Cell Imaging Data Research Articles

A CNN-based unified framework utilizing projection loss in unison with label noise handling for multiple Myeloma cancer diagnosis.

Multiple Myeloma (MM) is a malignancy of plasma cells. Similar to other forms of cancer, it demands prompt diagnosis for reducing the risk of mortality. The conventional diagnostic tools are resource-intense and hence, these solutions are not easily scalable for extending their reach to the masses. Advancements in deep learning have led to rapid developments in affordable, resource optimized, easily deployable computer-assisted solutions. This work proposes a unified framework for MM diagnosis using microscopic blood cell imaging data that addresses the key challenges of inter-class visual similarity of healthy versus cancer cells and that of the label noise of the dataset. To extract class distinctive features, we propose projection loss to maximize the projection of a sample's activation on the respective class vector besides imposing orthogonality constraints on the class vectors. This projection loss is used along with the cross-entropy loss to design a dual branch architecture that helps achieve improved performance and provides scope for targeting the label noise problem. Based on this architecture, two methodologies have been proposed to correct the noisy labels. A coupling classifier has also been proposed to resolve the conflicts in the dual-branch architecture's predictions. We have utilized a large dataset of 72 subjects (26 healthy and 46 MM cancer) containing a total of 74996 images (including 34555 training cell images and 40441 test cell images). This is so far the most extensive dataset on Multiple Myeloma cancer ever reported in the literature. An ablation study has also been carried out. The proposed architecture performs best with a balanced accuracy of 94.17% on binary cell classification of healthy versus cancer in the comparative performance with ten state-of-the-art architectures. Extensive experiments on two additional publicly available datasets of two different modalities have also been utilized for analyzing the label noise handling capability of the proposed methodology. The code will be available under https://github.com/shivgahlout/CAD-MM.

A Propagated Skeleton Approach to High Throughput Screening of Neurite Outgrowth for In Vitro Parkinson's Disease Modelling.

Neuronal models of neurodegenerative diseases such as Parkinson’s Disease (PD) are extensively studied in pathological and therapeutical research with neurite outgrowth being a core feature. Screening of neurite outgrowth enables characterization of various stimuli and therapeutic effects after lesion. In this study, we describe an autonomous computational assay for a high throughput skeletonization approach allowing for quantification of neurite outgrowth in large data sets from fluorescence microscopic imaging. Development and validation of the assay was conducted with differentiated SH-SY5Y cells and primary mesencephalic dopaminergic neurons (MDN) treated with the neurotoxic lesioning compound Rotenone. Results of manual annotation using NeuronJ and automated data were shown to correlate strongly (-value for SH-SY5Y cells and -value for MDN). Pooled linear regressions of results from SH-SY5Y cell image data could be integrated into an equation formula (; for normalized results) with y depicting automated and x depicting manual data. This automated neurite length algorithm constitutes a valuable tool for modelling of neurite outgrowth that can be easily applied to evaluate therapeutic compounds with high throughput approaches.

Data science in cell imaging.

Cell imaging has entered the 'Big Data' era. New technologies in light microscopy and molecular biology have led to an explosion in high-content, dynamic and multidimensional imaging data. Similar to the 'omics' fields two decades ago, our current ability to process, visualize, integrate and mine this new generation of cell imaging data is becoming a critical bottleneck in advancing cell biology. Computation, traditionally used to quantitatively test specific hypotheses, must now also enable iterative hypothesis generation and testing by deciphering hidden biologically meaningful patterns in complex, dynamic or high-dimensional cell image data. Data science is uniquely positioned to aid in this process. In this Perspective, we survey the rapidly expanding new field of data science in cell imaging. Specifically, we highlight how data science tools are used within current image analysis pipelines, propose a computation-first approach to derive new hypotheses from cell image data, identify challenges and describe the next frontiers where we believe data science will make an impact. We also outline steps to ensure broad access to these powerful tools - democratizing infrastructure availability, developing sensitive, robust and usable tools, and promoting interdisciplinary training to both familiarize biologists with data science and expose data scientists to cell imaging.

