High-throughput Microscopy Imaging Research Articles

Deep Learning-Based Identification of Intraocular Pressure-Associated Genes Influencing Trabecular Meshwork Cell Morphology

Genome-wide association studies have recently uncovered many loci associated with variation in intraocular pressure (IOP). Artificial intelligence (AI) can be used to interrogate the effect of specific genetic knockouts on the morphology of trabecular meshwork cells (TMCs) and thus, IOP regulation. Experimental study. Primary TMCs collected from human donors. Sixty-two genes at 55 loci associated with IOP variation were knocked out in primary TMC lines. All cells underwent high-throughput microscopy imaging after being stained with a 5-channel fluorescent cell staining protocol. A convolutional neural network was trained to distinguish between gene knockout and normal control cell images. The area under the receiver operator curve (AUC) metric was used to quantify morphological variation in gene knockouts to identify potential pathological perturbations. Degree of morphological variation as measured by deep learning algorithm accuracy of differentiation from normal controls. Cells where LTBP2 or BCAS3 had been perturbed demonstrated the greatest morphological variation from normal TMCs (AUC 0.851, standard deviation [SD] 0.030; and AUC 0.845, SD 0.020, respectively). Of 7 multigene loci, 5 had statistically significant differences in AUC (P<0.05) between genes, allowing for pathological gene prioritization. The mitochondrial channel most frequently showed the greatest degree of morphological variation (33.9% of cell lines). We demonstrate a robust method for functionally interrogating genome-wide association signals using high-throughput microscopy and AI. Genetic variations inducing marked morphological variation can be readily identified, allowing for the gene-based dissection of loci associated with complex traits. Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

A computer vision and residual neural network (ResNet) combined method for automated and accurate yeast replicative aging analysis of high-throughput microfluidic single-cell images

With the rapid development of microfluidic platforms in high-throughput single-cell culturing, laborious operation to manipulate massive budding yeast cells (Saccharomyces cerevisiae) in replicative aging studies has been greatly simplified and automated. As a result, large datasets of microscopy images bring challenges to fast and accurately determine yeast replicative lifespan (RLS), which is the most important parameter to study cell aging. Based on our microfluidic diploid yeast long-term culturing (DYLC) chip that features 1100 traps to immobilize single cells and record their proliferation and aging via time-lapse imaging, herein, a dedicated algorithm combined with computer vision and residual neural network (ResNet) was presented to efficiently process tremendous micrographs in a high-throughput and automated manner. The image-processing algorithm includes following pivotal steps: (i) segmenting multi-trap micrographs into time-lapse single-trap sub-images, (ii) labeling 8 yeast budding features and training the 18-layer ResNet, (iii) converting the ResNet predictions in analog values into digital signals, (iv) recognizing cell dynamic events, and (v) determining yeast RLS and budding time interval (BTI) ultimately. The ResNet algorithm achieved high F1 scores (over 92%) demonstrating the effectiveness and accuracy in the recognition of yeast budding events, such as bud appearance, daughter dissection and cell death. Therefore, the results conduct that similar deep learning algorithms could be tailored to analyze high-throughput microscopy images and extract multiple cell behaviors in microfluidic single-cell analysis.

A multi-scale multi-model deep neural network via ensemble strategy on high-throughput microscopy image for protein subcellular localization

Protein subcellular locations are closely related to the function of proteins. By detecting the abnormalities in subcellular locations, we can infer the occurrence of some diseases and mine new drug targets. A large number of single-cell high-throughput microscopy images provide us with relevant resources for studying protein distribution patterns. However, in the existing image-based protein subcellular localization methods, the traditional techniques are lack of efficiency and accuracy, and the potential of deep learning methods has not been fully tapped. So in this study, we propose a multi-scale multi-model deep neural network via ensemble strategy for protein subcellular localization on single-cell high-throughput images. First of all, we employ a deep convolutional neural network as multi-scale feature extractor and use global average pooling to map extracted features at different stages into feature vectors, then concatenate these multi-scale features to form a multi-model structure for image classification. In addition, we add Squeeze-and-Excitation Blocks to the network to emphasize more informative features. What is more, we use an ensemble method to fuse the classification results from the multi-model structure to obtain the final subcellular location of each single-cell image. Experiments show the validity and effectiveness of our method on yeast cell images, it can significantly improve the accuracy of high-throughput microscopy image-based protein subcellular localization, and we achieve the classification accuracy of 0.9098 on the high-throughput microscopy images of yeast cells. In the work of protein subcellular localization, our method provides a framework for processing and classifying microscope images, and further lays the foundation for the study of protein and gene functions.

