A multi-model approach to simultaneous segmentation and classification of heterogeneous populations of cell nuclei in 3D confocal microscope images

Efficient automatic 3D segmentation of cell nuclei for high-content screening

BACKGROUND

High-content screening (HCS) is a pre-clinical approach for the assessment of drug efficacy. On modern platforms, it involves fluorescent image capture using three-dimensional (3D) scanning microscopy. Segmentation of cell nuclei in 3D images is an essential prerequisite to quantify captured fluorescence in cells for screening. However, this segmentation is challenging due to variabilities in cell confluency, drug-induced alterations in cell morphology, and gradual degradation of fluorescence with the depth of scanning. Despite advances in algorithms for segmenting nuclei for HCS, robust 3D methods that are insensitive to these conditions are still lacking.

RESULTS

We have developed an algorithm which first generates a 3D nuclear mask in the original images. Next, an iterative 3D marker-controlled watershed segmentation is applied to downsized images to segment adjacent nuclei under the mask. In the last step, borders of segmented nuclei are adjusted in the original images based on local nucleus and background intensities. The method was developed using a set of 10 3D images. Extensive tests on a separate set of 27 3D images containing 2,367 nuclei demonstrated that our method, in comparison with 6 reference methods, achieved the highest precision (PR = 0.97), recall (RE = 0.88) and F1-score (F1 = 0.93) of nuclei detection. The Jaccard index (JI = 0.83), which reflects the accuracy of nuclei delineation, was similar to that yielded by all reference approaches. Our method was on average more than twice as fast as the reference method that produced the best results. Additional tests carried out on three stacked 3D images comprising heterogenous nuclei yielded average PR = 0.96, RE = 0.84, F1 = 0.89, and JI = 0.80.

CONCLUSIONS

The high-performance metrics yielded by the proposed approach suggest that it can be used to reliably delineate nuclei in 3D images of monolayered and stacked cells exposed to cytotoxic drugs.

Deep Learning for Semantic Segmentation vs. Classification in Computational Pathology: Application to Mitosis Analysis in Breast Cancer Grading

Existing computational approaches have not yet resulted in effective and efficient computer-aided tools that are used in pathologists' daily practice. Focusing on a computer-based qualification for breast cancer diagnosis, the present study proposes two deep learning architectures to efficiently and effectively detect and classify mitosis in a histopathological tissue sample. The first method consists of two parts, entailing a preprocessing of the digital histological image and a free-handcrafted-feature Convolutional Neural Network (CNN) used for binary classification. Results show that the methodology proposed can achieve 95% accuracy in testing, with an F1-score of 94.35%. This result is higher than the results using classical image processing techniques and also higher than the approaches combining CCNs with handcrafted features. The second approach is an end-to-end methodology using semantic segmentation. Results showed that this algorithm can achieve an accuracy higher than 95% in testing and an average Dice index of 0.6, higher than the existing results using CNNs (0.9 F1-score). Additionally, due to the semantic properties of the deep learning approach, an end-to-end deep learning framework is viable to perform both tasks: detection and classification of mitosis. The results show the potential of deep learning in the analysis of Whole Slide Images (WSI) and its integration to computer-aided systems. The extension of this work to whole slide images is also addressed in the last sections; as well as, some computational key points that are useful when constructing a computer-aided-system inspired by the proposed technology.

NucleiNet: A convolutional encoder-decoder network for bio-image denoising

Generic and scalable data analysis procedures are highly demanded by the increasing number of multi-dimensional biomedical data. However, especially for time-lapse biological data, the high level of noise prevents for automated high-throughput analysis methods. The rapid developing of machine-learning methods and particularly deep-learning methods provide new tools and methodologies that can help in the denoising of such data. Using a convolutional encoder-decoder network, one can provide a scalable bio-image platform, called NucleiNet, to automatically segment, classify and track cell nuclei. The proposed method can achieve 0.99 F-score and 0.99 pixel-wise accuracy on C. elegans dataset, which means that over 99% of nuclei can be successfully detected with no merging nuclei found.

Quantification of the Extracellular Matrix Molecule Thrombospondin 1 and Its Pericellular Association in the Brain Using a Semiautomated Computerized Approach

The structure and functions of the extracellular matrix (ECM), its spatial distribution and pericellular association of ECM molecules remain poorly understood. Colocalization of ECM molecules with cell phenotypes through immunohistochemistry can provide crucial insights into their juxtacrine signaling role as well as their structural relevance to tissue architecture. As manual quantification of images introduces intra- and inter-user bias and is cumbersome for high-throughput approaches, we implemented an automated high-throughput method to quantify the spatial distribution and cellular association of one ECM molecule, thrombospondin 1 (TSP1) with two major cell phenotypes, neurons, and astrocytes. The distribution of TSP1 was homogeneous throughout the striatum and cortex along the anterior-posterior axis. TSP1 occupied 8.85% of the striatum and 7.40% in the cortex. TSP1 also associated with 94.58% and 88.45% of neurons in the striatum and cortex. The association with astrocytes was significantly lower at 47.55% and 28.09%. These findings highlight the key role that TSP1 plays in neuron physiology in a healthy brain, but also highlights key regional difference in astrocytes secreting ECM molecules. The semiautomated approach implemented here will improve the throughput and reliability of measuring the distribution and cellular colocalization of ECM molecules.

Algorithmic Mapping and Characterization of the Drug-Induced Phenotypic-Response Space of Parasites Causing Schistosomiasis

Neglected tropical diseases, especially those caused by helminths, constitute some of the most common infections of the world's poorest people. Amongst these, schistosomiasis (bilharzia or 'snail fever'), caused by blood flukes of the genus Schistosoma, ranks second only to malaria in terms of human impact: two hundred million people are infected and close to 800 million are at risk of infection. Drug screening against helminths poses unique challenges: the parasite cannot be cloned and is difficult to target using gene knockouts or RNAi. Consequently, both lead identification and validation involve phenotypic screening, where parasites are exposed to compounds whose effects are determined through the analysis of the ensuing phenotypic responses. The efficacy of leads thus identified derives from one or more or even unknown molecular mechanisms of action. The two most immediate and significant challenges that confront the state-of-the-art in this area are: the development of automated and quantitative phenotypic screening techniques and the mapping and quantitative characterization of the totality of phenotypic responses of the parasite. In this paper, we investigate and propose solutions for the latter problem in terms of the following: (1) mathematical formulation and algorithms that allow rigorous representation of the phenotypic response space of the parasite, (2) application of graph-theoretic and network analysis techniques for quantitative modeling and characterization of the phenotypic space, and (3) application of the aforementioned methodology to analyze the phenotypic space of S. mansoni - one of the etiological agents of schistosomiasis, induced by compounds that target its polo-like kinase 1 (PLK 1) gene - a recently validated drug target. In our approach, first, bio-image analysis algorithms are used to quantify the phenotypic responses of different drugs. Next, these responses are linearly mapped into a low- dimensional space using Principle Component Analysis (PCA). The phenotype space is modeled using neighborhood graphs which are used to represent the similarity amongst the phenotypes. These graphs are characterized and explored using network analysis algorithms. We present a number of results related to both the nature of the phenotypic space of the S. mansoni parasite as well as algorithmic issues encountered in constructing and analyzing the phenotypic-response space. In particular, the phenotype distribution of the parasite was found to have a distinct shape and topology. We have also quantitatively characterized the phenotypic space by varying critical model parameters. Finally, these maps of the phenotype space allows visualization and reasoning about complex relationships between putative drugs and their system-wide effects and can serve as a highly efficient paradigm for assimilating and unifying information from phenotypic screens both during lead identification and lead optimization.