Classification of Breast Cancer Cell Images using Multiple Convolution Neural Network Architectures

Breast cancer is a malignant tumor that affects women. It is the most prevalent cancer in women, affecting about 10% of all women at any point in their lives. The development of breast cancer begins in the lobules or ducts of the cells. Early detection and prevention are the best ways to stop this cancer from spreading. In this study, five Convolution Neural Network (CNN) models are used to process image data of breast cells. AlexNet, InceptionV3, GoogLeNet, VGG19 and Xception models are used for the classification of Invasive Ductal Carcinoma, IDC and Non-Invasive Ductal Carcinoma (Non-IDC) cells. The models are trained and tested at different epochs to record the learning rate. It is observed from the study that with higher epochs, the data loss decreases and accuracy increases. The accuracy of InceptionV3 and Xception is 92.48% and 90.72% respectively. Likewise, VGG19 and AlexNet have fairly close accuracy of 94.83% and 96.74%. However, GoogLeNet dominates over the other implemented models with the highest accuracy of 97.80%. The GoogLeNet model performs with high accuracy and precision in detecting IDC cells responsible for breast cancer.

Recognition of tenogenic differentiation using convolutional neural network

Abstract Methodologies to assess stem cell differentiation in the culturing state are needed for regenerative medicine and tissue engineering techniques. In recent years, convolutional neural networks (CNNs), a class of deep neural networks, have made impressive advancements in image-based classification, recognition and detection tasks. CNNs have been introduced as a non-invasive cell characterization method by learning features directly from image data of unlabeled cells. Furthermore, this approach serves as a rapid and inexpensive methodology with high performance compared to traditional techniques that require complex laboratory procedures including antibody staining and gene expression analysis. Here, we studied the potential of the CNNs approach to recognize stem cell differentiation based on cell morphology utilizing phasecontrast microscopy images.We have examined the differentiation potential of bone marrow mesenchymal stem cells (BMSCs) into tenocytes, with the treatment of bone morphogenetic protein-12 (BMP-12). After treatment, the phase-contrast images of cells were obtained directly from cell culture flasks to train CNN and the differentiated phenotype of stem cells was characterized by immunostaining. CNN was able to classify the cells into three groups including non-stem cells (chondrocytes), stem cells (BMSCs) and differentiated stem cells (tenocytes) based on their morphology with 92.2 % accuracy. The presented study revealed that CNN performed faster and non-invasive cell classification task compared to traditional methodologies.

Spatial molecular profiling: platforms, applications and analysis tools.

Molecular profiling technologies, such as genome sequencing and proteomics, have transformed biomedical research, but most such technologies require tissue dissociation, which leads to loss of tissue morphology and spatial information. Recent developments in spatial molecular profiling technologies have enabled the comprehensive molecular characterization of cells while keeping their spatial and morphological contexts intact. Molecular profiling data generate deep characterizations of the genetic, transcriptional and proteomic events of cells, while tissue images capture the spatial locations, organizations and interactions of the cells together with their morphology features. These data, together with cell and tissue imaging data, provide unprecedented opportunities to study tissue heterogeneity and cell spatial organization. This review aims to provide an overview of these recent developments in spatial molecular profiling technologies and the corresponding computational methods developed for analyzing such data.

Plasmodium classification on red blood cells image using multiclass support vector machines

Classification methods have been frequently used in various aspects, including bioinformatics. One of it’s purpose of this classification is to determine phase level of a disease. This research will classify the phase of plasmodium falciparum parasite which causes malaria. The disease is spread by an infected female Anopheles mosquito, which contains Plasmodium. The result of this research could be used to determine Plasmodium parasite phase in infected people’s red blood cells. The purpose of this research is to discover the success rate of Multiclass Support Vector Machines method and analyze it in order to predict the parasite phase levels. The data of this study is image data of red blood cells which were infected by three kinds of Plasmodium falciparum parasite levels. In the process, this study will be using Canopy as Integration Development Environments of phyton programming language. From 112 trials, the highest number of accuracy is 87.5% for Multiclass Support Vector Machines one vs rest method which used the 4-fold cross-validation with C=1 as parameter for linear kernel.

