Algorithms for cytoplasm segmentation of fluorescence labelled cells

Tissue fluidification promotes a cGAS-STING cytosolic DNA response in invasive breast cancer

The process in which locally confined epithelial malignancies progressively evolve into invasive cancers is often promoted by unjamming, a phase transition from a solid-like to a liquid-like state, which occurs in various tissues. Whether this tissue-level mechanical transition impacts phenotypes during carcinoma progression remains unclear. Here we report that the large fluctuations in cell density that accompany unjamming result in repeated mechanical deformations of cells and nuclei. This triggers a cellular mechano-protective mechanism involving an increase in nuclear size and rigidity, heterochromatin redistribution and remodelling of the perinuclear actin architecture into actin rings. The chronic strains and stresses associated with unjamming together with the reduction of Lamin B1 levels eventually result in DNA damage and nuclear envelope ruptures, with the release of cytosolic DNA that activates a cGAS-STING (cyclic GMP-AMP synthase-signalling adaptor stimulator of interferon genes)-dependent cytosolic DNA response gene program. This mechanically driven transcriptional rewiring ultimately alters the cell state, with the emergence of malignant traits, including epithelial-to-mesenchymal plasticity phenotypes and chemoresistance in invasive breast carcinoma.

Non-invasive measurement of nuclear relative stiffness from quantitative analysis of microscopy data

The connection between the properties of a cell tissue and those of the single constituent cells remains to be elucidated. At the purely mechanical level, the degree of rigidity of different cellular components, such as the nucleus and the cytoplasm, modulates the interplay between the cell inner processes and the external environment, while simultaneously mediating the mechanical interactions between neighboring cells. Being able to quantify the correlation between single-cell and tissue properties would improve our mechanobiological understanding of cell tissues. Here we develop a methodology to quantitatively extract a set of structural and motility parameters from the analysis of time-lapse movies of nuclei belonging to jammed and flocking cell monolayers. We then study in detail the correlation between the dynamical state of the tissue and the deformation of the nuclei. We observe that the nuclear deformation rate linearly correlates with the local divergence of the velocity field, which leads to a non-invasive estimate of the elastic modulus of the nucleus relative to the one of the cytoplasm. We also find that nuclei belonging to flocking monolayers, subjected to larger mechanical perturbations, are about two time stiffer than nuclei belonging to dynamically arrested monolayers, in agreement with atomic force microscopy results. Our results demonstrate a non-invasive route to the determination of nuclear relative stiffness for cells in a monolayer.

Metaheuristic based Optimization Methods for the Segmentation of Tuberculosis Sputum Smear Images

Tuberculosis (TB) is a worldwide health crisis and second primary infectious disease that causes death. An attempt has been made to detect the presence of bacilli in sputum smears. The smear images recorded under standard image acquisition protocol are segmented by metaheuristic-based methods. Morphological operators are embedded in Ant Colony Optimization (ACO) and Particle Swarm Optimization (PSO) segmentation to retain concavity of rod-shaped bacilli. Results demonstrate that hybrid ACO segmentation is able to retain the shape of bacilli in TB images. Segmented images are validated with ground truth using overlap, distance and probability-based measures. Significant shape-based features such as area, perimeter, compactness, shape factor and tortuosity are extracted from the segmented images. It is observed that hybrid method preserves more edges, detects the presence of bacilli and facilitates direct segmentation with reduced number of redundant searches to generate edges. Thus this hybrid ACO-morphology segmentation technique aid in the diagnostic relevance of TB images.

Image-based pooled whole-genome CRISPRi screening for subcellular phenotypes

Genome-wide CRISPR screens have transformed our ability to systematically interrogate human gene function, but are currently limited to a subset of cellular phenotypes. We report a novel pooled screening approach for a wider range of cellular and subtle subcellular phenotypes. Machine learning and convolutional neural network models are trained on the subcellular phenotype to be queried. Genome-wide screening then utilizes cells stably expressing dCas9-KRAB (CRISPRi), photoactivatable fluorescent protein (PA-mCherry), and a lentiviral guide RNA (gRNA) pool. Cells are screened by using microscopy and classified by artificial intelligence (AI) algorithms, which precisely identify the genetically altered phenotype. Cells with the phenotype of interest are photoactivated and isolated via flow cytometry, and the gRNAs are identified by sequencing. A proof-of-concept screen accurately identified PINK1 as essential for Parkin recruitment to mitochondria. A genome-wide screen identified factors mediating TFEB relocation from the nucleus to the cytosol upon prolonged starvation. Twenty-one of the 64 hits called by the neural network model were independently validated, revealing new effectors of TFEB subcellular localization. This approach, AI-photoswitchable screening (AI-PS), offers a novel screening platform capable of classifying a broad range of mammalian subcellular morphologies, an approach largely unattainable with current methodologies at genome-wide scale.

Limited-view binary tomography reconstruction assisted by shape centroid

In this paper, the binary tomographic reconstruction problem for very limited projection data availability is considered. Being this inverse problem highly ill-posed, we propose a new reconstruction model that uses a shape centroid-based regularization term, i.e., we assume that the center of gravity of the object of interest is known, at least approximately, in advance. Motivation for this regularization is found in the close connection between the projection data and the object centroid, as we will show. Experimental evaluation underpins that reasonable results can be obtained from practically minimal amount of projection data, gathered from just one projection direction.

EVICAN-a balanced dataset for algorithm development in cell and nucleus segmentation

Motivation

Deep learning use for quantitative image analysis is exponentially increasing. However, training accurate, widely deployable deep learning algorithms requires a plethora of annotated (ground truth) data. Image collections must contain not only thousands of images to provide sufficient example objects (i.e. cells), but also contain an adequate degree of image heterogeneity.

Results

We present a new dataset, EVICAN—Expert visual cell annotation, comprising partially annotated grayscale images of 30 different cell lines from multiple microscopes, contrast mechanisms and magnifications that is readily usable as training data for computer vision applications. With 4600 images and ∼26 000 segmented cells, our collection offers an unparalleled heterogeneous training dataset for cell biology deep learning application development.

