Deep learning for high-throughput quantification of oligodendrocyte ensheathment at single-cell resolution

3-Dimensional Immunostaining and Automated Deep-Learning Based Analysis of Nerve Degeneration

Multiple sclerosis (MS) is an autoimmune and neurodegenerative disease driven by inflammation and demyelination in the brain, spinal cord, and optic nerve. Optic neuritis, characterized by inflammation and demyelination of the optic nerve, is a symptom in many patients with MS. The optic nerve is the highway for visual information transmitted from the retina to the brain. It contains axons from the retinal ganglion cells (RGCs) that reside in the retina, myelin forming oligodendrocytes and resident microglia and astrocytes. Inflammation, demyelination, and axonal degeneration are also present in the optic nerve of mice subjected to experimental autoimmune encephalomyelitis (EAE), a preclinical mouse model of MS. Monitoring the optic nerve in EAE is a useful strategy to study the presentation and progression of pathology in the visual system; however, current approaches have relied on sectioning, staining and manual quantification. Further, information regarding the spatial load of lesions and inflammation is dependent on the area of sectioning. To better characterize cellular pathology in the EAE model, we employed a tissue clearing and 3D immunolabelling and imaging protocol to observe patterns of immune cell infiltration and activation throughout the optic nerve. Increased density of TOPRO staining for nuclei captured immune cell infiltration and Iba1 immunostaining was employed to monitor microglia and macrophages. Axonal degeneration was monitored by neurofilament immunolabelling to reveal axonal swellings throughout the optic nerve. In parallel, we developed a convolutional neural network with a UNet architecture (CNN-UNet) called BlebNet for automated identification and quantification of axonal swellings in whole mount optic nerves. Together this constitutes a toolkit for 3-dimensional immunostaining to monitor general optic nerve pathology and fast automated quantification of axonal defects that could also be adapted to monitor axonal degeneration and inflammation in other neurodegenerative disease models.

An in vivo accelerated developmental myelination model for testing promyelinating therapeutics

Background

Therapeutic agents stimulating the process of myelination could be beneficial for the treatment of demyelinating diseases, such as multiple sclerosis. The efficient translation of compounds promoting myelination in vitro to efficacy in vivo is inherently time-consuming and expensive. Thyroid hormones accelerate the differentiation and maturation of oligodendrocytes, thereby promoting myelination. Systemic administration of the thyroid hormone thyroxine (T4) accelerates brain maturation, including myelination, during early postnatal development. The objective of this study was to validate an animal model for rapid testing of promyelinating therapeutic candidates for their effects on early postnatal development by using T4 as a reference compound.

Methods

Daily subcutaneous injections of T4 were given to Sprague Dawley rat pups from postnatal day (PND) 2 to PND10. Changes in white matter were determined at PND10 using diffusion tensor magnetic resonance imaging (DTI). Temporal changes in myelination from PND3 to PND11 were also assessed by quantifying myelin basic protein (MBP) expression levels in the brain using the resonance Raman spectroscopy/enzyme-linked immunosorbent assay (RRS-ELISA) and quantitative immunohistochemistry.

Results

DTI of white matter tracts showed significantly higher fractional anisotropy in the internal capsule of T4-treated rat pups. The distribution of total FA values in the forebrain was significantly shifted towards higher values in the T4-treated group, suggesting increased myelination. In vivo imaging data were supported by in vitro observations, as T4 administration significantly potentiated the developmental increase in MBP levels in brain lysates starting from PND8. MBP levels in the brain of animals that received treatment for 9 days correlated with the FA metric determined in the same pups in vivo a day earlier. Furthermore, accelerated developmental myelination following T4 administration was confirmed by immunohistochemical staining for MBP in coronal brain sections of treated rat pups.

Conclusions

T4-treated rat pups had increased MBP expression levels and higher MRI fractional anisotropy values, both indications of accelerated myelination. This simple developmental myelination model affords a rapid test of promyelinating activity in vivo within several days, which could facilitate in vivo prescreening of candidate therapeutic compounds for developmental hypomyelinating diseases. Further research will be necessary to assess the utility of this platform for screening promyelination compounds in more complex demyelination disease models, such us multiple sclerosis.

Supplementary information

The online version contains supplementary material available at 10.1186/s12868-022-00714-y.

