this new microscopy imaging is visually superior quality, which reveals the appearance details of cells and suppresses background noise near zero. Using the cell-sensitive microscopy imaging, cells' original irradiance signals are restored from all exposures and the irradiance signals on non-cell background regions are restored as a uniform constant (i.e., the imaging system is sensitive to cells only but insensitive to non-cell background). The restored irradiance signals greatly facilitate the cell segmentation by simple thresholding. The experimental results validate that high quality cell segmentation can be achieved by our approach.

A SEGMENTATION FRAMEWORK FOR PHASE CONTRAST AND FLUORESCENCE MICROSCOPY IMAGES

The noninvasive imaging of unstained living cells is a widely used technique in biotechnology for determining biological and biochemical role of proteins, since it allows studying living specimens without altering them. Usually, fluorescence and contrast (or transmission) images are both used complementarily, as their combination allows possible better outcomes. However, segmentation of contrast images is particularly difficult due to the presence of defocused scans, lighting/shade-off artifacts and cells overlapping. In this work, we investigate the optical properties intervening during the image formation process, and propose different segmentation strategies that can benefit from these properties. The proposed scheme (i) combines the estimated phase and the fluorescence information in order to obtain initial markers for a latter segmentation stage; and (ii) use the shear oriented polar snakes, an active contour model that implicitly involves phase information on its energy functional. The obtained contour can be used as region of interest estimation, as data for a latter shape-fitting process, or as smart markers for a more detailed segmentation process (i.e. watershed). Experimental results provide a comparison of the different segmentation schemes, and confirm the suitability of the proposed strategy and model for cell images segmentation.