Availability and implementation

The dataset is freely available (https://edmond.mpdl.mpg.de/imeji/collection/l45s16atmi6Aa4sI?q=). Using a Mask R-CNN implementation, we demonstrate automated segmentation of cells and nuclei from brightfield images with a mean average precision of 61.6 % at a Jaccard Index above 0.5.

Unraveling spatial cellular pattern by computational tissue shuffling

Cell biology relies largely on reproducible visual observations. Unlike cell culture, tissues are heterogeneous, making difficult the collection of biological replicates that would spotlight a precise location. In consequence, there is no standard approach for estimating the statistical significance of an observed pattern in a tissue sample. Here, we introduce SET (for Synthesis of Epithelial Tissue), a method that can accurately reconstruct the cell tessellation formed by an epithelium in a microscopy image as well as thousands of alternative synthetic tessellations made of the exact same cells. SET can build an accurate null distribution to statistically test if any local pattern is necessarily the result of a process, or if it could be explained by chance in the given context. We provide examples in various tissues where visible, and invisible, cell and subcellular patterns are unraveled in a statistically significant manner using a single image and without any parameter settings.

Pomegranate: 2D segmentation and 3D reconstruction for fission yeast and other radially symmetric cells

Three-dimensional (3D) segmentation of cells in microscopy images is crucial to accurately capture signals that extend across optical sections. Using brightfield images for segmentation has the advantage of being minimally phototoxic and leaving all other channels available for signals of interest. However, brightfield images only readily provide information for two-dimensional (2D) segmentation. In radially symmetric cells, such as fission yeast and many bacteria, this 2D segmentation can be computationally extruded into the third dimension. However, current methods typically make the simplifying assumption that cells are straight rods. Here, we report Pomegranate, a pipeline that performs the extrusion into 3D using spheres placed along the topological skeletons of the 2D-segmented regions. The diameter of these spheres adapts to the cell diameter at each position. Thus, Pomegranate accurately represents radially symmetric cells in 3D even if cell diameter varies and regardless of whether a cell is straight, bent or curved. We have tested Pomegranate on fission yeast and demonstrate its ability to 3D segment wild-type cells as well as classical size and shape mutants. The pipeline is available as a macro for the open-source image analysis software Fiji/ImageJ. 2D segmentations created within or outside Pomegranate can serve as input, thus making this a valuable extension to the image analysis portfolio already available for fission yeast and other radially symmetric cell types.

Fluorescence anisotropy imaging in drug discovery

Non-invasive measurement of drug-target engagement can provide critical insights in the molecular pharmacology of small molecule drugs. Fluorescence polarization/fluorescence anisotropy measurements are commonly employed in protein/cell screening assays. However, the expansion of such measurements to the in vivo setting has proven difficult until recently. With the advent of high-resolution fluorescence anisotropy microscopy it is now possible to perform kinetic measurements of intracellular drug distribution and target engagement in commonly used mouse models. In this review we discuss the background, current advances and future perspectives in intravital fluorescence anisotropy measurements to derive pharmacokinetic and pharmacodynamic measurements in single cells and whole organs.

Globally optimal segmentation of cell nuclei in fluorescence microscopy images using shape and intensity information

Accurate and efficient segmentation of cell nuclei in fluorescence microscopy images plays a key role in many biological studies. Besides coping with image noise and other imaging artifacts, the separation of touching and partially overlapping cell nuclei is a major challenge. To address this, we introduce a globally optimal model-based approach for cell nuclei segmentation which jointly exploits shape and intensity information. Our approach is based on implicitly parameterized shape models, and we propose single-object and multi-object schemes. In the single-object case, the used shape parameterization leads to convex energies which can be directly minimized without requiring approximation. The multi-object scheme is based on multiple collaborating shapes and has the advantage that prior detection of individual cell nuclei is not needed. This scheme performs joint segmentation and cluster splitting. We describe an energy minimization scheme which converges close to global optima and exploits convex optimization such that our approach does not depend on the initialization nor suffers from local energy minima. The proposed approach is robust and computationally efficient. In contrast, previous shape-based approaches for cell segmentation either are computationally expensive, not globally optimal, or do not jointly exploit shape and intensity information. We successfully applied our approach to fluorescence microscopy images of five different cell types and performed a quantitative comparison with previous methods.

Automated cell segmentation in FIJI® using the DRAQ5 nuclear dye

BACKGROUND

Image segmentation and quantification are essential steps in quantitative cellular analysis. In this work, we present a fast, customizable, and unsupervised cell segmentation method that is based solely on Fiji (is just ImageJ)®, one of the most commonly used open-source software packages for microscopy analysis. In our method, the "leaky" fluorescence from the DNA stain DRAQ5 is used for automated nucleus detection and 2D cell segmentation.

RESULTS

Based on an evaluation with HeLa cells compared to human counting, our algorithm reached accuracy levels above 92% and sensitivity levels of 94%. 86% of the evaluated cells were segmented correctly, and the average intersection over union score of detected segmentation frames to manually segmented cells was above 0.83. Using this approach, we quantified changes in the projected cell area, circularity, and aspect ratio of THP-1 cells differentiating from monocytes to macrophages, observing significant cell growth and a transition from circular to elongated form. In a second application, we quantified changes in the projected cell area of CHO cells upon lowering the incubation temperature, a common stimulus to increase protein production in biotechnology applications, and found a stark decrease in cell area.

CONCLUSIONS

Our method is straightforward and easily applicable using our staining protocol. We believe this method will help other non-image processing specialists use microscopy for quantitative image analysis.

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

Background

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

Results

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

Conclusions

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

Electronic supplementary material

The online version of this article (10.1186/s12859-018-2375-z) contains supplementary material, which is available to authorized users.