Multi-labelled proteins recognition for high-throughput microscopy images using deep convolutional neural networks

BackgroundProteins are of extremely vital importance in the human body, and no movement or activity can be performed without proteins. Currently, microscopy imaging technologies developed rapidly are employed to observe proteins in various cells and tissues. In addition, due to the complex and crowded cellular environments as well as various types and sizes of proteins, a considerable number of protein images are generated every day and cannot be classified manually. Therefore, an automatic and accurate method should be designed to properly solve and analyse protein images with mixed patterns.ResultsIn this paper, we first propose a novel customized architecture with adaptive concatenate pooling and “buffering” layers in the classifier part, which could make the networks more adaptive to training and testing datasets, and develop a novel hard sampler at the end of our network to effectively mine the samples from small classes. Furthermore, a new loss is presented to handle the label imbalance based on the effectiveness of samples. In addition, in our method, several novel and effective optimization strategies are adopted to solve the difficult training-time optimization problem and further increase the accuracy by post-processing.ConclusionOur methods outperformed the SOTA method of multi-labelled protein classification on the HPA dataset, GapNet-PL, by above 2% in the F1 score. Therefore, experimental results based on the test set split from the Human Protein Atlas dataset show that our methods have good performance in automatically classifying multi-class and multi-labelled high-throughput microscopy protein images.

Leveraging multimodal microscopy to optimize deep learning models for cell segmentation.

Deep learning provides an opportunity to automatically segment and extract cellular features from high-throughput microscopy images. Many labeling strategies have been developed for this purpose, ranging from the use of fluorescent markers to label-free approaches. However, differences in the channels available to each respective training dataset make it difficult to directly compare the effectiveness of these strategies across studies. Here, we explore training models using subimage stacks composed of channels sampled from larger, “hyper-labeled,” image stacks. This allows us to directly compare a variety of labeling strategies and training approaches on identical cells. This approach revealed that fluorescence-based strategies generally provide higher segmentation accuracies but were less accurate than label-free models when labeling was inconsistent. The relative strengths of label and label-free techniques could be combined through the use of merging fluorescence channels and using out-of-focus brightfield images. Beyond comparing labeling strategies, using subimage stacks for training was also found to provide a method of simulating a wide range of labeling conditions, increasing the ability of the final model to accommodate a greater range of candidate cell labeling strategies.

Quantitative Hormone Signaling Output Analyses of Arabidopsis thaliana Interactions With Virulent and Avirulent Hyaloperonospora arabidopsidis Isolates at Single-Cell Resolution.

The phytohormones salicylic acid (SA), jasmonic acid (JA), and ethylene (ET) are central regulators of biotic and abiotic stress responses in Arabidopsis thaliana. Here, we generated modular fluorescent protein-based reporter lines termed COLORFUL-PR1pro, -VSP2pro, and -PDF1.2apro. These feature hormone-controlled nucleus-targeted transcriptional output sensors and the simultaneous constitutive expression of spectrally separated nuclear reference and plasma membrane-localized reporters. This set-up allowed the study of cell-type specific hormone activities, cellular viability and microbial invasion. Moreover, we developed a software-supported high-throughput confocal microscopy imaging protocol for output quantification to resolve the spatio-temporal dynamics of respective hormonal signaling activities at single-cell resolution. Proof-of-principle analyses in A. thaliana leaves revealed distinguished hormone sensitivities in mesophyll, epidermal pavement and stomatal guard cells, suggesting cell type-specific regulatory protein activities. In plant-microbe interaction studies, we found that virulent and avirulent Hyaloperonospora arabidopsidis (Hpa) isolates exhibit different invasion dynamics and induce spatio-temporally distinct hormonal activity signatures. On the cellular level, these hormone-controlled reporter signatures demarcate the nascent sites of Hpa entry and progression, and highlight initiation, transduction and local containment of immune signals.

