Keras R-CNN: library for cell detection in biological images using deep neural networks

Systematic data analysis pipeline for quantitative morphological cell phenotyping

Quantitative morphological phenotyping (QMP) is an image-based method used to capture morphological features at both the cellular and population level. Its interdisciplinary nature, spanning from data collection to result analysis and interpretation, can lead to uncertainties, particularly among those new to this actively growing field. High analytical specificity for a typical QMP is achieved through sophisticated approaches that can leverage subtle cellular morphological changes. Here, we outline a systematic workflow to refine the QMP methodology. For a practical review, we describe the main steps of a typical QMP; in each step, we discuss the available methods, their applications, advantages, and disadvantages, along with the R functions and packages for easy implementation. This review does not cover theoretical backgrounds, but provides several references for interested researchers. It aims to broaden the horizons for future phenome studies and demonstrate how to exploit years of endeavors to achieve more with less.

Making the most of bioimaging data through interdisciplinary interactions

The increasing technical complexity of all aspects involving bioimages, ranging from their acquisition to their analysis, has led to a diversification in the expertise of scientists engaged at the different stages of the discovery process. Although this diversity of profiles comes with the major challenge of establishing fruitful interdisciplinary collaboration, such collaboration also offers a superb opportunity for scientific discovery. In this Perspective, we review the different actors within the bioimaging research universe and identify the primary obstacles that hinder their interactions. We advocate that data sharing, which lies at the heart of innovation, is finally within reach after decades of being viewed as next to impossible in bioimaging. Building on recent community efforts, we propose actions to consolidate the development of a truly interdisciplinary bioimaging culture based on open data exchange and highlight the promising outlook of bioimaging as an example of multidisciplinary scientific endeavour.

Deep Learning-Based Microscopic Cell Detection Using Inverse Distance Transform and Auxiliary Counting

Microscopic cell detection is a challenging task due to significant inter-cell occlusions in dense clusters and diverse cell morphologies. This paper introduces a novel framework designed to enhance automated cell detection. The proposed approach integrates a deep learning model that produces an inverse distance transform-based detection map from the given image, accompanied by a secondary network designed to regress a cell density map from the same input. The inverse distance transform-based map effectively highlights each cell instance in the densely populated areas, while the density map accurately estimates the total cell count in the image. Then, a custom counting-aided cell center extraction strategy leverages the cell count obtained by integrating over the density map to refine the detection process, significantly reducing false responses and thereby boosting overall accuracy. The proposed framework demonstrated superior performance with F-scores of 96.93%, 91.21%, and 92.00% on the VGG, MBM, and ADI datasets, respectively, surpassing existing state-of-the-art methods. It also achieved the lowest distance error, further validating the effectiveness of the proposed approach. These results demonstrate significant potential for automated cell analysis in biomedical applications.

Comparing Deep Learning Performance for Chronic Lymphocytic Leukaemia Cell Segmentation in Brightfield Microscopy Images

Objectives

This article focuses on the detection of cells in low-contrast brightfield microscopy images; in our case, it is chronic lymphocytic leukaemia cells. The automatic detection of cells from brightfield time-lapse microscopic images brings new opportunities in cell morphology and migration studies; to achieve the desired results, it is advisable to use state-of-the-art image segmentation methods that not only detect the cell but also detect its boundaries with the highest possible accuracy, thus defining its shape and dimensions.

Methods

We compared eight state-of-the-art neural network architectures with different backbone encoders for image data segmentation, namely U-net, U-net++, the Pyramid Attention Network, the Multi-Attention Network, LinkNet, the Feature Pyramid Network, DeepLabV3, and DeepLabV3+. The training process involved training each of these networks for 1000 epochs using the PyTorch and PyTorch Lightning libraries. For instance segmentation, the watershed algorithm and three-class image semantic segmentation were used. We also used StarDist, a deep learning-based tool for object detection with star-convex shapes.

Results

The optimal combination for semantic segmentation was the U-net++ architecture with a ResNeSt-269 background with a data set intersection over a union score of 0.8902. For the cell characteristics examined (area, circularity, solidity, perimeter, radius, and shape index), the difference in mean value using different chronic lymphocytic leukaemia cell segmentation approaches appeared to be statistically significant (Mann-Whitney U test, P < .0001).