Application of a deep learning-based image analysis and live-cell imaging system for quantifying adipogenic differentiation kinetics of adipose-derived stem/stromal cells

Quantitative methods for assessing differentiative potency of adipose-derived stem/stromal cells may lead to improved clinical application of this multipotent stem cell, by advancing our understanding of specific processes such as adipogenic differentiation. Conventional cell staining methods are used to determine the formation of adipose areas during adipogenesis as a qualitative representation of adipogenic potency. Staining methods such as oil-red-O are quantifiable using absorbance measurements, but these assays are time and material consuming. Detection methods for cell characteristics using advanced image analysis by machine learning are emerging. Here, live-cell imaging was combined with a deep learning-based detection tool to quantify the presence of adipose areas and lipid droplet formation during adipogenic differentiation of adipose-derived stem/stromal cells. Different detection masks quantified adipose area and lipid droplet formation at different time points indicating kinetics of adipogenesis and showed differences between individual donors. Whereas CEBPA and PPARG expression seems to precede the increase in adipose area and lipid droplets, it might be able to predict expression of ADIPOQ. The applied method is a proof of concept, demonstrating that deep learning methods can be used to investigate adipogenic differentiation and kinetics in vitro using specific detection masks based on algorithm produced from annotation of image data.

Novel in vitro Experimental Approaches to Study Myelination and Remyelination in the Central Nervous System

Myelin is the lipidic insulating structure enwrapping axons and allowing fast saltatory nerve conduction. In the central nervous system, myelin sheath is the result of the complex packaging of multilamellar extensions of oligodendrocyte (OL) membranes. Before reaching myelinating capabilities, OLs undergo a very precise program of differentiation and maturation that starts from OL precursor cells (OPCs). In the last 20 years, the biology of OPCs and their behavior under pathological conditions have been studied through several experimental models. When co-cultured with neurons, OPCs undergo terminal maturation and produce myelin tracts around axons, allowing to investigate myelination in response to exogenous stimuli in a very simple in vitro system. On the other hand, in vivo models more closely reproducing some of the features of human pathophysiology enabled to assess the consequences of demyelination and the molecular mechanisms of remyelination, and they are often used to validate the effect of pharmacological agents. However, they are very complex, and not suitable for large scale drug discovery screening. Recent advances in cell reprogramming, biophysics and bioengineering have allowed impressive improvements in the methodological approaches to study brain physiology and myelination. Rat and mouse OPCs can be replaced by human OPCs obtained by induced pluripotent stem cells (iPSCs) derived from healthy or diseased individuals, thus offering unprecedented possibilities for personalized disease modeling and treatment. OPCs and neural cells can be also artificially assembled, using 3D-printed culture chambers and biomaterial scaffolds, which allow modeling cell-to-cell interactions in a highly controlled manner. Interestingly, scaffold stiffness can be adopted to reproduce the mechanosensory properties assumed by tissues in physiological or pathological conditions. Moreover, the recent development of iPSC-derived 3D brain cultures, called organoids, has made it possible to study key aspects of embryonic brain development, such as neuronal differentiation, maturation and network formation in temporal dynamics that are inaccessible to traditional in vitro cultures. Despite the huge potential of organoids, their application to myelination studies is still in its infancy. In this review, we shall summarize the novel most relevant experimental approaches and their implications for the identification of remyelinating agents for human diseases such as multiple sclerosis.

SKAP2 as a new regulator of oligodendroglial migration and myelin sheath formation

Oligodendroglial progenitor cells (OPCs) are highly proliferative and migratory cells, which differentiate into complex myelin forming and axon ensheathing mature oligodendrocytes during myelination. Recent studies indicate that the oligodendroglial cell population is heterogeneous on transcriptional and functional level depending on the location in the central nervous system. Here, we compared intrinsic properties of OPC from spinal cord and brain on functional and transcriptional level. Spinal cord OPC demonstrated increased migration as well as differentiation capacity. Moreover, transcriptome analysis revealed differential expression of several genes between both OPC populations. In spinal cord OPC, we confirmed upregulation of SKAP2, a cytoplasmatic adaptor protein known for its implication in cytoskeletal remodeling and migration in other cell types. Recent findings suggest that actin dynamics determine not only oligodendroglial migration, but also differentiation: Whereas actin polymerization is important for process extension, actin destabilization and depolymerization is required for myelin sheath formation. Downregulation or complete lack of SKAP2 in OPC resulted in reduced migration and impaired morphological maturation in oligodendrocytes. In contrast, overexpression of SKAP2 as well as constitutively active SKAP2 increased OPC migration suggesting that SKAP2 function is dependent on activation by phosphorylation. Furthermore, lack of SKAP2 enhanced the positive effect on OPC migration after integrin activation suggesting that SKAP2 acts as modulator of integrin dependent migration. In summary, we demonstrate the presence of intrinsic differences between spinal cord and brain OPC and identified SKAP2 as a new regulator of oligodendroglial migration and sheath formation.