Choosing non-redundant representative subsets of protein sequence data sets using submodular optimization

Selecting a non-redundant representative subset of sequences is a common step in many bioinformatics workflows, such as the creation of non-redundant training sets for sequence and structural models or selection of "operational taxonomic units" from metagenomics data. Previous methods for this task, such as CD-HIT, PISCES, and UCLUST, apply a heuristic threshold-based algorithm that has no theoretical guarantees. We propose a new approach based on submodular optimization. Submodular optimization, a discrete analogue to continuous convex optimization, has been used with great success for other representative set selection problems. We demonstrate that the submodular optimization approach results in representative protein sequence subsets with greater structural diversity than sets chosen by existing methods, using as a gold standard the SCOPe library of protein domain structures. In this setting, submodular optimization consistently yields protein sequence subsets that include more SCOPe domain families than sets of the same size selected by competing approaches. We also show how the optimization framework allows us to design a mixture objective function that performs well for both large and small representative sets. The framework we describe is the best possible in polynomial time (under some assumptions), and it is flexible and intuitive because it applies a suite of generic methods to optimize one of a variety of objective functions.

Multiscale image analysis reveals structural heterogeneity of the cell microenvironment in homotypic spheroids

Three-dimensional multicellular aggregates such as spheroids provide reliable in vitro substitutes for tissues. Quantitative characterization of spheroids at the cellular level is fundamental. We present the first pipeline that provides three-dimensional, high-quality images of intact spheroids at cellular resolution and a comprehensive image analysis that completes traditional image segmentation by algorithms from other fields. The pipeline combines light sheet-based fluorescence microscopy of optically cleared spheroids with automated nuclei segmentation (F score: 0.88) and concepts from graph analysis and computational topology. Incorporating cell graphs and alpha shapes provided more than 30 features of individual nuclei, the cellular neighborhood and the spheroid morphology. The application of our pipeline to a set of breast carcinoma spheroids revealed two concentric layers of different cell density for more than 30,000 cells. The thickness of the outer cell layer depends on a spheroid’s size and varies between 50% and 75% of its radius. In differently-sized spheroids, we detected patches of different cell densities ranging from 5 × 10⁵ to 1 × 10⁶cells/mm³. Since cell density affects cell behavior in tissues, structural heterogeneities need to be incorporated into existing models. Our image analysis pipeline provides a multiscale approach to obtain the relevant data for a system-level understanding of tissue architecture.

Quantification of neuronal density across cortical depth using automated 3D analysis of confocal image stacks

A new framework for measuring densities of immunolabeled neurons across cortical layers was implemented that combines a confocal microscopy sampling strategy with automated analysis of 3D image stacks. Its utility was demonstrated by quantifying neuronal density in macaque cortical areas V1 and V2. A series of overlapping confocal image stacks were acquired, each spanning from the pial surface to the white matter. DAPI channel images were automatically thresholded, and contiguous regions that included multiple clumped nuclear profiles were split using k-means clustering of image pixels for a set of candidate k values determined based on the clump's area; the most likely candidate segmentation was selected based on criteria that capture expected nuclear profile shape and size. The centroids of putative nuclear profiles estimated from 2D images were then grouped across z planes in an image stack to identify the positions of nuclei in x-y-z. 3D centroids falling outside user-specified exclusion boundaries were deleted, nuclei were classified by the presence or absence of signal in a channel corresponding to an immunolabeled antigen (e.g., the pan-neuronal marker NeuN) at the nuclear centroid location, and the set of classified cells was combined across image stacks to estimate density across cortical depth. The method was validated by comparison with conventional stereological methods. The average neuronal density across cortical layers was 230 × 10³ neurons per mm³ in V1 and 130 × 10³ neurons per mm³ in V2. The method is accurate, flexible, and general enough to measure densities of neurons of various molecularly identified types.

Resolution enhancement for low-temperature scanning microscopy by cryo-immersion

Here we report a simple way to enhance the resolution of a confocal scanning microscope under cryogenic conditions. Using a microscope objective (MO) with high numerical aperture (NA = 1.25) and 1-propanol as an immersion fluid with low freezing temperature we were able to reach an imaging resolution at 160 K comparable to ambient conditions. The MO and the sample were both placed inside the inner chamber of the cryostat to reduce distortions induced by temperature gradients. The image quality of our commercially available MO was further enhanced by scanning the sample (sample scanning) in contrast to beam scanning. The ease of the whole procedure marks an essential step towards the development of cryo high-resolution microscopy and correlative light and electron cryo microscopy (cryoCLEM).

Robust Cell Detection of Histopathological Brain Tumor Images Using Sparse Reconstruction and Adaptive Dictionary Selection

Successful diagnostic and prognostic stratification, treatment outcome prediction, and therapy planning depend on reproducible and accurate pathology analysis. Computer aided diagnosis (CAD) is a useful tool to help doctors make better decisions in cancer diagnosis and treatment. Accurate cell detection is often an essential prerequisite for subsequent cellular analysis. The major challenge of robust brain tumor nuclei/cell detection is to handle significant variations in cell appearance and to split touching cells. In this paper, we present an automatic cell detection framework using sparse reconstruction and adaptive dictionary learning. The main contributions of our method are: 1) A sparse reconstruction based approach to split touching cells; 2) An adaptive dictionary learning method used to handle cell appearance variations. The proposed method has been extensively tested on a data set with more than 2000 cells extracted from 32 whole slide scanned images. The automatic cell detection results are compared with the manually annotated ground truth and other state-of-the-art cell detection algorithms. The proposed method achieves the best cell detection accuracy with a F1 score = 0.96.