A machine learning approach to define antimalarial drug action from heterogeneous cell-based screens.

Drug resistance threatens the effective prevention and treatment of an ever-increasing range of human infections. This highlights an urgent need for new and improved drugs with novel mechanisms of action to avoid cross-resistance. Current cell-based drug screens are, however, restricted to binary live/dead readouts with no provision for mechanism of action prediction. Machine learning methods are increasingly being used to improve information extraction from imaging data. These methods, however, work poorly with heterogeneous cellular phenotypes and generally require time-consuming human-led training. We have developed a semi-supervised machine learning approach, combining human- and machine-labeled training data from mixed human malaria parasite cultures. Designed for high-throughput and high-resolution screening, our semi-supervised approach is robust to natural parasite morphological heterogeneity and correctly orders parasite developmental stages. Our approach also reproducibly detects and clusters drug-induced morphological outliers by mechanism of action, demonstrating the potential power of machine learning for accelerating cell-based drug discovery.

IA-Lab: A MATLAB framework for efficient microscopy image analysis development, applied to quantifying intracellular transport of internalized peptide-drug conjugate.

This work presents a MATLAB-based software package for high-throughput microscopy image analysis development, making such development more accessible for a large user community. The toolbox provides a GUI and a number of analysis workflows, and can serve as a general framework designed to allow for easy extension. For a new application, only a minor part of the object-oriented code needs to be replaced by new components, making development efficient. This makes it possible to quickly develop solutions for analysis not available in existing tools. We show its use in making a tool for quantifying intracellular transport of internalized peptide-drug conjugates.The code is freely available as open source on GitHub (https://github.com/amcorrigan/ia-lab)

Revealing the Synaptic Hodology of Mammalian Neural Circuits With Multiscale Neurocartography.

The functional features of neural circuits are determined by a combination of properties that range in scale from projections systems across the whole brain to molecular interactions at the synapse. The burgeoning field of neurocartography seeks to map these relevant features of brain structure—spanning a volume ∼20 orders of magnitude—to determine how neural circuits perform computations supporting cognitive function and complex behavior. Recent technological breakthroughs in tissue sample preparation, high-throughput electron microscopy imaging, and automated image analyses have produced the first visualizations of all synaptic connections between neurons of invertebrate model systems. However, the sheer size of the central nervous system in mammals implies that reconstruction of the first full brain maps at synaptic scale may not be feasible for decades. In this review, we outline existing and emerging technologies for neurocartography that complement electron microscopy-based strategies and are beginning to derive some basic organizing principles of circuit hodology at the mesoscale, microscale, and nanoscale. Specifically, we discuss how a host of light microscopy techniques including array tomography have been utilized to determine both long-range and subcellular organizing principles of synaptic connectivity. In addition, we discuss how new techniques, such as two-photon serial tomography of the entire mouse brain, have become attractive approaches to dissect the potential connectivity of defined cell types. Ultimately, principles derived from these techniques promise to facilitate a conceptual understanding of how connectomes, and neurocartography in general, can be effectively utilized toward reaching a mechanistic understanding of circuit function.

Rotation equivariant and invariant neural networks for microscopy image analysis.

MotivationNeural networks have been widely used to analyze high-throughput microscopy images. However, the performance of neural networks can be significantly improved by encoding known invariance for particular tasks. Highly relevant to the goal of automated cell phenotyping from microscopy image data is rotation invariance. Here we consider the application of two schemes for encoding rotation equivariance and invariance in a convolutional neural network, namely, the group-equivariant CNN (G-CNN), and a new architecture with simple, efficient conic convolution, for classifying microscopy images. We additionally integrate the 2D-discrete-Fourier transform (2D-DFT) as an effective means for encoding global rotational invariance. We call our new method the Conic Convolution and DFT Network (CFNet).ResultsWe evaluated the efficacy of CFNet and G-CNN as compared to a standard CNN for several different image classification tasks, including simulated and real microscopy images of subcellular protein localization, and demonstrated improved performance. We believe CFNet has the potential to improve many high-throughput microscopy image analysis applications.Availability and implementationSource code of CFNet is available at: https://github.com/bchidest/CFNet.Supplementary information Supplementary data are available at Bioinformatics online.