Pharmacological Modulation of Akt‐dependent Activation of eNOS/NO in Airway Cells

RationaleCa2+/calmodulin activates endothelial nitric oxide synthase (eNOS). However, other pathway(s) by which eNOS is activated is less studied in the airway cells. We hypothesized protein kinase B/Akt plays a role in the activation of eNOS and subsequent nitric oxide (NO) production.MethodsTo test if Akt activator SC79 activates Akt, A549 a type II alveolar epithelial cell‐line was transfected with a FRET‐based AktAR sensor and were treated with SC79 (10μg/ml). Cells were treated with SC79 ± phosphoinositide‐3‐kinase (PI3K) inhibitor LY294002(10μg/ml) and were harvested for Western blotting to detect phospho(p)‐eNOS. To test the production of NO, airway cells were loaded with DAF‐FM (5μM) ± eNOS inhibitor L‐NAME (10μM) and were stimulated with SC79. To test if SC79 might be protective against cadmium‐induced barrier functions and inflammation, cells were treated with cadmium( 100μM) or TNF‐α (0.1μg/ml) ± SC79 followed by Western blotting to measure tight junction protein (TJ) Zonula occluden (ZO‐1) and qPCR to measure IL‐8.ResultsLive cell imaging data show a significant increase in Akt activity (p<0.001) with SC79. AKT‐activation increased p‐eNOS via PI3K. Further, NO was induced with SC79 and was blocked by L‐NAME. Cadmium‐induced reduction in ZO‐1 protein levels and TNF‐α induced IL‐8 were both reversed by SC79.ConclusionOur preliminary data suggest that Akt plays a role in phosphorylating eNOS and NO production in airway cells. Further, Akt activators such as SC79 reversed IL‐8 and induced TJ proteins like ZO‐1. Future work will be directed towards testing the downstream mechanisms of eNOS/NO with Akt activators in patient‐derived primary airway cells.Support or Funding InformationR01DC016309, R21AI137484

CycleGAN With an Improved Loss Function for Cell Detection Using Partly Labeled Images.

The object detection, which has been widely applied in the biomedical field already, is of real significance but technically challenging. In practice, the object detection accuracy is vulnerable to labeling quality, which is usually not a big headache for simple algorithm or model verification since there are a bunch of ideal public available datasets whose classes and tags are all well-marked. However, in real scenarios, image data is often partially or even incorrectly labeled. Particularly, in cell detection, this becomes a thorny issue since the labelling of the dataset is incomplete and inaccurate. To address this issue, we propose a data-augmentation algorithm that can generate full labeled cell image data from incomplete labeled ones. First of all, we randomly extract the labeled objects from raw cell images, and meanwhile, keep their corresponding position information. Next, we employ the framework of cycle-consistent adversarial network, but significantly distinguished from the original one, to generate fully labeled data including both objects and backgrounds. We conduct extensive experiments on a blood cell classification dataset called BCCD to evaluate our model, and experimental results show that our proposed method can successfully address the weak annotation problem and improve the performance of object detection.

Medical Image Segmentation by Partitioning Spatially Constrained Fuzzy Approximation Spaces