Conclusion

We found that overall, the algorithms demonstrate equal agreement with ground truth, but with the comparison, it can be seen that the different approaches prefer different morphological features of the cells. Consequently, choosing the most suitable method for instance-based cell segmentation depends on the particular application, namely, the specific cellular traits being investigated.

Evaluation of a Deep Learning Based Approach to Computational Label Free Cell Viability Quantification

One of the most common techniques found in a cell biology or tissue engineering lab is the cytotoxicity assay. This can be performed using a variety of different dyes and stains and various protocols to result in a clear indication of dead and live cells within a culture to quantify the viability of a culture and monitor for sudden drops or increases in viability by a drug, material, viral vector, etc introduced into the culture. This assay helps cell biologists determine the health of their culture and what toxicity added substances may add to the culture and whether they are appropriate and safe to use with human cells. However, many of the dyes and stains used for this process are eventually toxic to cells, rendering the cells useless after testing and preventing real time monitoring of the same culture over a period of hours or days. Computation biology is moving cell biology towards novel and innovative techniques such as in silico labeling and dye free labeling using deep learning algorithms. In this work, we investigate whether it is feasible to train a Resnet CNN model to detect morphological changes in human cells that indicate cell death in order to classify cells as live or dead without utilizing a stain or dye. This work also aims to train one CNN model to count all cells regardless of viability status to get a total cell count, and then one CNN model that specifically identifies and counts all of the dead cells for an accurate dead and live cell total by utilizing both pieces of data to determine a general viability percentage for the culture. Additionally, this work explores the use of various image enhancements to understand if this process helps or impedes the deep learning models in their detection of total cells and dead cells.

Study of active food processing technology using computer vision and AI in coffee roasting

In the modern food processing industry, which is more complex than in the past, it is important to utilize real-time computer vision for active food processing technology using artificial intelligence. An integrated solution of computer vision and Deep Learning (DL) technology provides quality control and optimization of food processing in complex environments with obstacles. In this study, Coffee Bean Classification Model (CBCM) made by Machine Learning (ML) showed excellent performance, accurately distinguishing coffee beans through the avoidance of obstacles and empty spaces inside a rotating roasting machine. CBCM achieved a maximum validation accuracy of 98.44% and a minimum validation loss of 5.40% after the fifth epoch. Using a test dataset of 137 samples, CBCM achieved an accuracy of 99.27% and a loss of 2.82%. The developed solution using the CBCM was able to quantify the color change of the coffee beans during roasting.

Integrated analysis of single-cell sequencing and machine learning identifies a signature based on monocyte/macrophage hub genes to analyze the intracranial aneurysm associated immune microenvironment

Monocytes are pivotal immune cells in eliciting specific immune responses and can exert a significant impact on the progression, prognosis, and immunotherapy of intracranial aneurysms (IAs). The objective of this study was to identify monocyte/macrophage (Mo/MΦ)-associated gene signatures to elucidate their correlation with the pathogenesis and immune microenvironment of IAs, thereby offering potential avenues for targeted therapy against IAs. Single-cell RNA-sequencing (scRNA-seq) data of IAs were acquired from the Gene Expression Synthesis (GEO) database. The significant infiltration of monocyte subsets in the parietal tissue of IAs was identified using single-cell RNA sequencing and high-dimensional weighted gene co-expression network analysis (hdWGCNA). The integration of six machine learning algorithms identified four crucial genes linked to these Mo/MΦ. Subsequently, we developed a multilayer perceptron (MLP) neural model for the diagnosis of IAs (independent external test AUC=1.0, sensitivity =100%, specificity =100%). Furthermore, we employed the CIBERSORT method and MCP counter to establish the correlation between monocyte characteristics and immune cell infiltration as well as patient heterogeneity. Our findings offer valuable insights into the molecular characterization of monocyte infiltration in IAs, which plays a pivotal role in shaping the immune microenvironment of IAs. Recognizing this characterization is crucial for comprehending the limitations associated with targeted therapies for IAs. Ultimately, the results were verified by real-time fluorescence quantitative PCR and Immunohistochemistry.