CellECT: cell evolution capturing tool

BACKGROUND

Robust methods for the segmentation and analysis of cells in 3D time sequences (3D+t) are critical for quantitative cell biology. While many automated methods for segmentation perform very well, few generalize reliably to diverse datasets. Such automated methods could significantly benefit from at least minimal user guidance. Identification and correction of segmentation errors in time-series data is of prime importance for proper validation of the subsequent analysis. The primary contribution of this work is a novel method for interactive segmentation and analysis of microscopy data, which learns from and guides user interactions to improve overall segmentation.

RESULTS

We introduce an interactive cell analysis application, called CellECT, for 3D+t microscopy datasets. The core segmentation tool is watershed-based and allows the user to add, remove or modify existing segments by means of manipulating guidance markers. A confidence metric learns from the user interaction and highlights regions of uncertainty in the segmentation for the user's attention. User corrected segmentations are then propagated to neighboring time points. The analysis tool computes local and global statistics for various cell measurements over the time sequence. Detailed results on two large datasets containing membrane and nuclei data are presented: a 3D+t confocal microscopy dataset of the ascidian Phallusia mammillata consisting of 18 time points, and a 3D+t single plane illumination microscopy (SPIM) dataset consisting of 192 time points. Additionally, CellECT was used to segment a large population of jigsaw-puzzle shaped epidermal cells from Arabidopsis thaliana leaves. The cell coordinates obtained using CellECT are compared to those of manually segmented cells.

CONCLUSIONS

CellECT provides tools for convenient segmentation and analysis of 3D+t membrane datasets by incorporating human interaction into automated algorithms. Users can modify segmentation results through the help of guidance markers, and an adaptive confidence metric highlights problematic regions. Segmentations can be propagated to multiple time points, and once a segmentation is available for a time sequence cells can be analyzed to observe trends. The segmentation and analysis tools presented here generalize well to membrane or cell wall volumetric time series datasets.

Robust Nucleus/Cell Detection and Segmentation in Digital Pathology and Microscopy Images: A Comprehensive Review

Digital pathology and microscopy image analysis is widely used for comprehensive studies of cell morphology or tissue structure. Manual assessment is labor intensive and prone to interobserver variations. Computer-aided methods, which can significantly improve the objectivity and reproducibility, have attracted a great deal of interest in recent literature. Among the pipeline of building a computer-aided diagnosis system, nucleus or cell detection and segmentation play a very important role to describe the molecular morphological information. In the past few decades, many efforts have been devoted to automated nucleus/cell detection and segmentation. In this review, we provide a comprehensive summary of the recent state-of-the-art nucleus/cell segmentation approaches on different types of microscopy images including bright-field, phase-contrast, differential interference contrast, fluorescence, and electron microscopies. In addition, we discuss the challenges for the current methods and the potential future work of nucleus/cell detection and segmentation.

A versatile pipeline for the multi-scale digital reconstruction and quantitative analysis of 3D tissue architecture

A prerequisite for the systems biology analysis of tissues is an accurate digital three-dimensional reconstruction of tissue structure based on images of markers covering multiple scales. Here, we designed a flexible pipeline for the multi-scale reconstruction and quantitative morphological analysis of tissue architecture from microscopy images. Our pipeline includes newly developed algorithms that address specific challenges of thick dense tissue reconstruction. Our implementation allows for a flexible workflow, scalable to high-throughput analysis and applicable to various mammalian tissues. We applied it to the analysis of liver tissue and extracted quantitative parameters of sinusoids, bile canaliculi and cell shapes, recognizing different liver cell types with high accuracy. Using our platform, we uncovered an unexpected zonation pattern of hepatocytes with different size, nuclei and DNA content, thus revealing new features of liver tissue organization. The pipeline also proved effective to analyse lung and kidney tissue, demonstrating its generality and robustness.

Analysis of in vivo single cell behavior by high throughput, human-in-the-loop segmentation of three-dimensional images

BACKGROUND

Analysis of single cells in their native environment is a powerful method to address key questions in developmental systems biology. Confocal microscopy imaging of intact tissues, followed by automatic image segmentation, provides a means to conduct cytometric studies while at the same time preserving crucial information about the spatial organization of the tissue and morphological features of the cells. This technique is rapidly evolving but is still not in widespread use among research groups that do not specialize in technique development, perhaps in part for lack of tools that automate repetitive tasks while allowing experts to make the best use of their time in injecting their domain-specific knowledge.

RESULTS

Here we focus on a well-established stem cell model system, the C. elegans gonad, as well as on two other model systems widely used to study cell fate specification and morphogenesis: the pre-implantation mouse embryo and the developing mouse olfactory epithelium. We report a pipeline that integrates machine-learning-based cell detection, fast human-in-the-loop curation of these detections, and running of active contours seeded from detections to segment cells. The procedure can be bootstrapped by a small number of manual detections, and outperforms alternative pieces of software we benchmarked on C. elegans gonad datasets. Using cell segmentations to quantify fluorescence contents, we report previously-uncharacterized cell behaviors in the model systems we used. We further show how cell morphological features can be used to identify cell cycle phase; this provides a basis for future tools that will streamline cell cycle experiments by minimizing the need for exogenous cell cycle phase labels.

CONCLUSIONS

High-throughput 3D segmentation makes it possible to extract rich information from images that are routinely acquired by biologists, and provides insights - in particular with respect to the cell cycle - that would be difficult to derive otherwise.

Fabrication of three-dimensional hydrogel scaffolds for modeling shunt failure by tissue obstruction in hydrocephalus

Background

Shunt obstruction in the treatment of hydrocephalus is poorly understood, is multi-factorial, and in many cases is modeled ineffectively. Several mechanisms may be responsible, one of which involves shunt infiltration by reactive cells from the brain parenchyma. This has not been modeled in culture and cannot be consistently examined in vivo without a large sample size.

Methods

We have developed and tested a three-dimensional in vitro model of astrocyte migration and proliferation around clinical grade ventricular catheters and into catheter holes that mimics the development of cellular outgrowth from the parenchyma that may contribute to shunt obstruction.

Results

Cell attachment and growth was observed on shunt catheters for as long as 80 days with at least 77 % viability until 51 days. The model can be used to study cellular attachment to ventricular catheters under both static and pulsatile flow conditions, which better mimic physiological cerebrospinal fluid dynamics and shunt system flow rates (0.25 mL/min, 100 pulses/min). Pulsatile flow through the ventricular catheter decreased cell attachment/growth by 63 % after 18 h. Under both conditions it was possible to observe cells accumulating around and in shunt catheter holes.

Conclusions

Alone or in combination with previously-published culture models of shunt obstruction, this model serves as a relevant test bed to analyze mechanisms of shunt failure and to test catheter modifications that will prevent cell attachment and growth.