From observing to predicting single-cell structure and function with high-throughput/high-content microscopy.

In the past 15 years, cell-based microscopy has evolved its focus from observing cell function to aiming to predict it. In particular—powered by breakthroughs in computer vision, large-scale image analysis and machine learning—high-throughput and high-content microscopy imaging have enabled to uniquely harness single-cell information to systematically discover and annotate genes and regulatory pathways, uncover systems-level interactions and causal links between cellular processes, and begin to clarify and predict causal cellular behaviour and decision making. Here we review these developments, discuss emerging trends in the field, and describe how single-cell ‘omics and single-cell microscopy are imminently in an intersecting trajectory. The marriage of these two fields will make possible an unprecedented understanding of cell and tissue behaviour and function.

Accurate Prediction of Biological Assays with High-Throughput Microscopy Images and Convolutional Networks.

Predicting the outcome of biological assays based on high-throughput imaging data is a highly promising task in drug discovery since it can tremendously increase hit rates and suggest novel chemical scaffolds. However, end-to-end learning with convolutional neural networks (CNNs) has not been assessed for the task biological assay prediction despite the success of these networks at visual recognition. We compared several CNNs trained directly on high-throughput imaging data to a) CNNs trained on cell-centric crops and to b) the current state-of-the-art: fully connected networks trained on precalculated morphological cell features. The comparison was performed on the Cell Painting data set, the largest publicly available data set of microscopic images of cells with approximately 30,000 compound treatments. We found that CNNs perform significantly better at predicting the outcome of assays than fully connected networks operating on precomputed morphological features of cells. Surprisingly, the best performing method could predict 32% of the 209 biological assays at high predictive performance (AUC > 0.9) indicating that the cell morphology changes contain a large amount of information about compound activities. Our results suggest that many biological assays could be replaced by high-throughput imaging together with convolutional neural networks and that the costly cell segmentation and feature extraction step can be replaced by convolutional neural networks.

A New Unsupervised Approach for Segmenting and Counting Cells in High-Throughput Microscopy Image Sets.

New technological advances in automated microscopy have given rise to large volumes of data, which have made human-based analysis infeasible, heightening the need for automatic systems for high-throughput microscopy applications. In particular, in the field of fluorescence microscopy, automatic tools for image analysis are making an essential contribution in order to increase the statistical power of the cell analysis process. The development of these automatic systems is a difficult task due to both the diversification of the staining patterns and the local variability of the images. In this paper, we present an unsupervised approach for automatic cell segmentation and counting, namely CSC, in high-throughput microscopy images. The segmentation is performed by dividing the whole image into square patches that undergo a gray level clustering followed by an adaptive thresholding. Subsequently, the cell labeling is obtained by detecting the centers of the cells, using both distance transform and curvature analysis, and by applying a region growing process. The advantages of CSC are manifold. The foreground detection process works on gray levels rather than on individual pixels, so it proves to be very efficient. Moreover, the combination of distance transform and curvature analysis makes the counting process very robust to clustered cells. A further strength of the CSC method is the limited number of parameters that must be tuned. Indeed, two different versions of the method have been considered, CSC-7 and CSC-3, depending on the number of parameters to be tuned. The CSC method has been tested on several publicly available image datasets of real and synthetic images. Results in terms of standard metrics and spatially aware measures show that CSC outperforms the current state-of-the-art techniques.

Accurate Classification of Protein Subcellular Localization from High-Throughput Microscopy Images Using Deep Learning.