Image segmentation is an important prerequisite step for any automatic clinical analysis technique. It assists in visualization of human tissues, as accurate delineation of medical images requires involvement of expert practitioners, which is also time consuming. In this background, the rough-fuzzy clustering algorithm provides an effective approach for image segmentation. It handles uncertainties arising due to overlapping classes and incompleteness in class definition by partitioning the fuzzy approximation spaces. However, the existing rough-fuzzy clustering algorithms do not consider the spatial distribution of the image. They depend only on the distribution of pixels to determine their class labels. In this regard, this article introduces a new algorithm, termed as spatially constrained rough-fuzzy $c$ -means (sRFCM) for medical image segmentation. The proposed sRFCM algorithm combines wisely the merits of rough-fuzzy clustering and local neighborhood information. In the proposed algorithm, the labels of local neighbors influence in the determination of the label of center pixel. The effect of local neighbors acts as a regularizer. Moreover, the proposed sRFCM algorithm partitions each cluster in possibilistic lower approximation or core region and probabilistic boundary region. The cluster centroid depends on the core and boundary regions, weight parameter, and neighborhood regularizer. A novel segmentation validity index, termed as neighborhood Silhouette, is proposed to find out the optimum values of regularizer and weight parameter, controlling the performance of the sRFCM. The efficacy of the proposed sRFCM algorithm, as well as several existing segmentation algorithms, is demonstrated on four brain MR volume databases and one HEp-2 cell image data.

Pixel precise unsupervised detection of viral particle proliferation in cellular imaging data.

Cellular and molecular imaging techniques and models have been developed to characterize single stages of viral proliferation after focal infection of cells in vitro. The fast and automatic classification of cell imaging data may prove helpful prior to any further comparison of representative experimental data to mathematical models of viral propagation in host cells. Here, we use computer generated images drawn from a reproduction of an imaging model from a previously published study of experimentally obtained cell imaging data representing progressive viral particle proliferation in host cell monolayers. Inspired by experimental time-based imaging data, here in this study viral particle increase in time is simulated by a one-by-one increase, across images, in black or gray single pixels representing dead or partially infected cells, and hypothetical remission by a one-by-one increase in white pixels coding for living cells in the original image model. The image simulations are submitted to unsupervised learning by a Self-Organizing Map (SOM) and the Quantization Error in the SOM output (SOM-QE) is used for automatic classification of the image simulations as a function of the represented extent of viral particle proliferation or cell recovery. Unsupervised classification by SOM-QE of 160 model images, each with more than three million pixels, is shown to provide a statistically reliable, pixel precise, and fast classification model that outperforms human computer-assisted image classification by RGB image mean computation. The automatic classification procedure proposed here provides a powerful approach to understand finely tuned mechanisms in the infection and proliferation of virus in cell lines in vitro or other cells.

Assessing Cardiomyocyte Excitation-Contraction Coupling Site Detection From Live Cell Imaging Using a Structurally-Realistic Computational Model of Calcium Release.

Calcium signaling plays a pivotal role in cardiomyocytes, coupling electrical excitation to mechanical contraction of the heart. Determining locations of active calcium release sites, and how their recruitment changes in response to stimuli and in disease states is therefore of central interest in cardiac physiology. Current algorithms for detecting release sites from live cell imaging data are however not easily validated against a known “ground truth,” which makes interpretation of the output of such algorithms, in particular the degree of confidence in site detection, a challenging task. Computational models are capable of integrating findings from multiple sources into a consistent, predictive framework. In cellular physiology, such models have the potential to reveal structure and function beyond the temporal and spatial resolution limitations of individual experimental measurements. Here, we create a spatially detailed computational model of calcium release in an eight sarcomere section of a ventricular cardiomyocyte, using electron tomography reconstruction of cardiac ultrastructure and confocal imaging of protein localization. This provides a high-resolution model of calcium diffusion from intracellular stores, which can be used as a platform to simulate confocal fluorescence imaging in the context of known ground truth structures from the higher resolution model. We use this capability to evaluate the performance of a recently proposed method for detecting the functional response of calcium release sites in live cells. Model permutations reveal how calcium release site density and mitochondria acting as diffusion barriers impact the detection performance of the algorithm. We demonstrate that site density has the greatest impact on detection precision and recall, in particular affecting the effective detectable depth of sites in confocal data. Our findings provide guidance on how such detection algorithms may best be applied to experimental data and give insights into limitations when using two-dimensional microscopy images to analyse three-dimensional cellular structures.