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

BACKGROUND

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

METHODS

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

RESULTS

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

CONCLUSIONS

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

Automated profiling of individual cell-cell interactions from high-throughput time-lapse imaging microscopy in nanowell grids (TIMING)

MOTIVATION

There is a need for effective automated methods for profiling dynamic cell-cell interactions with single-cell resolution from high-throughput time-lapse imaging data, especially, the interactions between immune effector cells and tumor cells in adoptive immunotherapy.

RESULTS

Fluorescently labeled human T cells, natural killer cells (NK), and various target cells (NALM6, K562, EL4) were co-incubated on polydimethylsiloxane arrays of sub-nanoliter wells (nanowells), and imaged using multi-channel time-lapse microscopy. The proposed cell segmentation and tracking algorithms account for cell variability and exploit the nanowell confinement property to increase the yield of correctly analyzed nanowells from 45% (existing algorithms) to 98% for wells containing one effector and a single target, enabling automated quantification of cell locations, morphologies, movements, interactions, and deaths without the need for manual proofreading. Automated analysis of recordings from 12 different experiments demonstrated automated nanowell delineation accuracy >99%, automated cell segmentation accuracy >95%, and automated cell tracking accuracy of 90%, with default parameters, despite variations in illumination, staining, imaging noise, cell morphology, and cell clustering. An example analysis revealed that NK cells efficiently discriminate between live and dead targets by altering the duration of conjugation. The data also demonstrated that cytotoxic cells display higher motility than non-killers, both before and during contact.

CONTACT

broysam@central.uh.edu or nvaradar@central.uh.edu

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

In vivo cell-cycle profiling in xenograft tumors by quantitative intravital microscopy

Quantification of cell-cycle state at a single-cell level is essential to understand fundamental three-dimensional (3D) biological processes such as tissue development and cancer. Analysis of 3D in vivo images, however, is very challenging. Today's best practice, manual annotation of select image events, generates arbitrarily sampled data distributions, which are unsuitable for reliable mechanistic inferences. Here, we present an integrated workflow for quantitative in vivo cell-cycle profiling. It combines image analysis and machine learning methods for automated 3D segmentation and cell-cycle state identification of individual cell-nuclei with widely varying morphologies embedded in complex tumor environments. We applied our workflow to quantify cell-cycle effects of three antimitotic cancer drugs over 8 d in HT-1080 fibrosarcoma xenografts in living mice using a data set of 38,000 cells and compared the induced phenotypes. In contrast to results with 2D culture, observed mitotic arrest was relatively low, suggesting involvement of additional mechanisms in their antitumor effect in vivo.

Rapid 3-D delineation of cell nuclei for high-content screening platforms

High-resolution three-dimensional (3-D) microscopy combined with multiplexing of fluorescent labels allows high-content analysis of large numbers of cell nuclei. The full automation of 3-D screening platforms necessitates image processing algorithms that can accurately and robustly delineate nuclei in images with little to no human intervention. Imaging-based high-content screening was originally developed as a powerful tool for drug discovery. However, cell confluency, complexity of nuclear staining as well as poor contrast between nuclei and background result in slow and unreliable 3-D image processing and therefore negatively affect the performance of studying a drug response. Here, we propose a new method, 3D-RSD, to delineate nuclei by means of 3-D radial symmetries and test it on high-resolution image data of human cancer cells treated by drugs. The nuclei detection performance was evaluated by means of manually generated ground truth from 2351 nuclei (27 confocal stacks). When compared to three other nuclei segmentation methods, 3D-RSD possessed a better true positive rate of 83.3% and F-score of 0.895±0.045 (p-value=0.047). Altogether, 3D-RSD is a method with a very good overall segmentation performance. Furthermore, implementation of radial symmetries offers good processing speed, and makes 3D-RSD less sensitive to staining patterns. In particular, the 3D-RSD method performs well in cell lines, which are often used in imaging-based HCS platforms and are afflicted by nuclear crowding and overlaps that hinder feature extraction.

Automatic Myonuclear Detection in Isolated Single Muscle Fibers Using Robust Ellipse Fitting and Sparse Representation

Accurate and robust detection of myonuclei in isolated single muscle fibers is required to calculate myonuclear domain size. However, this task is challenging because: 1) shape and size variations of the nuclei, 2) overlapping nuclear clumps, and 3) multiple z-stack images with out-of-focus regions. In this paper, we have proposed a novel automatic detection algorithm to robustly quantify myonuclei in isolated single skeletal muscle fibers. The original z-stack images are first converted into one all-in-focus image using multi-focus image fusion. A sufficient number of ellipse fitting hypotheses are then generated from the myonuclei contour segments using heteroscedastic errors-in-variables (HEIV) regression. A set of representative training samples and a set of discriminative features are selected by a two-stage sparse model. The selected samples with representative features are utilized to train a classifier to select the best candidates. A modified inner geodesic distance based mean-shift clustering algorithm is used to produce the final nuclei detection results. The proposed method was extensively tested using 42 sets of z-stack images containing over 1,500 myonuclei. The method demonstrates excellent results that are better than current state-of-the-art approaches.

Current automated 3D cell detection methods are not a suitable replacement for manual stereologic cell counting

Stereologic cell counting has had a major impact on the field of neuroscience. A major bottleneck in stereologic cell counting is that the user must manually decide whether or not each cell is counted according to three-dimensional (3D) stereologic counting rules by visual inspection within hundreds of microscopic fields-of-view per investigated brain or brain region. Reliance on visual inspection forces stereologic cell counting to be very labor-intensive and time-consuming, and is the main reason why biased, non-stereologic two-dimensional (2D) “cell counting” approaches have remained in widespread use. We present an evaluation of the performance of modern automated cell detection and segmentation algorithms as a potential alternative to the manual approach in stereologic cell counting. The image data used in this study were 3D microscopic images of thick brain tissue sections prepared with a variety of commonly used nuclear and cytoplasmic stains. The evaluation compared the numbers and locations of cells identified unambiguously and counted exhaustively by an expert observer with those found by three automated 3D cell detection algorithms: nuclei segmentation from the FARSIGHT toolkit, nuclei segmentation by 3D multiple level set methods, and the 3D object counter plug-in for ImageJ. Of these methods, FARSIGHT performed best, with true-positive detection rates between 38 and 99% and false-positive rates from 3.6 to 82%. The results demonstrate that the current automated methods suffer from lower detection rates and higher false-positive rates than are acceptable for obtaining valid estimates of cell numbers. Thus, at present, stereologic cell counting with manual decision for object inclusion according to unbiased stereologic counting rules remains the only adequate method for unbiased cell quantification in histologic tissue sections.