Identification of antigen-presentation related B cells as a key player in Crohn's disease using single-cell dissecting, hdWGCNA, and deep learning

Crohn's disease (CD) arises from intricate intercellular interactions within the intestinal lamina propria. Our objective was to use single-cell RNA sequencing to investigate CD pathogenesis and explore its clinical significance. We identified a distinct subset of B cells, highly infiltrated in the CD lamina propria, that expressed genes related to antigen presentation. Using high-dimensional weighted gene co-expression network analysis and nine machine learning techniques, we demonstrated that the antigen-presenting CD-specific B cell signature effectively differentiated diseased mucosa from normal mucosa (Independent external testing AUC = 0.963). Additionally, using MCPcounter and non-negative matrix factorization, we established a relationship between the antigen-presenting CD-specific B cell signature and immune cell infiltration and patient heterogeneity. Finally, we developed a gene-immune convolutional neural network deep learning model that accurately diagnosed CD mucosa in diverse cohorts (Independent external testing AUC = 0.963). Our research has revealed a population of B cells with a potential promoting role in CD pathogenesis and represents a fundamental step in the development of future clinical diagnostic tools for the disease.

High-content imaging as a tool to quantify and characterize malaria parasites

In 2021, Plasmodium falciparum was responsible for 619,000 reported malaria-related deaths. Resistance has been detected to every clinically used antimalarial, urging the development of novel antimalarials with uncompromised mechanisms of actions. High-content imaging allows researchers to collect and quantify numerous phenotypic properties at the single-cell level, and machine learning-based approaches enable automated classification and clustering of cell populations. By combining these technologies, we developed a method capable of robustly differentiating and quantifying P. falciparum asexual blood stages. These phenotypic properties also allow for the quantification of changes in parasite morphology. Here, we demonstrate that our analysis can be used to quantify schizont nuclei, a phenotype that previously had to be enumerated manually. By monitoring stage progression and quantifying parasite phenotypes, our method can discern stage specificity of new compounds, thus providing insight into the compound's mode of action.

Integrated Multi-Omic Analysis Reveals Immunosuppressive Phenotype Associated with Poor Outcomes in High-Grade Serous Ovarian Cancer

High-grade serous ovarian cancer (HGSOC) is characterized by a complex genomic landscape, with both genetic and epigenetic diversity contributing to its pathogenesis, disease course, and response to treatment. To better understand the association between genomic features and response to treatment among 370 patients with newly diagnosed HGSOC, we utilized multi-omic data and semi-biased clustering of HGSOC specimens profiled by TCGA. A Cox regression model was deployed to select model input features based on the influence on disease recurrence. Among the features most significantly correlated with recurrence were the promotor-associated probes for the NFRKB and DPT genes and the TREML1 gene. Using 1467 transcriptomic and methylomic features as input to consensus clustering, we identified four distinct tumor clusters-three of which had noteworthy differences in treatment response and time to disease recurrence. Each cluster had unique divergence in differential analyses and distinctly enriched pathways therein. Differences in predicted stromal and immune cell-type composition were also observed, with an immune-suppressive phenotype specific to one cluster, which associated with short time to disease recurrence. Our model features were additionally used as a neural network input layer to validate the previously defined clusters with high prediction accuracy (91.3%). Overall, our approach highlights an integrated data utilization workflow from tumor-derived samples, which can be used to uncover novel drivers of clinical outcomes.

Topology-Guided Multi-Class Cell Context Generation for Digital Pathology

In digital pathology, the spatial context of cells is important for cell classification, cancer diagnosis and prognosis. To model such complex cell context, however, is challenging. Cells form different mixtures, lineages, clusters and holes. To model such structural patterns in a learnable fashion, we introduce several mathematical tools from spatial statistics and topological data analysis. We incorporate such structural descriptors into a deep generative model as both conditional inputs and a differentiable loss. This way, we are able to generate high quality multi-class cell layouts for the first time. We show that the topology-rich cell layouts can be used for data augmentation and improve the performance of downstream tasks such as cell classification.