High-throughput microscopy of many single cells generates high-dimensional data that are far from straightforward to analyze. One important problem is automatically detecting the cellular compartment where a fluorescently-tagged protein resides, a task relatively simple for an experienced human, but difficult to automate on a computer. Here, we train an 11-layer neural network on data from mapping thousands of yeast proteins, achieving per cell localization classification accuracy of 91%, and per protein accuracy of 99% on held-out images. We confirm that low-level network features correspond to basic image characteristics, while deeper layers separate localization classes. Using this network as a feature calculator, we train standard classifiers that assign proteins to previously unseen compartments after observing only a small number of training examples. Our results are the most accurate subcellular localization classifications to date, and demonstrate the usefulness of deep learning for high-throughput microscopy.

An Unsupervised kNN Method to Systematically Detect Changes in Protein Localization in High-Throughput Microscopy Images.

Despite the importance of characterizing genes that exhibit subcellular localization changes between conditions in proteome-wide imaging experiments, many recent studies still rely upon manual evaluation to assess the results of high-throughput imaging experiments. We describe and demonstrate an unsupervised k-nearest neighbours method for the detection of localization changes. Compared to previous classification-based supervised change detection methods, our method is much simpler and faster, and operates directly on the feature space to overcome limitations in needing to manually curate training sets that may not generalize well between screens. In addition, the output of our method is flexible in its utility, generating both a quantitatively ranked list of localization changes that permit user-defined cut-offs, and a vector for each gene describing feature-wise direction and magnitude of localization changes. We demonstrate that our method is effective at the detection of localization changes using the Δrpd3 perturbation in Saccharomyces cerevisiae, where we capture 71.4% of previously known changes within the top 10% of ranked genes, and find at least four new localization changes within the top 1% of ranked genes. The results of our analysis indicate that simple unsupervised methods may be able to identify localization changes in images without laborious manual image labelling steps.

High throughput microscopy identifies bisphenol AP, a bisphenol A analog, as a novel AR down-regulator.

Prostate cancer remains a deadly disease especially when patients become resistant to drugs that target the Androgen Receptor (AR) ligand binding domain. At this stage, patients develop recurring castrate-resistant prostate cancers (CRPCs). Interestingly, CRPC tumors maintain dependency on AR for growth; moreover, in CRPCs, constitutively active AR splice variants (e.g., AR-V7) begin to be expressed at higher levels. These splice variants lack the ligand binding domain and are rendered insensitive to current endocrine therapies. Thus, it is of paramount importance to understand what regulates the expression of AR and its splice variants to identify new therapeutic strategies in CRPCs. Here, we used high throughput microscopy and quantitative image analysis to evaluate effects of selected endocrine disruptors on AR levels in multiple breast and prostate cancer cell lines. Bisphenol AP (BPAP), which is used in chemical and medical industries, was identified as a down-regulator of both full length AR and the AR-V7 splice variant. We validated its activity by performing time-course, dose-response, Western blot and qPCR analyses. BPAP also reduced the percent of cells in S phase, which was accompanied by a ~60% loss in cell numbers and colony formation in anchorage-independent growth assays. Moreover, it affected mitochondria size and cell metabolism. In conclusion, our high content analysis-based screening platform was used to classify the effect of compounds on endogenous ARs, and identified BPAP as being capable of causing AR (both full-length and variants) down-regulation, cell cycle arrest and metabolic alterations in CRPC cell lines.

An Automatic Segmentation Method Combining an Active Contour Model and a Classification Technique for Detecting Polycomb-group Proteinsin High-Throughput Microscopy Images.

The large amount of data generated in biological experiments that rely on advanced microscopy can be handled only with automated image analysis. Most analyses require a reliable cell image segmentation eventually capable of detecting subcellular structures.We present an automatic segmentation method to detect Polycomb group (PcG) proteins areas isolated from nuclei regions in high-resolution fluorescent cell image stacks. It combines two segmentation algorithms that use an active contour model and a classification technique serving as a tool to better understand the subcellular three-dimensional distribution of PcG proteins in live cell image sequences. We obtained accurate results throughout several cell image datasets, coming from different cell types and corresponding to different fluorescent labels, without requiring elaborate adjustments to each dataset.