Wnt-responsive cancer stem cells are located close to distorted blood vessels and not in hypoxic regions in a p53-null mouse model of human breast cancer

Cancer stem cells (CSCs, or tumor-initiating cells) may be responsible for tumor formation in many types of cancer, including breast cancer. Using high-resolution imaging techniques, we analyzed the relationship between a Wnt-responsive, CSC-enriched population and the tumor vasculature using p53-null mouse mammary tumors transduced with a lentiviral Wnt signaling reporter. Consistent with their localization in the normal mammary gland, Wnt-responsive cells in tumors were enriched in the basal/myoepithelial population and generally located in close proximity to blood vessels. The Wnt-responsive CSCs did not colocalize with the hypoxia-inducible factor 1α-positive cells in these p53-null basal-like tumors. Average vessel diameter and vessel tortuosity were increased in p53-null mouse tumors, as well as in a human tumor xenograft as compared with the normal mammary gland. The combined strategy of monitoring the fluorescently labeled CSCs and vasculature using high-resolution imaging techniques provides a unique opportunity to study the CSC and its surrounding vasculature.

An active learning approach for rapid characterization of endothelial cells in human tumors

Currently, no available pathological or molecular measures of tumor angiogenesis predict response to antiangiogenic therapies used in clinical practice. Recognizing that tumor endothelial cells (EC) and EC activation and survival signaling are the direct targets of these therapies, we sought to develop an automated platform for quantifying activity of critical signaling pathways and other biological events in EC of patient tumors by histopathology. Computer image analysis of EC in highly heterogeneous human tumors by a statistical classifier trained using examples selected by human experts performed poorly due to subjectivity and selection bias. We hypothesized that the analysis can be optimized by a more active process to aid experts in identifying informative training examples. To test this hypothesis, we incorporated a novel active learning (AL) algorithm into FARSIGHT image analysis software that aids the expert by seeking out informative examples for the operator to label. The resulting FARSIGHT-AL system identified EC with specificity and sensitivity consistently greater than 0.9 and outperformed traditional supervised classification algorithms. The system modeled individual operator preferences and generated reproducible results. Using the results of EC classification, we also quantified proliferation (Ki67) and activity in important signal transduction pathways (MAP kinase, STAT3) in immunostained human clear cell renal cell carcinoma and other tumors. FARSIGHT-AL enables characterization of EC in conventionally preserved human tumors in a more automated process suitable for testing and validating in clinical trials. The results of our study support a unique opportunity for quantifying angiogenesis in a manner that can now be tested for its ability to identify novel predictive and response biomarkers.

A generic classification-based method for segmentation of nuclei in 3D images of early embryos

Background

Studying how individual cells spatially and temporally organize within the embryo is a fundamental issue in modern developmental biology to better understand the first stages of embryogenesis. In order to perform high-throughput analyses in three-dimensional microscopic images, it is essential to be able to automatically segment, classify and track cell nuclei. Many 3D/4D segmentation and tracking algorithms have been reported in the literature. Most of them are specific to particular models or acquisition systems and often require the fine tuning of parameters.

Results

We present a new automatic algorithm to segment and simultaneously classify cell nuclei in 3D/4D images. Segmentation relies on training samples that are interactively provided by the user and on an iterative thresholding process. This algorithm can correctly segment nuclei even when they are touching, and remains effective under temporal and spatial intensity variations. The segmentation is coupled to a classification of nuclei according to cell cycle phases, allowing biologists to quantify the effect of genetic perturbations and drug treatments. Robust 3D geometrical shape descriptors are used as training features for classification. Segmentation and classification results of three complete datasets are presented. In our working dataset of the Caenorhabditis elegans embryo, only 21 nuclei out of 3,585 were not detected, the overall F-score for segmentation reached 0.99, and more than 95% of the nuclei were classified in the correct cell cycle phase. No merging of nuclei was found.

Conclusion

We developed a novel generic algorithm for segmentation and classification in 3D images. The method, referred to as Adaptive Generic Iterative Thresholding Algorithm (AGITA), is freely available as an ImageJ plug-in.

Automated seeding-based nuclei segmentation in nonlinear optical microscopy

Nonlinear optical (NLO) microscopy based, e.g., on coherent anti-Stokes Raman scattering (CARS) or two-photon-excited fluorescence (TPEF) is a fast label-free imaging technique, with a great potential for biomedical applications. However, NLO microscopy as a diagnostic tool is still in its infancy; there is a lack of robust and durable nuclei segmentation methods capable of accurate image processing in cases of variable image contrast, nuclear density, and type of investigated tissue. Nonetheless, such algorithms specifically adapted to NLO microscopy present one prerequisite for the technology to be routinely used, e.g., in pathology or intraoperatively for surgical guidance. In this paper, we compare the applicability of different seeding and boundary detection methods to NLO microscopic images in order to develop an optimal seeding-based approach capable of accurate segmentation of both TPEF and CARS images. Among different methods, the Laplacian of Gaussian filter showed the best accuracy for the seeding of the image, while a modified seeded watershed segmentation was the most accurate in the task of boundary detection. The resulting combination of these methods followed by the verification of the detected nuclei performs high average sensitivity and specificity when applied to various types of NLO microscopy images.

Segmenting the etiological agent of schistosomiasis for high-content screening

Schistosomiasis is a parasitic disease with a global health impact second only to malaria. The World Health Organization has classified schistosomiasis as an illness for which new therapies are urgently needed. However, the causative parasite is refractory to current high-throughput drug screening due to the diversity and complexity of shape, appearance and movement-based phenotypes exhibited in response to putative drugs. Currently, there is no automated image-based approach capable of relieving this deficiency. We propose and validate an image segmentation algorithm designed to overcome the distinct challenges posed by schistosomes and macroparasites in general, including irregular shapes and sizes, dense groups of touching parasites and the unpredictable effects of drug exposure. Our approach combines a region-based distributing function with a novel edge detector derived from phase congruency and grayscale thinning by threshold superposition. The method is sufficiently rapid, robust and accurate to be used for quantitative analysis of diverse parasite phenotypes in high-throughput and high-content screening.

A flexible and robust approach for segmenting cell nuclei from 2D microscopy images using supervised learning and template matching

We describe a new supervised learning-based template matching approach for segmenting cell nuclei from microscopy images. The method uses examples selected by a user for building a statistical model that captures the texture and shape variations of the nuclear structures from a given dataset to be segmented. Segmentation of subsequent, unlabeled, images is then performed by finding the model instance that best matches (in the normalized cross correlation sense) local neighborhood in the input image. We demonstrate the application of our method to segmenting nuclei from a variety of imaging modalities, and quantitatively compare our results to several other methods. Quantitative results using both simulated and real image data show that, while certain methods may work well for certain imaging modalities, our software is able to obtain high accuracy across several imaging modalities studied. Results also demonstrate that, relative to several existing methods, the template-based method we propose presents increased robustness in the sense of better handling variations in illumination, variations in texture from different imaging modalities, providing more smooth and accurate segmentation borders, as well as handling better cluttered nuclei.