Improving the Detection of Epidemic Clones in Candida parapsilosis Outbreaks by Combining MALDI-TOF Mass Spectrometry and Deep Learning Approaches

Identifying fungal clones propagated during outbreaks in hospital settings is a problem that increasingly confronts biologists. Current tools based on DNA sequencing or microsatellite analysis require specific manipulations that are difficult to implement in the context of routine diagnosis. Using deep learning to classify the mass spectra obtained during the routine identification of fungi by MALDI-TOF mass spectrometry could be of interest to differentiate isolates belonging to epidemic clones from others. As part of the management of a nosocomial outbreak due to Candida parapsilosis in two Parisian hospitals, we studied the impact of the preparation of the spectra on the performance of a deep neural network. Our purpose was to differentiate 39 otherwise fluconazole-resistant isolates belonging to a clonal subset from 56 other isolates, most of which were fluconazole-susceptible, collected during the same period and not belonging to the clonal subset. Our study carried out on spectra obtained on four different machines from isolates cultured for 24 or 48 h on three different culture media showed that each of these parameters had a significant impact on the performance of the classifier. In particular, using different culture times between learning and testing steps could lead to a collapse in the accuracy of the predictions. On the other hand, including spectra obtained after 24 and 48 h of growth during the learning step restored the good results. Finally, we showed that the deleterious effect of the device variability used for learning and testing could be largely improved by including a spectra alignment step during preprocessing before submitting them to the neural network. Taken together, these experiments show the great potential of deep learning models to identify spectra of specific clones, providing that crucial parameters are controlled during both culture and preparation steps before submitting spectra to a classifier.

Weakly Supervised Deep Nuclei Segmentation With Sparsely Annotated Bounding Boxes for DNA Image Cytometry

Nuclei segmentation is an essential step in DNA ploidy analysis by image-based cytometry (DNA-ICM) which is widely used in cytopathology and allows an objective measurement of DNA content (ploidy). The routine fully supervised learning-based method requires often tedious and expensive pixel-wise labels. In this paper, we propose a novel weakly supervised nuclei segmentation framework which exploits only sparsely annotated bounding boxes, without any segmentation labels. The key is to integrate the traditional image segmentation and self-training into fully supervised instance segmentation. We first leverage the traditional segmentation to generate coarse masks for each box-annotated nucleus to supervise the training of a teacher model, which is then responsible for both the refinement of these coarse masks and pseudo labels generation of unlabeled nuclei. These pseudo labels and refined masks along with the original manually annotated bounding boxes jointly supervise the training of student model. Both teacher and student share the same architecture and especially the student is initialized by the teacher. We have extensively evaluated our method with both our DNA-ICM dataset and public cytopathological dataset. Without bells and whistles, our method outperforms all existing weakly supervised entries on both datasets. Code and our DNA-ICM dataset are publicly available at https://github.com/CVIU-CSU/Weakly-Supervised-Nuclei-Segmentation.

Bibliometric analysis of artificial intelligence for biotechnology and applied microbiology: Exploring research hotspots and frontiers

Background: In the biotechnology and applied microbiology sectors, artificial intelligence (AI) has been extensively used in disease diagnostics, drug research and development, functional genomics, biomarker recognition, and medical imaging diagnostics. In our study, from 2000 to 2021, science publications focusing on AI in biotechnology were reviewed, and quantitative, qualitative, and modeling analyses were performed.

Methods: On 6 May 2022, the Web of Science Core Collection (WoSCC) was screened for AI applications in biotechnology and applied microbiology; 3,529 studies were identified between 2000 and 2022, and analyzed. The following information was collected: publication, country or region, references, knowledgebase, institution, keywords, journal name, and research hotspots, and examined using VOSviewer and CiteSpace V bibliometric platforms.

Results: We showed that 128 countries published articles related to AI in biotechnology and applied microbiology; the United States had the most publications. In addition, 584 global institutions contributed to publications, with the Chinese Academy of Science publishing the most. Reference clusters from studies were categorized into ten headings: deep learning, prediction, support vector machines (SVM), object detection, feature representation, synthetic biology, amyloid, human microRNA precursors, systems biology, and single cell RNA-Sequencing. Research frontier keywords were represented by microRNA (2012–2020) and protein-protein interactions (PPIs) (2012–2020).

Conclusion: We systematically, objectively, and comprehensively analyzed AI-related biotechnology and applied microbiology literature, and additionally, identified current hot spots and future trends in this area. Our review provides researchers with a comprehensive overview of the dynamic evolution of AI in biotechnology and applied microbiology and identifies future key research areas.