Transfer Shape Modeling Towards High-throughput Microscopy Image Segmentation.

In order to deal with ambiguous image appearances in cell segmentation, high-level shape modeling has been introduced to delineate cell boundaries. However, shape modeling usually requires sufficient annotated training shapes, which are often labor intensive or unavailable. Meanwhile, when applying the model to different datasets, it is necessary to repeat the tedious annotation process to generate enough training data, and this will significantly limit the applicability of the model. In this paper, we propose to transfer shape modeling learned from an existing but different dataset (e.g. lung cancer) to assist cell segmentation in a new target dataset (e.g. skeletal muscle) without expensive manual annotations. Considering the intrinsic geometry structure of cell shapes, we incorporate the shape transfer model into a sparse representation framework with a manifold embedding constraint, and provide an efficient algorithm to solve the optimization problem. The proposed algorithm is tested on multiple microscopy image datasets with different tissue and staining preparations, and the experiments demonstrate its effectiveness.

Tara Oceans. Tara Oceans studies plankton at planetary scale. Introduction.

The ocean is the largest ecosystem on Earth, and yet we know very little about it. This is particularly true for the plankton that inhabit the ocean. Although these organisms are at least as important for the Earth system as the rainforests and form the base of marine food webs, most plankton are invisible to the naked eye and thus are largely uncharacterized. To study this invisible world, the multinational Tara Oceans consortium, with use of the 110-foot research schooner Tara , sampled microscopic plankton at 210 sites and depths up to 2000 m in all the major oceanic regions during expeditions from 2009 through 2013 ([ 1 ][1]). ![Figure][2] Research schooner Tara supported a multinational, multidisciplinary team in sampling plankton ecosystems around the world. F. LAREILLE/TARA EXPEDITIONS Success depended on collaboration between scientists and the Tara Expeditions logistics team. The journey involved not only science but also outreach and education as well as negotiation through the shoals of legal and political regulations, funding uncertainties, threats from pirates, and unpredictable weather ([ 2 ][3]). At various times, journalists, artists, and teachers were also on board. Visitors included Ban Ki-moon (Secretary-General of the United Nations) and numerous youngsters, including schoolchildren from the favelas in Rio de Janeiro. Sampling, usually 60 hours per site, followed standardized protocols ([ 3 ][4]) to capture the morphological and genetic diversity of the entire plankton community from viruses to small zooplankton, covering a size range from 0.02 µm to a few millimeters, in context with physical and chemical information. Besides the sampling, a lab on board contained a range of online instruments and microscopes to monitor the content of the samples as they were being collected. The main focus was on the organism-rich sunlit upper layer of the ocean (down to 200 m), but the twilight zone below was also sampled. Guided by satellite and in situ data, scientists sampled features such as mesoscale eddies, upwellings, acidic waters, and anaerobic zones, frequently in the open ocean. In addition to being used for genomics and oceanography, many samples were collected for other analyses, such as high-throughput microscopy imaging and flow cytometry. The samples and data collected on board were archived in a highly structured way to enable extensive data processing and integration on land ([ 4 ][5]). The five Research Articles in this issue of Science describe the samples, data, and analysis from Tara Oceans (based on a data freeze from 579 samples at 75 stations as of November 2013). De Vargas et al. used ribosomal RNA gene sequences to profile eukaryotic diversity in the photic zone. This taxonomic census shows that most biodiversity belongs to poorly known lineages of uncultured heterotrophic single-celled protists. Sunagawa et al. used metagenomics to study viruses, prokaryotes, and picoeukaryotes. They established a catalog with >40 million genes and identified temperature as the driver of photic