Automated identification of neural cells in the multi-photon images using deep-neural networks

The advancement of the neuroscientific imaging techniques has produced an unprecedented size of neural cell imaging data, which calls for automated processing. In particular, identification of cells from two photon images demands segmentation of neural cells out of various materials and classification of the segmented cells according to their cell types. To automatically segment neural cells, we used U-Net model, followed by classification of excitatory and inhibitory neurons and glia cells using a transfer learning technique. For transfer learning, we tested three public models of resnet18, resnet50 and inceptionv3, after replacing the fully connected layer with that for three classes. The best classification performance was found for the model with inceptionv3. The proposed application of deep learning technique is expected to provide a critical way to cell identification in the era of big neuroscience data.

Recognition of milk somatic cells based on dichotomy model

The number of various milk somatic cells can be calculated accurately by using image processing technology. In order to identify four kinds of cells,a method of milk somatic cell recognition based on dichotomy model was proposed. Firstly, eight typical morphological features were extracted from cells. Some morphological features were selected by feature optimization and Bayes classifier was used twice to carry out two binary classification. The texture feature described by HOG and BP neural network were uesd on the last classify. Finally, 96.02% of the average classification accuracy was achieved in the actual experiment of milk somatic cell image data.

An off-on fluorescent probe for real-time sensing the fluctuations of intracellular pH values in biological processes

Minute fluctuation in the intracellular pH is usually related to common diseases. The construction of fluorescent probes with wide response range, high selectivity, excellent sensitivity and good reversibility for intracellular pH detection is of great significance. In this work, we developed a novel pH probe (ZJ) based on a 3-hydroxy naphthalimide derivative via the optimization of substitute groups. ZJ showed a satisfying fluorescence performance to pH changes. ZJ manifests a remarkable fluorescence enhancement at 468 nm (over 12-fold) from pH 2.5 to 10.0. Live cell imaging data uncovered that ZJ can be successfully used in monitoring intracellular pH changes led by chloroquine, inflammation and autophagy, and confirmed with flow cytometry analysis. All these features render ZJ a potential candidate to study pH-associated drug development and physiological and pathological processes.

Learn to segment single cells with deep distance estimator and deep cell detector

Single cell segmentation is a critical and challenging step in cell imaging analysis. Traditional processing methods require time and labor to manually fine-tune parameters and lack parameter transferability between different situations. Recently, deep convolutional neural networks (CNN) treat segmentation as a pixel-wise classification problem and have become a general and efficient method for image segmentation. However, cell imaging data often possesses characteristics that adversely affect segmentation accuracy: absence of established training datasets, few pixels on cell boundaries, and ubiquitous blurry features. We developed a strategy that combines strengths of CNN and traditional watershed algorithm. First, we trained a CNN to learn Euclidean distance transform (EDT) of the mask corresponding to the input images (deep distance estimator). Next, we trained a faster R-CNN (Region with CNN) to detect individual cells in the EDT image (deep cell detector). Then, the watershed algorithm performed the final segmentation using the outputs of previous two steps. Tests on a library of fluorescence, phase contrast and differential interference contrast (DIC) images showed that both the combined method and various forms of the pixel-wise classification algorithm achieved similar pixel-wise accuracy. However, the combined method achieved significantly higher cell count accuracy than the pixel-wise classification algorithm did, with the latter performing poorly when separating connected cells, especially those connected by blurry boundaries. This difference is most obvious when applied to noisy images of densely packed cells. Furthermore, both deep distance estimator and deep cell detector converge fast and are easy to train.

Hyperspectral imaging fluorescence excitation scanning (HIFEX) microscopy for live cell imaging.