Differentiation and classification of bacterial endotoxins based on surface enhanced Raman scattering and advanced machine learning

Bacterial endotoxin, a major component of the Gram-negative bacterial outer membrane leaflet, is a lipopolysaccharide shed from bacteria during their growth and infection and can be utilized as a biomarker for bacterial detection. Here, the surface enhanced Raman scattering (SERS) spectra of eleven bacterial endotoxins with an average detection amount of 8.75 pg per measurement have been obtained based on silver nanorod array substrates, and the characteristic SERS peaks have been identified. With appropriate spectral pre-processing procedures, different classical machine learning algorithms, including support vector machine, k-nearest neighbor, random forest, etc., and a modified deep learning algorithm, RamanNet, have been applied to differentiate and classify these endotoxins. It has been found that most conventional machine learning algorithms can attain a differentiation accuracy of >99%, while RamanNet can achieve 100% accuracy. Such an approach has the potential for precise classification of endotoxins and could be used for rapid medical diagnoses and therapeutic decisions for pathogenic infections.

Paving the Way: Contributions of Big Data to Apicomplexan and Kinetoplastid Research

In the age of big data an important question is how to ensure we make the most out of the resources we generate. In this review, we discuss the major methods used in Apicomplexan and Kinetoplastid research to produce big datasets and advance our understanding of Plasmodium, Toxoplasma, Cryptosporidium, Trypanosoma and Leishmania biology. We debate the benefits and limitations of the current technologies, and propose future advancements that may be key to improving our use of these techniques. Finally, we consider the difficulties the field faces when trying to make the most of the abundance of data that has already been, and will continue to be, generated.

Machine Learning and Its Applications for Protozoal Pathogens and Protozoal Infectious Diseases

In recent years, massive attention has been attracted to the development and application of machine learning (ML) in the field of infectious diseases, not only serving as a catalyst for academic studies but also as a key means of detecting pathogenic microorganisms, implementing public health surveillance, exploring host-pathogen interactions, discovering drug and vaccine candidates, and so forth. These applications also include the management of infectious diseases caused by protozoal pathogens, such as Plasmodium, Trypanosoma, Toxoplasma, Cryptosporidium, and Giardia, a class of fatal or life-threatening causative agents capable of infecting humans and a wide range of animals. With the reduction of computational cost, availability of effective ML algorithms, popularization of ML tools, and accumulation of high-throughput data, it is possible to implement the integration of ML applications into increasing scientific research related to protozoal infection. Here, we will present a brief overview of important concepts in ML serving as background knowledge, with a focus on basic workflows, popular algorithms (e.g., support vector machine, random forest, and neural networks), feature extraction and selection, and model evaluation metrics. We will then review current ML applications and major advances concerning protozoal pathogens and protozoal infectious diseases through combination with correlative biology expertise and provide forward-looking insights for perspectives and opportunities in future advances in ML techniques in this field.

Automated detection and staging of malaria parasites from cytological smears using convolutional neural networks

Microscopic examination of blood smears remains the gold standard for laboratory inspection and diagnosis of malaria. Smear inspection is, however, time-consuming and dependent on trained microscopists with results varying in accuracy. We sought to develop an automated image analysis method to improve accuracy and standardization of smear inspection that retains capacity for expert confirmation and image archiving. Here, we present a machine learning method that achieves red blood cell (RBC) detection, differentiation between infected/uninfected cells, and parasite life stage categorization from unprocessed, heterogeneous smear images. Based on a pretrained Faster Region-Based Convolutional Neural Networks (R-CNN) model for RBC detection, our model performs accurately, with an average precision of 0.99 at an intersection-over-union threshold of 0.5. Application of a residual neural network-50 model to infected cells also performs accurately, with an area under the receiver operating characteristic curve of 0.98. Finally, combining our method with a regression model successfully recapitulates intraerythrocytic developmental cycle with accurate lifecycle stage categorization. Combined with a mobile-friendly web-based interface, called PlasmoCount, our method permits rapid navigation through and review of results for quality assurance. By standardizing assessment of Giemsa smears, our method markedly improves inspection reproducibility and presents a realistic route to both routine lab and future field-based automated malaria diagnosis.

