Automated and semi-automated enhancement, segmentation and tracing of cytoskeletal networks in microscopic images: A review

Deep learning-based cytoskeleton segmentation for accurate high-throughput measurement of cytoskeleton density

Microscopic analyses of cytoskeleton organization are crucial for understanding various cellular activities, including cell proliferation and environmental responses in plants. Traditionally, assessments of cytoskeleton dynamics have been qualitative, relying on microscopy-assisted visual inspection. However, the transition to quantitative digital microscopy has introduced new technical challenges, with segmentation of cytoskeleton structures proving particularly demanding. In this study, we examined the utility of a deep learning-based segmentation method for accurate quantitative evaluation of cytoskeleton organization using confocal microscopic images of the cortical microtubules in tobacco BY-2 cells. The results showed that, although conventional methods sufficed for measurement of cytoskeleton angles and parallelness, the deep learning-based method significantly improved the accuracy of density measurements. To assess the versatility of the method, we extended our analysis to physiologically significant models in the context of changes in cytoskeleton density, namely Arabidopsis thaliana guard cells and zygotes. The deep learning-based method successfully improved the accuracy of cytoskeleton density measurements for quantitative evaluations of physiological changes in both stomatal movement in guard cells and intracellular polarization in elongating zygotes, confirming its utility in these applications. The results demonstrate the effectiveness of deep learning-based segmentation in providing precise and high-throughput measurements of cytoskeleton density, and has the potential to automate and expedite analyses of large-scale image datasets.

Differential GTP-dependent in-vitro polymerization of recombinant Physcomitrella FtsZ proteins

Bacterial cell division and plant chloroplast division require selfassembling Filamentous temperature-sensitive Z (FtsZ) proteins. FtsZ proteins are GTPases sharing structural and biochemical similarities with eukaryotic tubulin. In the moss Physcomitrella, the morphology of the FtsZ polymer networks varies between the different FtsZ isoforms. The underlying mechanism and foundation of the distinct networks is unknown. Here, we investigated the interaction of Physcomitrella FtsZ2-1 with FtsZ1 isoforms via co-immunoprecipitation and mass spectrometry, and found protein-protein interaction in vivo. We tagged FtsZ1-2 and FtsZ2-1 with different fluorophores and expressed both in E. coli, which led to the formation of defined structures within the cells and to an influence on bacterial cell division and morphology. Furthermore, we have optimized the purification protocols for FtsZ1-2 and FtsZ2-1 expressed in E. coli and characterized their GTPase activity and polymerization in vitro. Both FtsZ isoforms showed GTPase activity. Stoichiometric mixing of both proteins led to a significantly increased GTPase activity, indicating a synergistic interaction between them. In light scattering assays, we observed GTP-dependent assembly of FtsZ1-2 and of FtsZ2-1 in a protein concentration dependent manner. Stoichiometric mixing of both proteins resulted in significantly faster polymerization, again indicating a synergistic interaction between them. Under the same conditions used for GTPase and light scattering assays both FtsZ isoforms formed filaments in a GTP-dependent manner as visualized by transmission electron microscopy (TEM). Taken together, our results reveal that Physcomitrella FtsZ1-2 and FtsZ2-1 are functionally different, can synergistically interact in vivo and in vitro, and differ in their properties from FtsZ proteins from bacteria, archaea and vascular plants.

Impact of photobleaching on quantitative, spatio-temporal, super-resolution imaging of mitochondria in live C. elegans larvae

Super-resolution (SR) 3D rendering allows superior quantitative analysis of intracellular structures but has largely been limited to fixed or ex vivo samples. Here we developed a method to perform SR live imaging of mitochondria during post-embryonic development of C. elegans larvae. Our workflow includes the drug-free mechanical immobilisation of animals using polystyrene nanobeads, which has previously not been used for in vivo SR imaging. Based on the alignment of moving objects and global threshold-based image segmentation, our method enables an efficient 3D reconstruction of individual mitochondria. We demonstrate for the first time that the frequency distribution of fluorescence intensities is not affected by photobleaching, and that global thresholding alone enables the quantitative comparison of mitochondria along timeseries. Our composite approach significantly improves the study of biological structures and processes in SR during C. elegans post-embryonic development. Furthermore, the discovery that image segmentation does not require any prior correction against photobleaching, a fundamental problem in fluorescence microscopy, will impact experimental strategies aimed at quantitatively studying the dynamics of organelles and other intracellular compartments in any biological system.

