Tracking cell lineages in 3D by incremental deep learning

Deep learning is emerging as a powerful approach for bioimage analysis. Its use in cell tracking is limited by the scarcity of annotated data for the training of deep-learning models. Moreover, annotation, training, prediction, and proofreading currently lack a unified user interface. We present ELEPHANT, an interactive platform for 3D cell tracking that addresses these challenges by taking an incremental approach to deep learning. ELEPHANT provides an interface that seamlessly integrates cell track annotation, deep learning, prediction, and proofreading. This enables users to implement cycles of incremental learning starting from a few annotated nuclei. Successive prediction-validation cycles enrich the training data, leading to rapid improvements in tracking performance. We test the software’s performance against state-of-the-art methods and track lineages spanning the entire course of leg regeneration in a crustacean over 1 week (504 timepoints). ELEPHANT yields accurate, fully-validated cell lineages with a modest investment in time and effort.

Analytics and visualization tools to characterize single-cell stochasticity using bacterial single-cell movie cytometry data

Background Time-lapse microscopy live-cell imaging is essential for studying the evolution of bacterial communities at single-cell resolution. It allows capturing detailed information about the morphology, gene expression, and spatial characteristics of individual cells at every time instance of the imaging experiment. The image analysis of bacterial "single-cell movies" (videos) generates big data in the form of multidimensional time series of measured bacterial attributes. If properly analyzed, these datasets can help us decipher the bacterial communities' growth dynamics and identify the sources and potential functional role of intra- and inter-subpopulation heterogeneity. Recent research has highlighted the importance of investigating the role of biological "noise" in gene regulation, cell growth, cell division, etc. Single-cell analytics of complex single-cell movie datasets, capturing the interaction of multiple micro-colonies with thousands of cells, can shed light on essential phenomena for human health, such as the competition of pathogens and benign microbiome cells, the emergence of dormant cells (“persisters”), the formation of biofilms under different stress conditions, etc. However, highly accurate and automated bacterial bioimage analysis and single-cell analytics methods remain elusive, even though they are required before we can routinely exploit the plethora of data that single-cell movies generate. Results We present visualization and single-cell analytics using R (ViSCAR), a set of methods and corresponding functions, to visually explore and correlate single-cell attributes generated from the image processing of complex bacterial single-cell movies. They can be used to model and visualize the spatiotemporal evolution of attributes at different levels of the microbial community organization (i.e., cell population, colony, generation, etc.), to discover possible epigenetic information transfer across cell generations, infer mathematical and statistical models describing various stochastic phenomena (e.g., cell growth, cell division), and even identify and auto-correct errors introduced unavoidably during the bioimage analysis of a dense movie with thousands of overcrowded cells in the microscope's field of view. Conclusions ViSCAR empowers researchers to capture and characterize the stochasticity, uncover the mechanisms leading to cellular phenotypes of interest, and decipher a large heterogeneous microbial communities' dynamic behavior. ViSCAR source code is available from GitLab at https://gitlab.com/ManolakosLab/viscar.

U-Hack Med Gap Year—A Virtual Undergraduate Internship Program in Computer-Assisted Healthcare and Biomedical Research

The COVID-19 healthcare crisis dramatically changed educational opportunities for undergraduate students. To overcome the lack of exposure to lab research and provide an alternative to cancelled classes and online lectures, the Lyda Hill Department of Bioinformatics at UT Southwestern Medical Center established an innovative, fully remote and paid “U-Hack Med Gap Year” internship program. At the core of the internship program were dedicated biomedical research projects spanning nine months in fields as diverse as computational microscopy, bioimage analysis, genome sequence analysis and establishment of a surgical skill analysis platform. To complement the project work, a biweekly Gap Year lab meeting was devised with opportunities to develop important skills in presenting, data sharing and analysis of new research. Despite a challenging year, all selected students completed the full internship period and over 30% will continue their project remotely after the end of the program.

Deep learning for bioimage analysis in developmental biology

ABSTRACT Deep learning has transformed the way large and complex image datasets can be processed, reshaping what is possible in bioimage analysis. As the complexity and size of bioimage data continues to grow, this new analysis paradigm is becoming increasingly ubiquitous. In this Review, we begin by introducing the concepts needed for beginners to understand deep learning. We then review how deep learning has impacted bioimage analysis and explore the open-source resources available to integrate it into a research project. Finally, we discuss the future of deep learning applied to cell and developmental biology. We analyze how state-of-the-art methodologies have the potential to transform our understanding of biological systems through new image-based analysis and modelling that integrate multimodal inputs in space and time.

2020 BioImage Analysis Survey: Community experiences and needs for the future

In this paper, we summarize a global survey of 484 participants of the imaging community, conducted in 2020 through the NIH Center for Open BioImage Analysis (COBA). This 23-question survey covered experience with image analysis, scientific background and demographics, and views and requests from different members of the imaging community. Through open-ended questions we asked the community to provide feedback for the open-source tool developers and tool user groups. The community's requests for tool developers include general improvement of tool documentation and easy-to-follow tutorials. Respondents encourage tool users to follow the best practices guidelines for imaging and ask their image analysis questions on the Scientific Community Image forum (forum.image.sc). We analyzed the community's preferred method of learning, based on level of computational proficiency and work description. In general, written step-by-step and video tutorials are preferred methods of learning by the community, followed by interactive webinars and office hours with an expert. There is also enthusiasm for a centralized location online for existing educational resources. The survey results will help the community, especially developers, trainers, and organizations like COBA, decide how to structure and prioritize their efforts.

New quantitative automated model to simulate bacterial dissemination in human tissue during irrigation of contaminated wounds

This study presents a simple and cost-effective model using microparticles to simulate the bacterial distribution pattern in soft tissue after low- and high-pressure irrigation. Silica coated iron microparticles [comparable diameter (1 µm) and weight (0.8333 pg) to Staphylococcus aureus] were applied to the surface of twenty fresh human muscle tissue samples in two amputated lower legs. Particle dissemination into deep tissue layers as an undesired side effect was investigated in four measuring fields as positive control (PC) as well as after performing pulsatile high-pressure (HP, 8 measuring fields) and low-pressure flushing (LP, 8 measuring fields). Five biopsies were taken out of each measuring field to get a total number of 100 biopsies. After histological and digital image processing, the specimens were analysed, and all incomplete sections were excluded. A special detection algorithm was parameterised using the open source bioimage analysis software QuPath. The application of this detection algorithm enabled automated counting and detection of the particles with a sensitivity of 95 % compared to manual counts. Statistical analysis revealed significant differences (p < 0.05) in our three different sample groups: HP (M = 1608, S = 302), LP (M = 2176, SD = 609) and PC (M = 4011, SD = 686). While both HP and LP flushing techniques are able to reduce the number of bacteria, a higher effectiveness is shown for HP irrigation. Nevertheless, a challenge for the validity of the study is the use of dead tissue and therefore a possible negative influence of high-pressure irrigation on tissue healing and further dispersion of particles cannot be evaluated.