microbial community composition. Brum et al. , by sequencing and electron microscopy, found that viruses are diverse on a regional basis but less so on a global basis. The viral communities are passively transported by oceanic currents and structured by local environments. Lima-Mendez et al. modeled interactions between viruses, prokaryotes, and eukaryotes. Regional and global parameters refine resulting networks. Villar et al. studied the dispersal of plankton as oceanic currents swirl around the southern tip of Africa, where the Agulhas rings are generated. Vertical mixing in the rings drives nitrogen cycling and selects for specific organisms. Tara Oceans combined ecology, systems biology, and oceanography to study plankton in their environmental context. The project has generated resources such as an ocean microbial reference gene catalog; a census of plankton diversity covering viruses, prokaryotes, and eukaryotes; and methodologies to explore interactions between them and their integration with environmental conditions. Although many more such analyses will follow, life in the ocean is already a little less murky than it was before. 1. [↵][6]1. E. Karsenti 2. et al ., PLOS Biol. 9, e1001177 (2011). [OpenUrl][7][CrossRef][8][PubMed][9] 2. [↵][10]1. E. Karsenti , The making of Tara Oceans: Funding blue skies research for our Blue Planet. Mol. Syst. Biol. 11, 811 (2015) [doi:10.15252/msb.20156271][11]. [OpenUrl][12] 3. [↵][13]1. S. Pesant 2. et al ., BioRXiv, (2015). 4. [↵][14]1. S. Sunagawa, 2. E. Karsenti, 3. C. Bowler, 4. P. Bork Computational ecosystems biology in Tara Oceans: Translating data into knowledge. Mol. Syst. Biol. 11, 809 (2015) [doi:10.15252/msb.20156272][15]. [OpenUrl][16] [1]: #ref-1 [2]: pending:yes [3]: #ref-2 [4]: #ref-3 [5]: #ref-4 [6]: #xref-ref-1-1 View reference 1 in text [7]: {openurl}?query=rft.jtitle%253DPLoS%2Bbiology%26rft.stitle%253DPLoS%2BBiol%26rft.aulast%253DKarsenti%26rft.auinit1%253DE.%26rft.volume%253D9%26rft.issue%253D10%26rft.spage%253De1001177%26rft.epage%253De1001177%26rft.atitle%253DA%2Bholistic%2Bapproach%2Bto%2Bmarine%2Beco-systems%2Bbiology.%26rft_id%253Dinfo%253Adoi%252F10.1371%252Fjournal.pbio.1001177%26rft_id%253Dinfo%253Apmid%252F22028628%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [8]: /lookup/external-ref?access_num=10.1371/journal.pbio.1001177&link_type=DOI [9]: /lookup/external-ref?access_num=22028628&link_type=MED&atom=%2Fsci%2F348%2F6237%2F873.atom [10]: #xref-ref-2-1 View reference 2 in text [11]: http://msb.embopress.org/content/11/5/811 [12]: {openurl}?query=rft.jtitle%253D%2BMol.%2BSyst.%2BBiol.%26rft.volume%253D15%26rft.spage%253D6271%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [13]: #xref-ref-3-1 View reference 3 in text [14]: #xref-ref-4-1 View reference 4 in text [15]: http://msb.embopress.org/content/11/5/809 [16]: {openurl}?query=rft.jtitle%253DMol.%2BSyst.%2BBiol.%26rft.volume%253D15%26rft.spage%253D6272%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx

Influence of the phase effect on gradient‐based and statistics‐based focus measures in bright field microscopy

Autofocusing is essential to high throughput microscopy and live cell imaging and requires reliable focus measures. Phase objects such as separated single Chinese hamster ovary cells are almost invisible at the optical focus position in bright field microscopy images. Because of the phase effect, defocused images of phase objects have more contrast. In this paper, we show that widely used focus measures exhibit an untypical behaviour for such images. In the case of homogeneous cells, that is, when most cells tend to lie in the same focal plane, both gradient-based and statistics-based focus measures tend to have a local minimum instead of a global maximum at the optical focus position. On the other hand, if images show inhomogeneous cells, gradient-based focus measures tend to yield typical focus curves, whereas statistics-based focus measures deliver curves similar to the case of homogeneous cells. These results were interpreted using the equation describing the phase effect and patch-wise analysis of the focus curves. Bioprocess engineering experts are also influenced by the phase effect. Forty-four focus positions selected by them led to the conclusion that they prefer to look at defocused images instead of those at the optical focus.