Extracting 3D cell parameters from dense tissue environments: application to the development of the mouse heart

MOTIVATION

In developmental biology, quantitative tools to extract features from fluorescence microscopy images are becoming essential to characterize organ morphogenesis at the cellular level. However, automated image analysis in this context is a challenging task, owing to perturbations induced by the acquisition process, especially in organisms where the tissue is dense and opaque.

RESULTS

We propose an automated framework for the segmentation of 3D microscopy images of highly cluttered environments such as developing tissues. The approach is based on a partial differential equation framework that jointly takes advantage of the nuclear and cellular membrane information to enable accurate extraction of nuclei and cells in dense tissues. This framework has been used to study the developing mouse heart, allowing the extraction of quantitative information such as the cell cycle duration; the method also provides qualitative information on cell division and cell polarity through the creation of 3D orientation maps that provide novel insight into tissue organization during organogenesis.

A computational approach to detect gap junction plaques and associate them with cells in fluorescent images

Intercellular signaling is a fundamental requirement for complex biological system function and survival. Communication between adjoining cells is largely achieved via gap junction channels made up of multiple subunits of connexin proteins, each with unique selectivity and regulatory properties. Intercellular communication via gap junction channels facilitates transmission of an array of cellular signals, including ions, macromolecules, and metabolites that coordinate physiological processes throughout tissues and entire organisms. Although current methods used to quantify connexin expression rely on number or area density measurements in a field of view, they lack cellular assignment, distance measurement capabilities (both within the cell and to extracellular structures), and complete automation. We devised an automated computational approach built on a contour expansion algorithm platform that allows connexin protein detection and assignment to specific cells within complex tissues. In addition, parallel implementation of the contour expansion algorithm allows for high-throughput analysis as the complexity of the biological sample increases. This method does not depend specifically on connexin identification and can be applied more widely to the analysis of numerous immunocytochemical markers as well as to identify particles within tissues such as nanoparticles, gene delivery vehicles, or even cellular fragments such as exosomes or microparticles.

ACME: automated cell morphology extractor for comprehensive reconstruction of cell membranes

The quantification of cell shape, cell migration, and cell rearrangements is important for addressing classical questions in developmental biology such as patterning and tissue morphogenesis. Time-lapse microscopic imaging of transgenic embryos expressing fluorescent reporters is the method of choice for tracking morphogenetic changes and establishing cell lineages and fate maps in vivo. However, the manual steps involved in curating thousands of putative cell segmentations have been a major bottleneck in the application of these technologies especially for cell membranes. Segmentation of cell membranes while more difficult than nuclear segmentation is necessary for quantifying the relations between changes in cell morphology and morphogenesis. We present a novel and fully automated method to first reconstruct membrane signals and then segment out cells from 3D membrane images even in dense tissues. The approach has three stages: 1) detection of local membrane planes, 2) voting to fill structural gaps, and 3) region segmentation. We demonstrate the superior performance of the algorithms quantitatively on time-lapse confocal and two-photon images of zebrafish neuroectoderm and paraxial mesoderm by comparing its results with those derived from human inspection. We also compared with synthetic microscopic images generated by simulating the process of imaging with fluorescent reporters under varying conditions of noise. Both the over-segmentation and under-segmentation percentages of our method are around 5%. The volume overlap of individual cells, compared to expert manual segmentation, is consistently over 84%. By using our software (ACME) to study somite formation, we were able to segment touching cells with high accuracy and reliably quantify changes in morphogenetic parameters such as cell shape and size, and the arrangement of epithelial and mesenchymal cells. Our software has been developed and tested on Windows, Mac, and Linux platforms and is available publicly under an open source BSD license (https://github.com/krm15/ACME).

Ranked retrieval of segmented nuclei for objective assessment of cancer gene repositioning

BACKGROUND

Correct segmentation is critical to many applications within automated microscopy image analysis. Despite the availability of advanced segmentation algorithms, variations in cell morphology, sample preparation, and acquisition settings often lead to segmentation errors. This manuscript introduces a ranked-retrieval approach using logistic regression to automate selection of accurately segmented nuclei from a set of candidate segmentations. The methodology is validated on an application of spatial gene repositioning in breast cancer cell nuclei. Gene repositioning is analyzed in patient tissue sections by labeling sequences with fluorescence in situ hybridization (FISH), followed by measurement of the relative position of each gene from the nuclear center to the nuclear periphery. This technique requires hundreds of well-segmented nuclei per sample to achieve statistical significance. Although the tissue samples in this study contain a surplus of available nuclei, automatic identification of the well-segmented subset remains a challenging task.

RESULTS

Logistic regression was applied to features extracted from candidate segmented nuclei, including nuclear shape, texture, context, and gene copy number, in order to rank objects according to the likelihood of being an accurately segmented nucleus. The method was demonstrated on a tissue microarray dataset of 43 breast cancer patients, comprising approximately 40,000 imaged nuclei in which the HES5 and FRA2 genes were labeled with FISH probes. Three trained reviewers independently classified nuclei into three classes of segmentation accuracy. In man vs. machine studies, the automated method outperformed the inter-observer agreement between reviewers, as measured by area under the receiver operating characteristic (ROC) curve. Robustness of gene position measurements to boundary inaccuracies was demonstrated by comparing 1086 manually and automatically segmented nuclei. Pearson correlation coefficients between the gene position measurements were above 0.9 (p < 0.05). A preliminary experiment was conducted to validate the ranked retrieval in a test to detect cancer. Independent manual measurement of gene positions agreed with automatic results in 21 out of 26 statistical comparisons against a pooled normal (benign) gene position distribution.

CONCLUSIONS

Accurate segmentation is necessary to automate quantitative image analysis for applications such as gene repositioning. However, due to heterogeneity within images and across different applications, no segmentation algorithm provides a satisfactory solution. Automated assessment of segmentations by ranked retrieval is capable of reducing or even eliminating the need to select segmented objects by hand and represents a significant improvement over binary classification. The method can be extended to other high-throughput applications requiring accurate detection of cells or nuclei across a range of biomedical applications.