Human Oligodendrocytes and Myelin In Vitro to Evaluate Developmental Neurotoxicity

Neurodevelopment is uniquely sensitive to toxic insults and there are concerns that environmental chemicals are contributing to widespread subclinical developmental neurotoxicity (DNT). Increased DNT evaluation is needed due to the lack of such information for most chemicals in common use, but in vivo studies recommended in regulatory guidelines are not practical for the large-scale screening of potential DNT chemicals. It is widely acknowledged that developmental neurotoxicity is a consequence of disruptions to basic processes in neurodevelopment and that testing strategies using human cell-based in vitro systems that mimic these processes could aid in prioritizing chemicals with DNT potential. Myelination is a fundamental process in neurodevelopment that should be included in a DNT testing strategy, but there are very few in vitro models of myelination. Thus, there is a need to establish an in vitro myelination assay for DNT. Here, we summarize the routes of myelin toxicity and the known models to study this particular endpoint.

Automated in vivo Tracking of Cortical Oligodendrocytes

Oligodendrocytes exert a profound influence on neural circuits by accelerating action potential conduction, altering excitability, and providing metabolic support. As oligodendrogenesis continues in the adult brain and is essential for myelin repair, uncovering the factors that control their dynamics is necessary to understand the consequences of adaptive myelination and develop new strategies to enhance remyelination in diseases such as multiple sclerosis. Unfortunately, few methods exist for analysis of oligodendrocyte dynamics, and even fewer are suitable for in vivo investigation. Here, we describe the development of a fully automated cell tracking pipeline using convolutional neural networks (Oligo-Track) that provides rapid volumetric segmentation and tracking of thousands of cells over weeks in vivo. This system reliably replicated human analysis, outperformed traditional analytic approaches, and extracted injury and repair dynamics at multiple cortical depths, establishing that oligodendrogenesis after cuprizone-mediated demyelination is suppressed in deeper cortical layers. Volumetric data provided by this analysis revealed that oligodendrocyte soma size progressively decreases after their generation, and declines further prior to death, providing a means to predict cell age and eventual cell death from individual time points. This new CNN-based analysis pipeline offers a rapid, robust method to quantitatively analyze oligodendrocyte dynamics in vivo, which will aid in understanding how changes in these myelinating cells influence circuit function and recovery from injury and disease.

One-step Reprogramming of Human Fibroblasts into Oligodendrocyte-like Cells by SOX10, OLIG2, and NKX6.2

Limited access to human oligodendrocytes impairs better understanding of oligodendrocyte pathology in myelin diseases. Here, we describe a method to robustly convert human fibroblasts directly into oligodendrocyte-like cells (dc-hiOLs), which allows evaluation of remyelination-promoting compounds and disease modeling. Ectopic expression of SOX10, OLIG2, and NKX6.2 in human fibroblasts results in rapid generation of O4⁺ cells, which further differentiate into MBP⁺ mature oligodendrocyte-like cells within 16 days. dc-hiOLs undergo chromatin remodeling to express oligodendrocyte markers, ensheath axons, and nanofibers in vitro, respond to promyelination compound treatment, and recapitulate in vitro oligodendroglial pathologies associated with Pelizaeus-Merzbacher leukodystrophy related to PLP1 mutations. Furthermore, DNA methylome analysis provides evidence that the CpG methylation pattern significantly differs between dc-hiOLs derived from fibroblasts of young and old donors, indicating the maintenance of the source cells’ “age.” In summary, dc-hiOLs represent a reproducible technology that could contribute to personalized medicine in the field of myelin diseases.