In the past two decades, spectral imaging technologies have expanded the capacity of fluorescence microscopy for accurate detection of multiple labels, separation of labels from cellular and tissue autofluorescence, and analysis of autofluorescence signatures. These technologies have been implemented using a range of optical techniques, such as tunable filters, diffraction gratings, prisms, interferometry, and custom Bayer filters. Each of these techniques has associated strengths and weaknesses with regard to spectral resolution, spatial resolution, temporal resolution, and signal-to-noise characteristics. We have previously shown that spectral scanning of the fluorescence excitation spectrum can provide greatly increased signal strength compared to traditional emission-scanning approaches. Here, we present results from utilizing a Hyperspectral Imaging Fluorescence Excitation Scanning (HIFEX) microscope system for live cell imaging. Live cell signaling studies were performed using HEK 293 and rat pulmonary microvascular endothelial cells (PMVECs), transfected with either a cAMP FRET reporter or a Ca2+ reporter. Cells were further labeled to visualize subcellular structures (nuclei, membrane, mitochondria, etc.). Spectral images were acquired using a custom inverted microscope (TE2000, Nikon Instruments) equipped with a 300W Xe arc lamp and tunable excitation filter (VF-5, Sutter Instrument Co., equipped with VersaChrome filters, Semrock), and run through MicroManager. Timelapse spectral images were acquired from 350-550 nm, in 5 nm increments. Spectral image data were linearly unmixed using custom MATLAB scripts. Results indicate that the HIFEX microscope system can acquire live cell image data at acquisition speeds of 8 ms/wavelength band with minimal photobleaching, sufficient for studying moderate speed cAMP and Ca2+ events.

Application of deep convolutional neural networks in classification of protein subcellular localization with microscopy images.

Single-cell microscopy image analysis has proved invaluable in protein subcellular localization for inferring gene/protein function. Fluorescent-tagged proteins across cellular compartments are tracked and imaged in response to genetic or environmental perturbations. With a large number of images generated by high-content microscopy while manual labeling is both labor-intensive and error-prone, machine learning offers a viable alternative for automatic labeling of subcellular localizations. Contrarily, in recent years applications of deep learning methods to large datasets in natural images and other domains have become quite successful. An appeal of deep learning methods is that they can learn salient features from complicated data with little data preprocessing. For such purposes, we applied several representative types of deep convolutional neural networks (CNNs) and two popular ensemble methods, random forests and gradient boosting, to predict protein subcellular localization with a moderately large cell image data set. We show a consistently better predictive performance of CNNs over the two ensemble methods. We also demonstrate the use of CNNs for feature extraction. In the end, we share our computer code and pretrained models to facilitate CNN's applications in genetics and computational biology.

Deep Learning in Image Cytometry: A Review.

Artificial intelligence, deep convolutional neural networks, and deep learning are all niche terms that are increasingly appearing in scientific presentations as well as in the general media. In this review, we focus on deep learning and how it is applied to microscopy image data of cells and tissue samples. Starting with an analogy to neuroscience, we aim to give the reader an overview of the key concepts of neural networks, and an understanding of how deep learning differs from more classical approaches for extracting information from image data. We aim to increase the understanding of these methods, while highlighting considerations regarding input data requirements, computational resources, challenges, and limitations. We do not provide a full manual for applying these methods to your own data, but rather review previously published articles on deep learning in image cytometry, and guide the readers toward further reading on specific networks and methods, including new methods not yet applied to cytometry data. © 2018 The Authors. Cytometry Part A published by Wiley Periodicals, Inc. on behalf of International Society for Advancement of Cytometry.

Sharing and reusing cell image data.

The rapid growth in content and complexity of cell image data creates an opportunity for synergy between experimental and computational scientists. Sharing microscopy data enables computational scientists to develop algorithms and tools for data analysis, integration, and mining. These tools can be applied by experimentalists to promote hypothesis-generation and discovery. We are now at the dawn of this revolution: infrastructure is being developed for data standardization, deposition, sharing, and analysis; some journals and funding agencies mandate data deposition; data journals publish high-content microscopy data sets; quantification becomes standard in scientific publications; new analytic tools are being developed and dispatched to the community; and huge data sets are being generated by individual labs and philanthropic initiatives. In this Perspective, I reflect on sharing and reusing cell image data and the opportunities that will come along with it.