Automatic segmentation and supervised learning-based selection of nuclei in cancer tissue images

Analysis of preferential localization of certain genes within the cell nuclei is emerging as a new technique for the diagnosis of breast cancer. Quantitation requires accurate segmentation of 100-200 cell nuclei in each tissue section to draw a statistically significant result. Thus, for large-scale analysis, manual processing is too time consuming and subjective. Fortuitously, acquired images generally contain many more nuclei than are needed for analysis. Therefore, we developed an integrated workflow that selects, following automatic segmentation, a subpopulation of accurately delineated nuclei for positioning of fluorescence in situ hybridization-labeled genes of interest. Segmentation was performed by a multistage watershed-based algorithm and screening by an artificial neural network-based pattern recognition engine. The performance of the workflow was quantified in terms of the fraction of automatically selected nuclei that were visually confirmed as well segmented and by the boundary accuracy of the well-segmented nuclei relative to a 2D dynamic programming-based reference segmentation method. Application of the method was demonstrated for discriminating normal and cancerous breast tissue sections based on the differential positioning of the HES5 gene. Automatic results agreed with manual analysis in 11 out of 14 cancers, all four normal cases, and all five noncancerous breast disease cases, thus showing the accuracy and robustness of the proposed approach.

Enabling user-guided segmentation and tracking of surface-labeled cells in time-lapse image sets of living tissues

To study the process of morphogenesis, one often needs to collect and segment time-lapse images of living tissues to accurately track changing cellular morphology. This task typically involves segmenting and tracking tens to hundreds of individual cells over hundreds of image frames, a scale that would certainly benefit from automated routines; however, any automated routine would need to reliably handle a large number of sporadic, and yet typical problems (e.g., illumination inconsistency, photobleaching, rapid cell motions, and drift of focus or of cells moving through the imaging plane). Here, we present a segmentation and cell tracking approach based on the premise that users know their data best-interpreting and using image features that are not accounted for in any a priori algorithm design. We have developed a program, SeedWater Segmenter, that combines a parameter-less and fast automated watershed algorithm with a suite of manual intervention tools that enables users with little to no specialized knowledge of image processing to efficiently segment images with near-perfect accuracy based on simple user interactions.

Embedding topic discovery in conditional random fields model for segmenting nuclei using multispectral data

Segmentation of cells/nuclei is a challenging problem in 2-D histological and cytological images. Although a large number of algorithms have been proposed, newer efforts continue to be devoted to investigate robust models that could have high level of adaptability with regard to considerable amount of image variability. In this paper, we propose a multiclassification conditional random fields (CRFs) model using a combination of low-level cues (bottom-up) and high-level contextual information (top-down) for separating nuclei from the background. In our approach, the contextual information is extracted by an unsupervised topic discovery process, which efficiently helps to suppress segmentation errors caused by intensity inhomogeneity and variable chromatin texture. In addition, we propose a multilayer CRF, an extension of the traditional single-layer CRF, to handle high-dimensional dataset obtained through spectral microscopy, which provides combined benefits of spectroscopy and imaging microscopy, resulting in the ability to acquire spectral images of microscopic specimen. The approach is evaluated with color images, as well as spectral images. The overall accuracy of the proposed segmentation algorithm reaches 95% when applying multilayer CRF model to the spectral microscopy dataset. Experiments also show that our method outperforms seeded watershed, a widely used algorithm for cell segmentation.

Cell-based quantification of molecular biomarkers in histopathology specimens

AIMS

To investigate the use of a computer-assisted technology for objective, cell-based quantification of molecular biomarkers in specified cell types in histopathology specimens, with the aim of advancing current visual estimation and pixel-level (rather than cell-based) quantification methods.

METHODS AND RESULTS

Tissue specimens were multiplex-immunostained to reveal cell structures, cell type markers, and analytes, and imaged with multispectral microscopy. The image data were processed with novel software that automatically delineates and types each cell in the field, measures morphological features, and quantifies analytes in different subcellular compartments of specified cells.The methodology was validated with the use of cell blocks composed of differentially labelled cultured cells mixed in known proportions, and evaluated on human breast carcinoma specimens for quantifying human epidermal growth factor receptor 2, estrogen receptor, progesterone receptor, Ki67, phospho-extracellular signal-related kinase, and phospho-S6. Automated cell-level analyses closely matched human assessments, but, predictably, differed from pixel-level analyses of the same images.

CONCLUSIONS

Our method reveals the type, distribution, morphology and biomarker state of each cell in the field, and allows multiple biomarkers to be quantified over specified cell types, regardless of their abundance. It is ideal for studying specimens from patients in clinical trials of targeted therapeutic agents, for investigating minority stromal cell subpopulations, and for phenotypic characterization to personalize therapy and prognosis.

Non-parametric population analysis of cellular phenotypes

Methods to quantify cellular-level phenotypic differences between genetic groups are a key tool in genomics research. In disease processes such as cancer, phenotypic changes at the cellular level frequently manifest in the modification of cell population profiles. These changes are hard to detect due the ambiguity in identifying distinct cell phenotypes within a population. We present a methodology which enables the detection of such changes by generating a phenotypic signature of cell populations in a data-derived feature-space. Further, this signature is used to estimate a model for the redistribution of phenotypes that was induced by the genetic change. Results are presented on an experiment involving deletion of a tumor-suppressor gene dominant in breast cancer, where the methodology is used to detect changes in nuclear morphology between control and knockout groups.

Three-dimensional segmentation of nuclei and mitotic chromosomes for the study of cell divisions in live Drosophila embryos

Drosophila embryogenesis is an established model to investigate mechanisms and genes related to cell divisions in an intact multicellular organism. Progression through the cell cycle phases can be monitored in vivo using fluorescently labeled fusion proteins and time-lapse microscopy. To measure cellular properties in microscopic images, accurate and fast image segmentation methods are a critical prerequisite. To quantify static and dynamic features of interphase nuclei and mitotic chromosomes, we developed a three-dimensional (3D) segmentation method based on multiple level sets. We tested our method on 3D time-series images of live embryos expressing histone-2Av-green fluorescence protein. Our method is robust to low signal-to-noise ratios inherent to high-speed imaging, fluorescent signals in the cytoplasm, and dynamic changes of shape and texture. Comparisons with manual ground-truth segmentations showed that our method achieves more than 90% accuracy on the object as well as voxel levels and performs consistently throughout all cell cycle phases and developmental stages from syncytial blastoderm to postblastoderm mitotic domains.

Automated biochemical, morphological, and organizational assessment of precancerous changes from endogenous two-photon fluorescence images

Background

Multi-photon fluorescence microscopy techniques allow for non-invasive interrogation of live samples in their native environment. These methods are particularly appealing for identifying pre-cancers because they are sensitive to the early changes that occur on the microscopic scale and can provide additional information not available using conventional screening techniques.