Quantitative 3D analysis of complex single border cell behaviors in coordinated collective cell migration

Understanding the mechanisms of collective cell migration is crucial for cancer metastasis, wound healing and many developmental processes. Imaging a migrating cluster in vivo is feasible, but the quantification of individual cell behaviours remains challenging. We have developed an image analysis toolkit, CCMToolKit, to quantify the Drosophila border cell system. In addition to chaotic motion, previous studies reported that the migrating cells are able to migrate in a highly coordinated pattern. We quantify the rotating and running migration modes in 3D while also observing a range of intermediate behaviours. Running mode is driven by cluster external protrusions. Rotating mode is associated with cluster internal cell extensions that could not be easily characterized. Although the cluster moves slower while rotating, individual cells retain their mobility and are in fact slightly more active than in running mode. We also show that individual cells may exchange positions during migration.

Hybrid segmentation of fluorescent Leschmania-infected images using a watersched and combined region merging based method

Automatic parasite segmentation in fluorescent images is of high importance as it serves as an easier and faster tool for detecting and counting parasites in each focus. In this paper we present a hybrid segmentation for the Promastigote form of Leishmania parasites in Indirect Immunofluorescence (IIF) images, combining edge and region-based techniques through the morphological algorithm of watershed. The proposed approach deals first with a pre-processing step to correct illumination non-uniformities in the fluorescence Leishmania-infected images before performing the initial segmentation by means of the watershed algorithm. A merging step using joint region homogeneity and edge integrity criteria is then applied to improve the segmentation results. Segmentation tests of 1438 parasites from 40 collected IIF images illustrate the efficiency of our approach.

Detection and tracking of overlapping cell nuclei for large scale mitosis analyses

Background

Cell culture on printed micropatterns slides combined with automated fluorescent microscopy allows for extraction of tens of thousands of videos of small isolated growing cell clusters. The analysis of such large dataset in space and time is of great interest to the community in order to identify factors involved in cell growth, cell division or tissue formation by testing multiples conditions. However, cells growing on a micropattern tend to be tightly packed and to overlap with each other. Consequently, image analysis of those large dynamic datasets with no possible human intervention has proven impossible using state of the art automated cell detection methods.

Results

Here, we propose a fully automated image analysis approach to estimate the number, the location and the shape of each cell nucleus, in clusters at high throughput. The method is based on a robust fit of Gaussian mixture models with two and three components on each frame followed by an analysis over time of the fitting residual and two other relevant features. We use it to identify with high precision the very first frame containing three cells. This allows in our case to measure a cell division angle on each video and to construct division angle distributions for each tested condition. We demonstrate the accuracy of our method by validating it against manual annotation on about 4000 videos of cell clusters.

Conclusions

The proposed approach enables the high throughput analysis of video sequences of isolated cell clusters obtained using micropatterns. It relies only on two parameters that can be set robustly as they reduce to the average cell size and intensity.

Curvelet initialized level set cell segmentation for touching cells in low contrast images

Cell segmentation is an important element of automatic cell analysis. This paper proposes a method to extract the cell nuclei and the cell boundaries of touching cells in low contrast images. First, the contrast of the low contrast cell images is improved by a combination of multiscale top hat filter and h-maxima. Then, a curvelet initialized level set method has been proposed to detect the cell nuclei and the boundaries. The image enhancement results have been verified using PSNR (Peak Signal to noise ratio) and the segmentation results have been verified using accuracy, sensitivity and precision metrics. The results show improved values of the performance metrics with the proposed method.

Cell recognition based on topological sparse coding for microscopy imaging of focused ultrasound treatment

BACKGROUND

Ultrasound is considered a reliable, widely available, non-invasive, and inexpensive imaging technique for assessing and detecting the development phases of cancer; both in vivo and ex vivo, and for understanding the effects on cell cycle and viability after ultrasound treatment.

METHODS

Based on the topological continuity characteristics, and that adjacent points or areas represent similar features, we propose a topological penalized convex objective function of sparse coding, to recognize similar cell phases.

RESULTS

This method introduces new features using a deep learning method of sparse coding with topological continuity characteristics. Large-scale comparison tests demonstrate that the RAW can outperform SIFT GIST and HoG as the input features with this method, achieving higher sensitivity, specificity, F1 score, and accuracy.

CONCLUSIONS

Experimental results show that the proposed topological sparse coding technique is valid and effective for extracting new features, and the proposed system was effective for cell recognition of microscopy images of theMDA-MB-231 cell line. This method allows features from sparse coding learning methods to have topological continuity characteristics, and the RAW features are more applicable for the deep learning of the topological sparse coding method than SIFT GIST and HoG.

Light sheet fluorescence microscopy (LSFM): past, present and future

Light sheet fluorescence microscopy (LSFM) has emerged as an important imaging modality to follow biology in live 3D samples over time with reduced phototoxicity and photobleaching. In particular, LSFM has been instrumental in revealing the detail of early embryonic development of Zebrafish, Drosophila, and C. elegans. Open access projects, DIY-SPIM, OpenSPIM, and OpenSPIN, now allow LSFM to be set-up easily and at low cost. The aim of this paper is to facilitate the set-up and use of LSFM by reviewing and comparing open access projects, image processing tools and future challenges.

Automated high-throughput analysis of B cell spreading on immobilized antibodies with whole slide imaging

Automated image processing methods enable objective, reproducible and high quality analysis of fluorescent cell images in a reasonable amount of time. Therefore, we propose the application of image processing pipelines based on established segmentation algorithms which can handle massive amounts of whole slide imaging data of multiple fluorescent labeled cells. After automated parameter adaption the segmentation pipelines provide high quality cell delineations revealing significant differences in the spreading of B cells: LPS-activated B cells spread significantly less on anti CD19 mAb than on anti BCR mAb and both processes could be inhibited by the F-actin destabilizing drug Cytochalasin D. Moreover, anti CD19 mAb induce a more symmetrical spreading than anti BCR mAb as reflected by the higher cell circularity.