A Study of the Recent Trends of Immunology: Key Challenges, Domains, Applications, Datasets, and Future Directions

The human immune system is very complex. Understanding it traditionally required specialized knowledge and expertise along with years of study. However, in recent times, the introduction of technologies such as AIoMT (Artificial Intelligence of Medical Things), genetic intelligence algorithms, smart immunological methodologies, etc., has made this process easier. These technologies can observe relations and patterns that humans do and recognize patterns that are unobservable by humans. Furthermore, these technologies have also enabled us to understand better the different types of cells in the immune system, their structures, their importance, and their impact on our immunity, particularly in the case of debilitating diseases such as cancer. The undertaken study explores the AI methodologies currently in the field of immunology. The initial part of this study explains the integration of AI in healthcare and how it has changed the face of the medical industry. It also details the current applications of AI in the different healthcare domains and the key challenges faced when trying to integrate AI with healthcare, along with the recent developments and contributions in this field by other researchers. The core part of this study is focused on exploring the most common classifications of health diseases, immunology, and its key subdomains. The later part of the study presents a statistical analysis of the contributions in AI in the different domains of immunology and an in-depth review of the machine learning and deep learning methodologies and algorithms that can and have been applied in the field of immunology. We have also analyzed a list of machine learning and deep learning datasets about the different subdomains of immunology. Finally, in the end, the presented study discusses the future research directions in the field of AI in immunology and provides some possible solutions for the same.

Multi-Class Cell Detection Using Spatial Context Representation

In digital pathology, both detection and classification of cells are important for automatic diagnostic and prognostic tasks. Classifying cells into subtypes, such as tumor cells, lymphocytes or stromal cells is particularly challenging. Existing methods focus on morphological appearance of individual cells, whereas in practice pathologists often infer cell classes through their spatial context. In this paper, we propose a novel method for both detection and classification that explicitly incorporates spatial contextual information. We use the spatial statistical function to describe local density in both a multi-class and a multi-scale manner. Through representation learning and deep clustering techniques, we learn advanced cell representation with both appearance and spatial context. On various benchmarks, our method achieves better performance than state-of-the-arts, especially on the classification task. We also create a new dataset for multi-class cell detection and classification in breast cancer and we make both our code and data publicly available.

SDoF-Net: Super Depth of Field Network for Cell Detection in Leucorrhea Micrograph

Accompanied with the rapid increase of the demand for routine examination of leucorrhea, efficiency and accuracy become the primary task. However, in super depth of field (SDoF) system, the problem of automatic detection and localization of cells in leucorrhea micro-images is still a big challenge. The changing of the relative position between the cell center and focus plane of microscope lead to variable cell morphological structure in the two-dimensional image, which is an important reason for the low accuracy of current deep learning target detection algorithms. In this paper, an object detection method based on Retinanet in state of super depth of field is proposed, which can achieve high precision detecting of leucorrhea components by the SDoF feature aggregation module. Compared with the current mainstream algorithms, the mean average accuracy (mAP) index has been improved significantly, the mAP index is 82.7% for SDoF module and 83.0% for SDoF+ module, with an average increase of more than 10%. These improved features can significantly improve the efficiency and accuracy of the algorithm. The algorithm proposed in this paper can be integrated into the leucorrhea automatic detection system.

HRMAn 2.0: Next-generation artificial intelligence-driven analysis for broad host-pathogen interactions

To study the dynamics of infection processes, it is common to manually enumerate imaging-based infection assays. However, manual counting of events from imaging data is biased, error-prone and a laborious task. We recently presented HRMAn (Host Response to Microbe Analysis), an automated image analysis program using state-of-the-art machine learning and artificial intelligence algorithms to analyse pathogen growth and host defence behaviour. With HRMAn, we can quantify intracellular infection by pathogens such as Toxoplasma gondii and Salmonella in a variety of cell types in an unbiased and highly reproducible manner, measuring multiple parameters including pathogen growth, pathogen killing and activation of host cell defences. Since HRMAn is based on the KNIME Analytics platform, it can easily be adapted to work with other pathogens and produce more readouts from quantitative imaging data. Here we showcase improvements to HRMAn resulting in the release of HRMAn 2.0 and new applications of HRMAn 2.0 for the analysis of host-pathogen interactions using the established pathogen T. gondii and further extend it for use with the bacterial pathogen Chlamydia trachomatis and the fungal pathogen Cryptococcus neoformans.