•

SOX10, OLIG2, and NKX6.2 directly convert human fibroblasts into dc-hiOLs in 16 days

•

dc-hiOLs express key oligodendrocyte markers

•

dc-hiOLs preserve the epigenetic age of donor cells

•

dc-hiOLs from PMD patients show maturation deficit and vulnerability to cell death

The Current Challenges for Drug Discovery in CNS Remyelination

The myelin sheath wraps around axons, allowing saltatory currents to be transmitted along neurons. Several genetic, viral, or environmental factors can damage the central nervous system (CNS) myelin sheath during life. Unless the myelin sheath is repaired, these insults will lead to neurodegeneration. Remyelination occurs spontaneously upon myelin injury in healthy individuals but can fail in several demyelination pathologies or as a consequence of aging. Thus, pharmacological intervention that promotes CNS remyelination could have a major impact on patient’s lives by delaying or even preventing neurodegeneration. Drugs promoting CNS remyelination in animal models have been identified recently, mostly as a result of repurposing phenotypical screening campaigns that used novel oligodendrocyte cellular models. Although none of these have as yet arrived in the clinic, promising candidates are on the way. Many questions remain. Among the most relevant is the question if there is a time window when remyelination drugs should be administrated and why adult remyelination fails in many neurodegenerative pathologies. Moreover, a significant challenge in the field is how to reconstitute the oligodendrocyte/axon interaction environment representative of healthy as well as disease microenvironments in drug screening campaigns, so that drugs can be screened in the most appropriate disease-relevant conditions. Here we will provide an overview of how the field of in vitro models developed over recent years and recent biological findings about how oligodendrocytes mature after reactivation of their staminal niche. These data have posed novel questions and opened new views about how the adult brain is repaired after myelin injury and we will discuss how these new findings might change future drug screening campaigns for CNS regenerative drugs.

Anti-senescent drug screening by deep learning-based morphology senescence scoring

Advances in deep learning technology have enabled complex task solutions. The accuracy of image classification tasks has improved owing to the establishment of convolutional neural networks (CNN). Cellular senescence is a hallmark of ageing and is important for the pathogenesis of ageing-related diseases. Furthermore, it is a potential therapeutic target. Specific molecular markers are used to identify senescent cells. Moreover senescent cells show unique morphology, which can be identified. We develop a successful morphology-based CNN system to identify senescent cells and a quantitative scoring system to evaluate the state of endothelial cells by senescence probability output from pre-trained CNN optimised for the classification of cellular senescence, Deep Learning-Based Senescence Scoring System by Morphology (Deep-SeSMo). Deep-SeSMo correctly evaluates the effects of well-known anti-senescent reagents. We screen for drugs that control cellular senescence using a kinase inhibitor library by Deep-SeSMo-based drug screening and identify four anti-senescent drugs. RNA sequence analysis reveals that these compounds commonly suppress senescent phenotypes through inhibition of the inflammatory response pathway. Thus, morphology-based CNN system can be a powerful tool for anti-senescent drug screening.

Cellular senescence is a hallmark of ageing and is important for the pathogenesis of ageing-related diseases. Here, the authors develop a morphology-based deep learning system to identify senescent cells and a quantitative scoring system to evaluate the state of endothelial cells to evaluate the effects of anti-senescent reagents.

High-Content Imaging to Phenotype Human Primary and iPSC-Derived Cells

Increasingly powerful microscopy, liquid handling, and computational techniques have enabled cell imaging in high throughput. Microscopy images are quantified using high-content analysis platforms linking object features to cell behavior. This can be attempted on physiologically relevant cell models, including stem cells and primary cells, in complex environments, and conceivably in the presence of perturbations. Recently, substantial focus has been devoted to cell profiling for cell therapy, assays for drug discovery or biomarker identification for clinical decision-making protocols, bringing this wealth of information into translational applications. In this chapter, we focus on two protocols enabling to (1) benchmark human cells, in particular human endothelial cells as a case study and (2) extract cells from blood for follow-up experiments including image-based drug testing. We also present concepts of high-content imaging and discuss the benefits and challenges, with the aim of enabling readers to tailor existing pipelines and bring such approaches closer to translational research and the clinic.