Learning-guided automatic three dimensional synapse quantification for drosophila neurons

BACKGROUND

The subcellular distribution of synapses is fundamentally important for the assembly, function, and plasticity of the nervous system. Automated and effective quantification tools are a prerequisite to large-scale studies of the molecular mechanisms of subcellular synapse distribution. Common practices for synapse quantification in neuroscience labs remain largely manual or semi-manual. This is mainly due to computational challenges in automatic quantification of synapses, including large volume, high dimensions and staining artifacts. In the case of confocal imaging, optical limit and xy-z resolution disparity also require special considerations to achieve the necessary robustness.

RESULTS

A novel algorithm is presented in the paper for learning-guided automatic recognition and quantification of synaptic markers in 3D confocal images. The method developed a discriminative model based on 3D feature descriptors that detected the centers of synaptic markers. It made use of adaptive thresholding and multi-channel co-localization to improve the robustness. The detected markers then guided the splitting of synapse clumps, which further improved the precision and recall of the detected synapses. Algorithms were tested on lobula plate tangential cells (LPTCs) in the brain of Drosophila melanogaster, for GABAergic synaptic markers on axon terminals as well as dendrites.

CONCLUSIONS

The presented method was able to overcome the staining artifacts and the fuzzy boundaries of synapse clumps in 3D confocal image, and automatically quantify synaptic markers in a complex neuron such as LPTC. Comparison with some existing tools used in automatic 3D synapse quantification also proved the effectiveness of the proposed method.

Towards automatic image analysis and assessment of the multicellular apoptosis process

Apoptotic programmed cell death (PCD) is a fundamental aspect of developmental maturation. However, the authors' understanding of apoptosis, especially in the multi-cell regime, is incomplete because of the difficulty of identifying dying cells by conventional strategies. Real-time in vivo microscopy of Drosophila, an excellent model system for studying the PCD during development, has been used to uncover plausible collective apoptosis at the tissue level, although the dynamic regulation of the process remains to be deciphered. In this work, the authors have developed an image-analysis program that can quantitatively analyse time-lapse microscopy of live tissues undergoing apoptosis with a fluorescent nuclear marker, and subsequently extract the spatiotemporal patterns of multicellular response. The program can process a large number of cells (>10³) automatically tracked across sets of image frames. It is applied to characterise the apoptosis of Drosophila wing epithelium at eclosion. Using the natural anatomic structures as reference, the authors identify dynamic patterns in the progression of PCD within the Drosophila tissues. The results not only confirm the previously observed collective multi-cell behaviour from a quantitative perspective, but also reveal a plausible role played by the anatomic structures, such as the wing veins, in the PCD propagation across the Drosophila wing.

An improved joint optimization of multiple level set functions for the segmentation of overlapping cervical cells

In this paper, we present an improved algorithm for the segmentation of cytoplasm and nuclei from clumps of overlapping cervical cells. This problem is notoriously difficult because of the degree of overlap among cells, the poor contrast of cell cytoplasm and the presence of mucus, blood, and inflammatory cells. Our methodology addresses these issues by utilizing a joint optimization of multiple level set functions, where each function represents a cell within a clump, that have both unary (intracell) and pairwise (intercell) constraints. The unary constraints are based on contour length, edge strength, and cell shape, while the pairwise constraint is computed based on the area of the overlapping regions. In this way, our methodology enables the analysis of nuclei and cytoplasm from both free-lying and overlapping cells. We provide a systematic evaluation of our methodology using a database of over 900 images generated by synthetically overlapping images of free-lying cervical cells, where the number of cells within a clump is varied from 2 to 10 and the overlap coefficient between pairs of cells from 0.1 to 0.5. This quantitative assessment demonstrates that our methodology can successfully segment clumps of up to 10 cells, provided the overlap between pairs of cells is <;0.2. Moreover, if the clump consists of three or fewer cells, then our methodology can successfully segment individual cells even when the overlap is ~0.5. We also evaluate our approach quantitatively and qualitatively on a set of 16 extended depth of field images, where we are able to segment a total of 645 cells, of which only ~10% are free-lying. Finally, we demonstrate that our method of cell nuclei segmentation is competitive when compared with the current state of the art.

Fourier-ring descriptor to characterize rare circulating cells from images generated using immunofluorescence microscopy

We address the problem of subclassification of rare circulating cells using data driven feature selection from images of candidate circulating tumor cells from patients diagnosed with breast, prostate, or lung cancer. We determine a set of low level features which can differentiate among candidate cell types. We have implemented an image representation based on concentric Fourier rings (FRDs) which allow us to exploit size variations and morphological differences among cells while being rotationally invariant. We discuss potential clinical use in the context of treatment monitoring for cancer patients with metastatic disease.

Retrospective non-uniform illumination correction techniques in images of tuberculosis

Image pre-processing is highly significant in automated analysis of microscopy images. In this work, non-uniform illumination correction has been attempted using the surface fitting method (SFM), multiple regression method (MRM), and bidirectional empirical mode decomposition (BEMD) in digital microscopy images of tuberculosis (TB). The sputum smear positive and negative images recorded under a standard image acquisition protocol were subjected to illumination correction techniques and evaluated by error and statistical measures. Results show that SFM performs more efficiently than MRM or BEMD. The SFM produced sharp images of TB bacilli with better contrast. To further validate the results, multifractal analysis was performed that showed distinct variation before and after implementation of illumination correction by SFM. Results demonstrate that after illumination correction, there is a 26% increase in the number of bacilli, which aids in classification of the TB images into positive and negative, as TB positivity depends on the count of bacilli.