Rapid 3D phenotypic analysis of neurons and organoids using data-driven cell segmentation-free machine learning

Phenotypic profiling of large three-dimensional microscopy data sets has not been widely adopted due to the challenges posed by cell segmentation and feature selection. The computational demands of automated processing further limit analysis of hard-to-segment images such as of neurons and organoids. Here we describe a comprehensive shallow-learning framework for automated quantitative phenotyping of three-dimensional (3D) image data using unsupervised data-driven voxel-based feature learning, which enables computationally facile classification, clustering and advanced data visualization. We demonstrate the analysis potential on complex 3D images by investigating the phenotypic alterations of: neurons in response to apoptosis-inducing treatments and morphogenesis for oncogene-expressing human mammary gland acinar organoids. Our novel implementation of image analysis algorithms called Phindr3D allowed rapid implementation of data-driven voxel-based feature learning into 3D high content analysis (HCA) operations and constitutes a major practical advance as the computed assignments represent the biology while preserving the heterogeneity of the underlying data. Phindr3D is provided as Matlab code and as a stand-alone program (https://github.com/DWALab/Phindr3D).

Fluorescence microscopy is a fundamental technology for cell biology. However, unbiased quantitative phenotypic analysis of microscopy images of cells grown in 3D organoids or in dense culture conditions in large enough numbers to reach statistical clarity remains a fundamental challenge. Here, we report that using data-driven voxel-based features and machine learning it is possible to analyze complex 3D image data without compressing them to 2D, identifying individual cells or using computationally intensive deep learning techniques. Further, we present methods for analyzing this data by classification or clustering. Together these techniques provide the means for facile discovery and interpretation of meaningful patterns in a high dimensional feature space without complex image processing and prior knowledge or assumptions about the feature space. Our method enables novel opportunities for rapid large-scale multivariate phenotypic microscopy image analysis in 3D using a standard desktop computer.

Discriminating the single-cell gene regulatory networks of human pancreatic islets: A novel deep learning application

Analysis of single-cell pancreatic data can play an important role in understanding various metabolic diseases and health conditions. Due to the sparsity and noise present in such single-cell gene expression data, inference of single-cell gene regulatory networks remains a challenge. Since recent studies have reported the reliable inference of single-cell gene regulatory networks (SCGRNs), the current study focused on discriminating the SCGRNs of T2D patients from those of healthy controls. By accurately distinguishing SCGRNs of healthy pancreas from those of T2D pancreas, it would be possible to annotate, organize, visualize, and identify common patterns of SCGRNs in metabolic diseases. Such annotated SCGRNs could play an important role in accelerating the process of building large data repositories. This study aimed to contribute to the development of a novel deep learning (DL) application. First, we generated a dataset consisting of 224 SCGRNs belonging to both T2D and healthy pancreas and made it freely available. Next, we chose seven DL architectures, including VGG16, VGG19, Xception, ResNet50, ResNet101, DenseNet121, and DenseNet169, trained each of them on the dataset, and checked their prediction based on a test set. Of note, we evaluated the DL architectures on a single NVIDIA GeForce RTX 2080Ti GPU. Experimental results on the whole dataset, using several performance measures, demonstrated the superiority of VGG19 DL model in the automatic classification of SCGRNs, derived from the single-cell pancreatic data.

DeepScratch: Single-cell based topological metrics of scratch wound assays

Changes in tissue architecture and multicellular organisation contribute to many diseases, including cancer and cardiovascular diseases. Scratch wound assay is a commonly used tool that assesses cells' migratory ability based on the area of a wound they cover over a certain time. However, analysis of changes in the organisational patterns formed by migrating cells following genetic or pharmacological perturbations are not well explored in these assays, in part because analysing the resulting imaging data is challenging. Here we present DeepScratch, a neural network that accurately detects the cells in scratch assays based on a heterogeneous set of markers. We demonstrate the utility of DeepScratch by analysing images of more than 232,000 lymphatic endothelial cells. In addition, we propose various topological measures of cell connectivity and local cell density (LCD) to characterise tissue remodelling during wound healing. We show that LCD-based metrics allow classification of CDH5 and CDC42 genetic perturbations that are known to affect cell migration through different biological mechanisms. Such differences cannot be captured when considering only the wound area. Taken together, single-cell detection using DeepScratch allows more detailed investigation of the roles of various genetic components in tissue topology and the biological mechanisms underlying their effects on collective cell migration.