Methodology/Principal Findings

In this study, we developed novel automated approaches, which can be employed for the real-time analysis of two-photon fluorescence images, to non-invasively discriminate between normal and pre-cancerous/HPV-immortalized engineered tissues by concurrently assessing metabolic activity, morphology, organization, and keratin localization. Specifically, we found that the metabolic activity was significantly enhanced and more uniform throughout the depths of the HPV-immortalized epithelia, based on our extraction of the NADH and FAD fluorescence contributions. Furthermore, we were able to separate the keratin contribution from metabolic enzymes to improve the redox estimates and to use the keratin localization as a means to discriminate between tissue types. To assess morphology and organization, Fourier-based, power spectral density (PSD) approaches were employed. The nuclear size distribution throughout the epithelial depths was quantified by evaluating the variance of the corresponding spatial frequencies, which was found to be greater in the normal tissue compared to the HPV-immortalized tissues. The PSD was also used to calculate the Hurst parameter to identify the level of organization in the tissues, assuming a fractal model for the fluorescence intensity fluctuations within a field. We found the range of organization was greater in the normal tissue and closely related to the level of differentiation.

Conclusions/Significance

A wealth of complementary morphological, biochemical and organizational tissue parameters can be extracted from high resolution images that are acquired based entirely on endogenous sources of contrast. They are promising diagnostic parameters for the non-invasive identification of early cancerous changes and could improve significantly diagnosis and treatment for numerous patients.

Comparison of segmentation algorithms for fluorescence microscopy images of cells

The analysis of fluorescence microscopy of cells often requires the determination of cell edges. This is typically done using segmentation techniques that separate the cell objects in an image from the surrounding background. This study compares segmentation results from nine different segmentation techniques applied to two different cell lines and five different sets of imaging conditions. Significant variability in the results of segmentation was observed that was due solely to differences in imaging conditions or applications of different algorithms. We quantified and compared the results with a novel bivariate similarity index metric that evaluates the degree of underestimating or overestimating a cell object. The results show that commonly used threshold-based segmentation techniques are less accurate than k-means clustering with multiple clusters. Segmentation accuracy varies with imaging conditions that determine the sharpness of cell edges and with geometric features of a cell. Based on this observation, we propose a method that quantifies cell edge character to provide an estimate of how accurately an algorithm will perform. The results of this study will assist the development of criteria for evaluating interlaboratory comparability.

Quantitative characterization of preneoplastic progression using single-cell computed tomography and three-dimensional karyometry

The development of morphological biosignatures to precisely characterize preneoplastic progression necessitates high-resolution three-dimensional (3D) cell imagery and robust image processing algorithms. We report on the quantitative characterization of nuclear structure alterations associated with preneoplastic progression in human esophageal epithelial cells using single-cell optical tomography and fully automated 3D karyometry. We stained cultured cells with hematoxylin and generated 3D images of individual cells by mathematically reconstructing 500 projection images acquired using optical absorption tomographic imaging. For 3D karyometry, we developed novel, fully automated algorithms to robustly segment the cellular, nuclear, and subnuclear components in the acquired cell images, and computed 41 quantitative morphological descriptors from these segmented volumes. In addition, we developed algorithms to quantify the spatial distribution and texture of the nuclear DNA. We applied our methods to normal, metaplastic, and dysplastic human esophageal epithelial cell lines, analyzing 100 cells per line. The 3D karyometric descriptors elucidated quantitative differences in morphology and enabled robust discrimination between cell lines on the basis of extracted morphological features. The morphometric hallmarks of cancer progression such as increased nuclear size, elevated nuclear content, and anomalous chromatin texture and distribution correlated with this preneoplastic progression model, pointing to the clinical use of our method for early cancer detection.

Interactive segmentation of clustered cells via geodesic commute distance and constrained density weighted Nyström method

An interactive method is proposed for complex cell segmentation, in particular of clustered cells. This article has two main contributions: First, we explore a hybrid combination of the random walk and the geodesic graph based methods for image segmentation and propose the novel concept of geodesic commute distance to classify pixels. The computation of geodesic commute distance requires an eigenvector decomposition of the weighted Laplacian matrix of a graph constructed from the image to be segmented. Second, by incorporating pairwise constraints from seeds into the algorithm, we present a novel method for eigenvector decomposition, namely a constrained density weighted Nyström method. Both visual and quantitative comparison with other semiautomatic algorithms including Voronoi-based segmentation, grow cut, graph cuts, random walk, and geodesic method are given to evaluate the performance of the proposed method, which is a powerful tool for quantitative analysis of clustered cell images in live cell imaging.

Tracking and quantitative analysis of dynamic movements of cells and particles

Understanding complex cellular processes requires investigating the underlying mechanisms within a spatiotemporal context. Although cellular processes are dynamic in nature, most studies in molecular cell biology are based on fixed specimens, for example, using immunocytochemistry or fluorescence in situ hybridization (FISH). However, breakthroughs in fluorescence microscopy imaging techniques, in particular, the discovery of green fluorescent protein (GFP) and its spectral variants, have facilitated the study of a wide range of dynamic processes by allowing nondestructive labeling of target structures in living cells. In addition, the tremendous improvements in spatial and temporal resolution of light microscopes now allow cellular processes to be analyzed in unprecedented detail. These state-of-the-art imaging technologies, however, provide a huge amount of digital image data. To cope with the enormous amount of image data and to extract reproducible as well as quantitative information, computer-based image analysis is required. In this article, we describe methods for computer-based analysis of multidimensional live cell microscopy images and their application to study the dynamics of cells and particles. First, we sketch a general workflow for quantitative analysis of live cell images. Then, we detail computational methods for automatic image analysis comprising image preprocessing, segmentation, registration, tracking, and classification. We conclude with a discussion of quantitative analysis and systems biology.

Using machine learning to speed up manual image annotation: application to a 3D imaging protocol for measuring single cell gene expression in the developing C. elegans embryo

BACKGROUND

Image analysis is an essential component in many biological experiments that study gene expression, cell cycle progression, and protein localization. A protocol for tracking the expression of individual C. elegans genes was developed that collects image samples of a developing embryo by 3-D time lapse microscopy. In this protocol, a program called StarryNite performs the automatic recognition of fluorescently labeled cells and traces their lineage. However, due to the amount of noise present in the data and due to the challenges introduced by increasing number of cells in later stages of development, this program is not error free. In the current version, the error correction (i.e., editing) is performed manually using a graphical interface tool named AceTree, which is specifically developed for this task. For a single experiment, this manual annotation task takes several hours.

RESULTS

In this paper, we reduce the time required to correct errors made by StarryNite. We target one of the most frequent error types (movements annotated as divisions) and train a support vector machine (SVM) classifier to decide whether a division call made by StarryNite is correct or not. We show, via cross-validation experiments on several benchmark data sets, that the SVM successfully identifies this type of error significantly. A new version of StarryNite that includes the trained SVM classifier is available at http://starrynite.sourceforge.net.

CONCLUSIONS

We demonstrate the utility of a machine learning approach to error annotation for StarryNite. In the process, we also provide some general methodologies for developing and validating a classifier with respect to a given pattern recognition task.