Detection and measurement of the intracellular calcium variation in follicular cells

This work presents a new method for measuring the variation of intracellular calcium in follicular cells. The proposal consists in two stages: (i) the detection of the cell's nuclei and (ii) the analysis of the fluorescence variations. The first stage is performed via watershed modified transformation, where the process of labeling is controlled. The detection process uses the contours of the cells as descriptors, where they are enhanced with a morphological filter that homogenizes the luminance variation of the image. In the second stage, the fluorescence variations are modeled as an exponential decreasing function, where the fluorescence variations are highly correlated with the changes of intracellular free Ca(2+). Additionally, it is introduced a new morphological called medium reconstruction process, which helps to enhance the data for the modeling process. This filter exploits the undermodeling and overmodeling properties of reconstruction operators, such that it preserves the structure of the original signal. Finally, an experimental process shows evidence of the capabilities of the proposal.

Digital reconstruction of the cell body in dense neural circuits using a spherical-coordinated variational model

Mapping the neuronal circuits is essential to understand brain function. Recent technological advancements have made it possible to acquire the brain atlas at single cell resolution. Digital reconstruction of the neural circuits down to this level across the whole brain would significantly facilitate brain studies. However, automatic reconstruction of the dense neural connections from microscopic image still remains a challenge. Here we developed a spherical-coordinate based variational model to reconstruct the shape of the cell body i.e. soma, as one of the procedures for this purpose. When intuitively processing the volumetric images in the spherical coordinate system, the reconstruction of somas with variational model is no longer sensitive to the interference of the complicated neuronal morphology, and could automatically and robustly achieve accurate soma shape regardless of the dense spatial distribution, and diversity in cell size, and morphology. We believe this method would speed drawing the neural circuits and boost brain studies.

Tracking epithelial cell junctions in C. elegans embryogenesis with active contours guided by SIFT flow

Quantitative analysis of cell shape in live samples is an important goal in developmental biology. Automated or semi-automated segmentation and tracking of cell nuclei has been successfully implemented in several biological systems. Segmentation and tracking of cell surfaces has been more challenging. Here, we present a new approach to tracking cell junctions in the developing epidermis of C. elegans embryos. Epithelial junctions as visualized with DLG-1::GFP form lines at the subapical circumference of differentiated epidermal cells and delineate changes in epidermal cell shape and position. We develop and compare two approaches for junction segmentation. For the first method (projection approach), 3-D cell boundaries are projected into 2D for segmentation using active contours with a nonintersecting force, and subsequently tracked using scale-invariant feature transform (SIFT) flow. The resulting 2-D tracked boundaries are then back-projected into 3-D space. The second method (volumetric approach) uses a 3-D extended version of active contours guided by SIFT flow in 3-D space. In both methods, cell junctions are manually located at the first time point and tracked in a fully automated way for the remainder of the video. Using these methods, we have generated the first quantitative description of ventral epidermal cell movements and shape changes during epidermal enclosure.

Automated image segmentation of haematoxylin and eosin stained skeletal muscle cross-sections

The ability to accurately and efficiently quantify muscle morphology is essential to determine the physiological relevance of a variety of muscle conditions including growth, atrophy and repair. There is agreement across the muscle biology community that important morphological characteristics of muscle fibres, such as cross-sectional area, are critical factors that determine the health and function (e.g. quality) of the muscle. However, at this time, quantification of muscle characteristics, especially from haematoxylin and eosin stained slides, is still a manual or semi-automatic process. This procedure is labour-intensive and time-consuming. In this paper, we have developed and validated an automatic image segmentation algorithm that is not only efficient but also accurate. Our proposed automatic segmentation algorithm for haematoxylin and eosin stained skeletal muscle cross-sections consists of two major steps: (1) A learning-based seed detection method to find the geometric centres of the muscle fibres, and (2) a colour gradient repulsive balloon snake deformable model that adopts colour gradient in Luv colour space. Automatic quantification of muscle fibre cross-sectional areas using the proposed method is accurate and efficient, providing a powerful automatic quantification tool that can increase sensitivity, objectivity and efficiency in measuring the morphometric features of the haematoxylin and eosin stained muscle cross-sections.

Multi-scale Gaussian representation and outline-learning based cell image segmentation

Background

High-throughput genome-wide screening to study gene-specific functions, e.g. for drug discovery, demands fast automated image analysis methods to assist in unraveling the full potential of such studies. Image segmentation is typically at the forefront of such analysis as the performance of the subsequent steps, for example, cell classification, cell tracking etc., often relies on the results of segmentation.

Methods

We present a cell cytoplasm segmentation framework which first separates cell cytoplasm from image background using novel approach of image enhancement and coefficient of variation of multi-scale Gaussian scale-space representation. A novel outline-learning based classification method is developed using regularized logistic regression with embedded feature selection which classifies image pixels as outline/non-outline to give cytoplasm outlines. Refinement of the detected outlines to separate cells from each other is performed in a post-processing step where the nuclei segmentation is used as contextual information.

Results and conclusions

We evaluate the proposed segmentation methodology using two challenging test cases, presenting images with completely different characteristics, with cells of varying size, shape, texture and degrees of overlap. The feature selection and classification framework for outline detection produces very simple sparse models which use only a small subset of the large, generic feature set, that is, only 7 and 5 features for the two cases. Quantitative comparison of the results for the two test cases against state-of-the-art methods show that our methodology outperforms them with an increase of 4-9% in segmentation accuracy with maximum accuracy of 93%. Finally, the results obtained for diverse datasets demonstrate that our framework not only produces accurate segmentation but also generalizes well to different segmentation tasks.