Electrospun Fiber Scaffolds for Engineering Glial Cell Behavior to Promote Neural Regeneration

Electrospinning is a fabrication technique used to produce nano- or micro- diameter fibers to generate biocompatible, biodegradable scaffolds for tissue engineering applications. Electrospun fiber scaffolds are advantageous for neural regeneration because they mimic the structure of the nervous system extracellular matrix and provide contact guidance for regenerating axons. Glia are non-neuronal regulatory cells that maintain homeostasis in the healthy nervous system and regulate regeneration in the injured nervous system. Electrospun fiber scaffolds offer a wide range of characteristics, such as fiber alignment, diameter, surface nanotopography, and surface chemistry that can be engineered to achieve a desired glial cell response to injury. Further, electrospun fibers can be loaded with drugs, nucleic acids, or proteins to provide the local, sustained release of such therapeutics to alter glial cell phenotype to better support regeneration. This review provides the first comprehensive overview of how electrospun fiber alignment, diameter, surface nanotopography, surface functionalization, and therapeutic delivery affect Schwann cells in the peripheral nervous system and astrocytes, oligodendrocytes, and microglia in the central nervous system both in vitro and in vivo. The information presented can be used to design and optimize electrospun fiber scaffolds to target glial cell response to mitigate nervous system injury and improve regeneration.

Myelin detection in fluorescence microscopy images using machine learning

BACKGROUND

The myelin sheath produced by glial cells insulates the axons, and supports the function of the nervous system. Myelin sheath degeneration causes neurodegenerative disorders, such as multiple sclerosis (MS). There are no therapies for MS that promote remyelination. Drug discovery frequently involves screening thousands of compounds. However, this is not feasible for remyelination drugs, since myelin quantification is a manual labor-intensive endeavor. Therefore, the development of assistive software for expedited myelin detection is instrumental for MS drug discovery by enabling high-content image-based drug screens.

NEW METHOD

In this study, we developed a machine learning based expedited myelin detection approach in fluorescence microscopy images. Multi-channel three-dimensional microscopy images of a mouse stem cell-based myelination assay were labeled by experts. A spectro-spatial feature extraction method was introduced to represent local dependencies of voxels both in spatial and spectral domains. Feature extraction yielded two data set of over forty-seven thousand annotated images in total.

RESULTS

Myelin detection performances of 23 different supervised machine learning techniques including a customized-convolutional neural network (CNN), were assessed using various train/test split ratios of the data sets. The highest accuracy values of 98.84±0.09% and 98.46±0.11% were achieved by Boosted Trees and customized-CNN, respectively.

COMPARISON WITH EXISTING METHODS

Our approach can detect myelin in a common experimental setup. Myelin extending in any orientation in 3 dimensions is segmented from 3 channel z-stack fluorescence images.

CONCLUSIONS

Our results suggest that the proposed expedited myelin detection approach is a feasible and robust method for remyelination drug screening.

Multiple sclerosis iPS-derived oligodendroglia conserve their properties to functionally interact with axons and glia in vivo

Remyelination failure in multiple sclerosis (MS) is associated with a migration/differentiation block of oligodendroglia. The reason for this block is highly debated. It could result from disease-related extrinsic or intrinsic regulators in oligodendroglial biology. To avoid confounding immune-mediated extrinsic effect, we used an immune-deficient mouse model to compare induced pluripotent stem cell-derived oligodendroglia from MS and healthy donors following engraftment in the developing CNS. We show that the MS-progeny behaves and differentiates into oligodendrocytes to the same extent as controls. They generate equal amounts of myelin, with bona fide nodes of Ranvier, and promote equal restoration of their host slow conduction. MS-progeny expressed oligodendrocyte- and astrocyte-specific connexins and established functional connections with donor and host glia. Thus, MS oligodendroglia, regardless of major immune manipulators, are intrinsically capable of myelination and making functional axo-glia/glia-glia connections, reinforcing the view that the MS oligodendrocyte differentiation block is not from major intrinsic oligodendroglial deficits.