CellSegm - a MATLAB toolbox for high-throughput 3D cell segmentation

: The application of fluorescence microscopy in cell biology often generates a huge amount of imaging data. Automated whole cell segmentation of such data enables the detection and analysis of individual cells, where a manual delineation is often time consuming, or practically not feasible. Furthermore, compared to manual analysis, automation normally has a higher degree of reproducibility. CellSegm, the software presented in this work, is a Matlab based command line software toolbox providing an automated whole cell segmentation of images showing surface stained cells, acquired by fluorescence microscopy. It has options for both fully automated and semi-automated cell segmentation. Major algorithmic steps are: (i) smoothing, (ii) Hessian-based ridge enhancement, (iii) marker-controlled watershed segmentation, and (iv) feature-based classfication of cell candidates. Using a wide selection of image recordings and code snippets, we demonstrate that CellSegm has the ability to detect various types of surface stained cells in 3D. After detection and outlining of individual cells, the cell candidates can be subject to software based analysis, specified and programmed by the end-user, or they can be analyzed by other software tools. A segmentation of tissue samples with appropriate characteristics is also shown to be resolvable in CellSegm. The command-line interface of CellSegm facilitates scripting of the separate tools, all implemented in Matlab, offering a high degree of flexibility and tailored workflows for the end-user. The modularity and scripting capabilities of CellSegm enable automated workflows and quantitative analysis of microscopic data, suited for high-throughput image based screening.

Segmentation and morphometric analysis of cells from fluorescence microscopy images of cytoskeletons

We developed a method to reconstruct cell geometry from confocal fluorescence microscopy images of the cytoskeleton. In the method, region growing was implemented twice. First, it was applied to the extracellular regions to differentiate them from intracellular noncytoskeletal regions, which both appear black in fluorescence microscopy imagery, and then to cell regions for cell identification. Analysis of morphological parameters revealed significant changes in cell shape associated with cytoskeleton disruption, which offered insight into the mechanical role of the cytoskeleton in maintaining cell shape. The proposed segmentation method is promising for investigations on cell morphological changes with respect to internal cytoskeletal structures.

Chapter 17: bioimage informatics for systems pharmacology

Recent advances in automated high-resolution fluorescence microscopy and robotic handling have made the systematic and cost effective study of diverse morphological changes within a large population of cells possible under a variety of perturbations, e.g., drugs, compounds, metal catalysts, RNA interference (RNAi). Cell population-based studies deviate from conventional microscopy studies on a few cells, and could provide stronger statistical power for drawing experimental observations and conclusions. However, it is challenging to manually extract and quantify phenotypic changes from the large amounts of complex image data generated. Thus, bioimage informatics approaches are needed to rapidly and objectively quantify and analyze the image data. This paper provides an overview of the bioimage informatics challenges and approaches in image-based studies for drug and target discovery. The concepts and capabilities of image-based screening are first illustrated by a few practical examples investigating different kinds of phenotypic changes caEditorsused by drugs, compounds, or RNAi. The bioimage analysis approaches, including object detection, segmentation, and tracking, are then described. Subsequently, the quantitative features, phenotype identification, and multidimensional profile analysis for profiling the effects of drugs and targets are summarized. Moreover, a number of publicly available software packages for bioimage informatics are listed for further reference. It is expected that this review will help readers, including those without bioimage informatics expertise, understand the capabilities, approaches, and tools of bioimage informatics and apply them to advance their own studies.

Fast automatic segmentation of nuclei in microscopy images of tissue sections

In this paper, we present a segmentation method for nuclei in microscopy images of tissue sections. The proposed method is completely automatic and performs well in the conflicting aims of speed efficiency, detection accuracy and shape fitting. It proposes an efficient alternative to existing methods ([1], [4]), in achieving the three main usual segmentation steps: (i) background extraction, (ii) seed finding and (iii) seed growing. Eventually, some significant results are depicted and discussed.

Efficient globally optimal segmentation of cells in fluorescence microscopy images using level sets and convex energy functionals

In high-throughput applications, accurate and efficient segmentation of cells in fluorescence microscopy images is of central importance for the quantification of protein expression and the understanding of cell function. We propose an approach for segmenting cell nuclei which is based on active contours using level sets and convex energy functionals. Compared to previous work, our approach determines the global solution. Thus, the approach does not suffer from local minima and the segmentation result does not depend on the initialization. We consider three different well-known energy functionals for active contour-based segmentation and introduce convex formulations of these functionals. We also suggest a numeric approach for efficiently computing the solution. The performance of our approach has been evaluated using fluorescence microscopy images from different experiments comprising different cell types. We have also performed a quantitative comparison with previous segmentation approaches.

Automatic cell counting in vivo in the larval nervous system of Drosophila

Identification and counting of cells is necessary to test biological hypotheses, for instance of nervous system formation, disease, degeneration, injury and regeneration, but manual counting is time consuming, tedious, and subject to bias. The fruit fly Drosophila is a widely used model organism to analyse gene function, and most research is carried out in the intact animal or in whole organs, rather than in cell culture. Inferences on gene function require that cell counts are known from these sample types. Image processing and pattern recognition techniques are appropriate tools to automate cell counting. However, counting cells in Drosophila is a complex task: variations in immunohistochemical markers and developmental stages result in images of very different properties, rendering it challenging to identify true cells. Here, we present a technique for counting automatically larval glial cells in three dimensions, from confocal microscopy serial optical sections. Local outlier thresholding and domes are combined to find the cells. Shape descriptors extracted from a data set are used to characterize cells and avoid oversegmentation. Morphological operators are employed to divide cells that could otherwise be missed. The method is accurate and very fast, and treats all samples equally and objectively, rendering all data comparable across specimens. Our method is also applicable to identify cells labelled with other nuclear markers and in sections of mouse tissues.

A fast, automatic segmentation algorithm for locating and delineating touching cell boundaries in imaged histopathology

BACKGROUND

Automated analysis of imaged histopathology specimens could potentially provide support for improved reliability in detection and classification in a range of investigative and clinical cancer applications. Automated segmentation of cells in the digitized tissue microarray (TMA) is often the prerequisite for quantitative analysis. However overlapping cells usually bring significant challenges for traditional segmentation algorithms.

OBJECTIVES

In this paper, we propose a novel, automatic algorithm to separate overlapping cells in stained histology specimens acquired using bright-field RGB imaging.

METHODS

It starts by systematically identifying salient regions of interest throughout the image based upon their underlying visual content. The segmentation algorithm subsequently performs a quick, voting based seed detection. Finally, the contour of each cell is obtained using a repulsive level set deformable model using the seeds generated in the previous step. We compared the experimental results with the most current literature, and the pixel wise accuracy between human experts' annotation and those generated using the automatic segmentation algorithm.

RESULTS

The method is tested with 100 image patches which contain more than 1000 overlapping cells. The overall precision and recall of the developed algorithm is 90% and 78%, respectively. We also implement the algorithm on GPU. The parallel implementation is 22 times faster than its C/C++ sequential implementation.

CONCLUSION

The proposed segmentation algorithm can accurately detect and effectively separate each of the overlapping cells. GPU is proven to be an efficient parallel platform for overlapping cell segmentation.

Robust segmentation of overlapping cells in histopathology specimens using parallel seed detection and repulsive level set

Automated image analysis of histopathology specimens could potentially provide support for early detection and improved characterization of breast cancer. Automated segmentation of the cells comprising imaged tissue microarrays (TMAs) is a prerequisite for any subsequent quantitative analysis. Unfortunately, crowding and overlapping of cells present significant challenges for most traditional segmentation algorithms. In this paper, we propose a novel algorithm that can reliably separate touching cells in hematoxylin-stained breast TMA specimens that have been acquired using a standard RGB camera. The algorithm is composed of two steps. It begins with a fast, reliable object center localization approach that utilizes single-path voting followed by mean-shift clustering. Next, the contour of each cell is obtained using a level set algorithm based on an interactive model. We compared the experimental results with those reported in the most current literature. Finally, performance was evaluated by comparing the pixel-wise accuracy provided by human experts with that produced by the new automated segmentation algorithm. The method was systematically tested on 234 image patches exhibiting dense overlap and containing more than 2200 cells. It was also tested on whole slide images including blood smears and TMAs containing thousands of cells. Since the voting step of the seed detection algorithm is well suited for parallelization, a parallel version of the algorithm was implemented using graphic processing units (GPU) that resulted in significant speedup over the C/C++ implementation.

A NEW SEPARATION ALGORITHM FOR OVERLAPPING BLOOD CELLS USING SHAPE ANALYSIS

Blood cell classification is widely used in the biomedical research. Appropriate separation between touching and overlapping blood cells is of great importance for the successful classification. In this paper, a novel algorithm based on shape information is proposed for the separation of partially overlapping blood cells. It is motivated by the problem of finding the borders between adjacent blood cells in microscopy images. The algorithm can not only separate the simple touching blood cells, but also large clusters of overlapping blood cells. In addition, this algorithm can be adopted for other applications, where separation between touching and overlapping particles is required.

Fast globally optimal segmentation of cells in fluorescence microscopy images

Accurate and efficient segmentation of cells in fluorescence microscopy images is of central importance for the quantification of protein expression in high-throughput screening applications. We propose a new approach for segmenting cell nuclei which is based on active contours and convex energy functionals. Compared to previous work, our approach determines the global solution. Thus, the approach does not suffer from local minima and the segmentation result does not depend on the initialization. We also suggest a numeric approach for efficiently computing the solution. The performance of our approach has been evaluated using fluorescence microscopy images of different cell types. We have also performed a quantitative comparison with previous segmentation approaches.

Comparison of parameter-adapted segmentation methods for fluorescence micrographs

Interpreting images from fluorescence microscopy is often a time-consuming task with poor reproducibility. Various image processing routines that can help investigators evaluate the images are therefore useful. The critical aspect for a reliable automatic image analysis system is a robust segmentation algorithm that can perform accurate segmentation for different cell types. In this study, several image segmentation methods were therefore compared and evaluated in order to identify the most appropriate segmentation schemes that are usable with little new parameterization and robustly with different types of fluorescence-stained cells for various biological and biomedical tasks. The study investigated, compared, and enhanced four different methods for segmentation of cultured epithelial cells. The maximum-intensity linking (MIL) method, an improved MIL, a watershed method, and an improved watershed method based on morphological reconstruction were used. Three manually annotated datasets consisting of 261, 817, and 1,333 HeLa or L929 cells were used to compare the different algorithms. The comparisons and evaluations showed that the segmentation performance of methods based on the watershed transform was significantly superior to the performance of the MIL method. The results also indicate that using morphological opening by reconstruction can improve the segmentation of cells stained with a marker that exhibits the dotted surface of cells.

Oriented Markov random field based dendritic spine segmentation for fluorescence microscopy images

Dendritic spines have been shown to be closely related to various functional properties of the neuron. Usually dendritic spines are manually labeled to analyze their morphological changes, which is very time-consuming and susceptible to operator bias, even with the assistance of computers. To deal with these issues, several methods have been recently proposed to automatically detect and measure the dendritic spines with little human interaction. However, problems such as degraded detection performance for images with larger pixel size (e.g. 0.125 μm/pixel instead of 0.08 μm/pixel) still exist in these methods. Moreover, the shapes of detected spines are also distorted. For example, the "necks" of some spines are missed. Here we present an oriented Markov random field (OMRF) based algorithm which improves spine detection as well as their geometric characterization. We begin with the identification of a region of interest (ROI) containing all the dendrites and spines to be analyzed. For this purpose, we introduce an adaptive procedure for identifying the image background. Next, the OMRF model is discussed within a statistical framework and the segmentation is solved as a maximum a posteriori estimation (MAP) problem, whose optimal solution is found by a knowledge-guided iterative conditional mode (KICM) algorithm. Compared with the existing algorithms, the proposed algorithm not only provides a more accurate representation of the spine shape, but also improves the detection performance by more than 50% with regard to reducing both the misses and false detection.