Extrinsic immune cell-derived, but not intrinsic oligodendroglial factors contribute to oligodendroglial differentiation block in multiple sclerosis

Multiple sclerosis (MS) is the most frequent demyelinating disease in young adults and despite significant advances in immunotherapy, disease progression still cannot be prevented. Promotion of remyelination, an endogenous repair mechanism resulting in the formation of new myelin sheaths around demyelinated axons, represents a promising new treatment approach. However, remyelination frequently fails in MS lesions, which can in part be attributed to impaired differentiation of oligodendroglial progenitor cells into mature, myelinating oligodendrocytes. The reasons for impaired oligodendroglial differentiation and defective remyelination in MS are currently unknown. To determine whether intrinsic oligodendroglial factors contribute to impaired remyelination in relapsing–remitting MS (RRMS), we compared induced pluripotent stem cell-derived oligodendrocytes (hiOL) from RRMS patients and controls, among them two monozygous twin pairs discordant for MS. We found that hiOL from RRMS patients and controls were virtually indistinguishable with respect to remyelination-associated functions and proteomic composition. However, while analyzing the effect of extrinsic factors we discovered that supernatants of activated peripheral blood mononuclear cells (PBMCs) significantly inhibit oligodendroglial differentiation. In particular, we identified CD4⁺ T cells as mediators of impaired oligodendroglial differentiation; at least partly due to interferon-gamma secretion. Additionally, we observed that blocked oligodendroglial differentiation induced by PBMC supernatants could not be restored by application of oligodendroglial differentiation promoting drugs, whereas treatment of PBMCs with the immunomodulatory drug teriflunomide prior to supernatant collection partly rescued oligodendroglial differentiation. In summary, these data indicate that the oligodendroglial differentiation block is not due to intrinsic oligodendroglial factors but rather caused by the inflammatory environment in RRMS lesions which underlines the need for drug screening approaches taking the inflammatory environment into account. Combined, these findings may contribute to the development of new remyelination promoting strategies.

Effects of Biotin on survival, ensheathment, and ATP production by oligodendrocyte lineage cells in vitro

Mechanisms implicated in disease progression in multiple sclerosis include continued oligodendrocyte (OL)/myelin injury and failure of myelin repair. Underlying causes include metabolic stress with resultant energy deficiency. Biotin is a cofactor for carboxylases involved in ATP production that impact myelin production by promoting fatty acid synthesis. Here, we investigate the effects of high dose Biotin (MD1003) on the functional properties of post-natal rat derived oligodendrocyte progenitor cells (OPCs). A2B5 positive OPCs were assessed using an in vitro injury assay, culturing cells in either DFM (DMEM/F12+N1) or “stress media” (no glucose (NG)-DMEM), with Biotin added over a range from 2.5 to 250 μg/ml, and cell viability determined after 24 hrs. Biotin reduced the increase in OPC cell death in the NG condition. In nanofiber myelination assays, biotin increased the percentage of ensheathing cells, the number of ensheathed segments per cell, and length of ensheathed segments. In dispersed cell culture, Biotin also significantly increased ATP production, assessed using a Seahorse bio-analyzer. For most assays, the positive effects of Biotin were observed at the higher end of the dose-response analysis. We conclude that Biotin, in vitro, protects OL lineage cells from metabolic injury, enhances myelin-like ensheathment, and is associated with increased ATP production.

Prediction of Sequential Organelles Localization under Imbalance using A Balanced Deep U-Net

Assessing the structure and function of organelles in living organisms of the primitive unicellular red algae Cyanidioschyzon merolae on three-dimensional sequential images demands a reliable automated technique in the class imbalance among various cellular structures during mitosis. Existing classification networks with commonly used loss functions were focused on larger numbers of cellular structures that lead to the unreliability of the system. Hence, we proposed a balanced deep regularized weighted compound dice loss (RWCDL) network for better localization of cell organelles. Specifically, we introduced two new loss functions, namely compound dice (CD) and RWCD by implementing multi-class variant dice and weighting mechanism, respectively for maximizing weights of peroxisome and nucleus among five classes as the main contribution of this study. We extended the Unet-like convolution neural network (CNN) architecture for evaluating the ability of our proposed loss functions for improved segmentation. The feasibility of the proposed approach is confirmed with three different large scale mitotic cycle data set with different number of occurrences of cell organelles. In addition, we compared the training behavior of our designed architectures with the ground truth segmentation using various performance measures. The proposed balanced RWCDL network generated the highest area under the curve (AUC) value in elevating the small and obscure peroxisome and nucleus, which is 30% higher than the network with commonly used mean square error (MSE) and dice loss (DL) functions. The experimental results indicated that the proposed approach can efficiently identify the cellular structures, even when the contour between the cells is obscure and thus convinced that the balanced deep RWCDL approach is reliable and can be helpful for biologist to accurately identify the relationship between the cell behavior and structures of cell organelles during mitosis.