Evolving generalized Voronoi diagrams for accurate cellular image segmentation

Analyzing cellular morphologies on a cell-by-cell basis is vital for drug discovery, cell biology, and many other biological studies. Interactions between cells in their culture environments cause cells to touch each other in acquired microscopy images. Because of this phenomenon, cell segmentation is a challenging task, especially when the cells are of similar brightness and of highly variable shapes. The concept of topological dependence and the maximum common boundary (MCB) algorithm are presented in our previous work (Yu et al., Cytometry Part A 2009;75A:289-297). However, the MCB algorithm suffers a few shortcomings, such as low computational efficiency and difficulties in generalizing to higher dimensions. To overcome these limitations, we present the evolving generalized Voronoi diagram (EGVD) algorithm. Utilizing image intensity and geometric information, EGVD preserves topological dependence easily in both 2D and 3D images, such that touching cells can be segmented satisfactorily. A systematic comparison with other methods demonstrates that EGVD is accurate and much more efficient.

Segmentation of fluorescence microscopy cell images using unsupervised mining

The accurate measurement of cell and nuclei contours are critical for the sensitive and specific detection of changes in normal cells in several medical informatics disciplines. Within microscopy, this task is facilitated using fluorescence cell stains, and segmentation is often the first step in such approaches. Due to the complex nature of cell issues and problems inherent to microscopy, unsupervised mining approaches of clustering can be incorporated in the segmentation of cells. In this study, we have developed and evaluated the performance of multiple unsupervised data mining techniques in cell image segmentation. We adapt four distinctive, yet complementary, methods for unsupervised learning, including those based on k-means clustering, EM, Otsu’s threshold, and GMAC. Validation measures are defined, and the performance of the techniques is evaluated both quantitatively and qualitatively using synthetic and recently published real data. Experimental results demonstrate that k-means, Otsu’s threshold, and GMAC perform similarly, and have more precise segmentation results than EM. We report that EM has higher recall values and lower precision results from under-segmentation due to its Gaussian model assumption. We also demonstrate that these methods need spatial information to segment complex real cell images with a high degree of efficacy, as expected in many medical informatics applications.

DeadEasy Mito-Glia: automatic counting of mitotic cells and glial cells in Drosophila

Cell number changes during normal development, and in disease (e.g., neurodegeneration, cancer). Many genes affect cell number, thus functional genetic analysis frequently requires analysis of cell number alterations upon loss of function mutations or in gain of function experiments. Drosophila is a most powerful model organism to investigate the function of genes involved in development or disease in vivo. Image processing and pattern recognition techniques can be used to extract information from microscopy images to quantify automatically distinct cellular features, but these methods are still not very extended in this model organism. Thus cellular quantification is often carried out manually, which is laborious, tedious, error prone or humanly unfeasible. Here, we present DeadEasy Mito-Glia, an image processing method to count automatically the number of mitotic cells labelled with anti-phospho-histone H3 and of glial cells labelled with anti-Repo in Drosophila embryos. This programme belongs to the DeadEasy suite of which we have previously developed versions to count apoptotic cells and neuronal nuclei. Having separate programmes is paramount for accuracy. DeadEasy Mito-Glia is very easy to use, fast, objective and very accurate when counting dividing cells and glial cells labelled with a nuclear marker. Although this method has been validated for Drosophila embryos, we provide an interactive window for biologists to easily extend its application to other nuclear markers and other sample types. DeadEasy MitoGlia is freely available as an ImageJ plug-in, it increases the repertoire of tools for in vivo genetic analysis, and it will be of interest to a broad community of developmental, cancer and neuro-biologists.

Multiple nuclei tracking using integer programming for quantitative cancer cell cycle analysis

Automated cell segmentation and tracking are critical for quantitative analysis of cell cycle behavior using time-lapse fluorescence microscopy. However, the complex, dynamic cell cycle behavior poses new challenges to the existing image segmentation and tracking methods. This paper presents a fully automated tracking method for quantitative cell cycle analysis. In the proposed tracking method, we introduce a neighboring graph to characterize the spatial distribution of neighboring nuclei, and a novel dissimilarity measure is designed based on the spatial distribution, nuclei morphological appearance, migration, and intensity information. Then, we employ the integer programming and division matching strategy, together with the novel dissimilarity measure, to track cell nuclei. We applied this new tracking method for the tracking of HeLa cancer cells over several cell cycles, and the validation results showed that the high accuracy for segmentation and tracking at 99.5% and 90.0%, respectively. The tracking method has been implemented in the cell-cycle analysis software package, DCELLIQ, which is freely available.

Rapid automated cell quantification on HIV microfluidic devices

Lab-chip device analysis often requires high throughput quantification of fluorescent cell images, obtained under different conditions of fluorescent intensity, illumination, focal depth, and optical magnification. Many laboratories still use manual counting--a tedious, expensive process prone to inter-observer variability. The manual counting process can be automated for fast and precise data gathering and reduced manual bias. We present a method to segment and count cells in microfluidic chips that are labeled with a single stain, or multiple stains, using image analysis techniques in Matlab and discuss its advantages over manual counting. Microfluidic based cell capturing devices for HIV monitoring were used to validate our method. Captured CD4(+) CD3(+) T lymphocytes were stained with DAPI, AF488-anti CD4, and AF647-anti CD3 for cell identification. Altogether 4788 (76 x 3 x 21) gray color images were obtained from devices using discarded 10 HIV infected patient whole blood samples (21 devices). We observed that the automatic method performs similarly to manual counting for a small number of cells. However, automated counting is more accurate and more than 100 times faster than manual counting for multiple-color stained cells, especially when large numbers of cells need to be quantified (>500 cells). The algorithm is fully automatic for subsequent microscope images that cover the full device area. It accounts for problems that generally occur in fluorescent lab-chip cell images such as: uneven background, overlapping cell images and cell detection with multiple stains. This method can be used in laboratories to save time and effort, and to increase cell counting accuracy of lab-chip devices for various applications, such as circulating tumor cell detection, cell detection in biosensors, and HIV monitoring devices, i.e. CD4 counts.