Data-Driven and Cell-Specific Determination of Nuclei-Associated Actin Structure

Quantitative and volumetric assessment of filamentous actin fibers (F-actin) remains challenging due to their interconnected nature, leading researchers to utilize threshold based or qualitative measurement methods with poor reproducibility. Here we introduce a novel machine learning based methodology for accurate quantification and reconstruction of nuclei-associated F-actin. Utilizing a Convolutional Neural Network (CNN), we segment actin filaments and nuclei from 3D confocal microscopy images and then reconstruct each fiber by connecting intersecting contours on cross-sectional slices. This allowed measurement of the total number of actin filaments and individual actin filament length and volume in a reproducible fashion. Focusing on the role of F-actin in supporting nucleocytoskeletal connectivity, we quantified apical F-actin, basal F-actin, and nuclear architecture in mesenchymal stem cells (MSCs) following the disruption of the Linker of Nucleoskeleton and Cytoskeleton (LINC) Complexes. Disabling LINC in mesenchymal stem cells (MSCs) generated F-actin disorganization at the nuclear envelope characterized by shorter length and volume of actin fibers contributing a less elongated nuclear shape. Our findings not only present a new tool for mechanobiology but introduce a novel pipeline for developing realistic computational models based on quantitative measures of F-actin.

Quantitative evaluation of fiber network structure-property relationships in bacterial cellulose hydrogels

The present study attempts to elucidate the network structure-property relationships of bacterial cellulose (BC) hydrogels comprising cellulose nanofibrils with favorable mechanical properties. To achieve this, it is necessary to establish a method based on quantitative evaluation of nanofibril network structure, rather than a simple application of classical polymer network theory. BC hydrogels with various network structures related to their mechanical properties were prepared from seven bacterial strains. The crosslink densities of the gels were determined quantitatively by a combination of fluorescence microscopy and image analysis. The tensile tests showed that the stress-strain curves of BC hydrogels exhibited strain hardening according to the power law for strain, and the power exponent had a linear relationship with the crosslink density. This result provides insight into the structure-property relationships of BC hydrogels, which could be used to inform quality control, process optimization, and high-throughput property prediction during manufacture.

Automatic extraction of actin networks in plants

The actin cytoskeleton is essential in eukaryotes, not least in the plant kingdom where it plays key roles in cell expansion, cell division, environmental responses and pathogen defence. Yet, the precise structure-function relationships of properties of the actin network in plants are still to be unravelled, including details of how the network configuration depends upon cell type, tissue type and developmental stage. Part of the problem lies in the difficulty of extracting high-quality, quantitative measures of actin network features from microscopy data. To address this problem, we have developed DRAGoN, a novel image analysis algorithm that can automatically extract the actin network across a range of cell types, providing seventeen different quantitative measures that describe the network at a local level. Using this algorithm, we then studied a number of cases in Arabidopsis thaliana, including several different tissues, a variety of actin-affected mutants, and cells responding to powdery mildew. In many cases we found statistically-significant differences in actin network properties. In addition to these results, our algorithm is designed to be easily adaptable to other tissues, mutants and plants, and so will be a valuable asset for the study and future biological engineering of the actin cytoskeleton in globally-important crops.

Data driven and cell specific determination of nuclei-associated actin structure

Quantitative and volumetric assessment of filamentous actin fibers (F-actin) remains challenging due to their interconnected nature, leading researchers to utilize threshold based or qualitative measurement methods with poor reproducibility. Here we introduce a novel machine learning based methodology for accurate quantification and reconstruction of nuclei-associated F-actin. Utilizing a Convolutional Neural Network (CNN), we segment actin filaments and nuclei from 3D confocal microscopy images and then reconstruct each fiber by connecting intersecting contours on cross-sectional slices. This allowed measurement of the total number of actin filaments and individual actin filament length and volume in a reproducible fashion. Focusing on the role of F-actin in supporting nucleocytoskeletal connectivity, we quantified apical F-actin, basal F-actin, and nuclear architecture in mesenchymal stem cells (MSCs) following the disruption of the Linker of Nucleoskeleton and Cytoskeleton (LINC) Complexes. Disabling LINC in mesenchymal stem cells (MSCs) generated F-actin disorganization at the nuclear envelope characterized by shorter length and volume of actin fibers contributing a less elongated nuclear shape. Our findings not only present a new tool for mechanobiology but introduce a novel pipeline for developing realistic computational models based on quantitative measures of F-actin.

Tracing and tracking filamentous structures across scales: A systematic review

Filamentous structures are ubiquitous in nature, are studied in diverse scientific fields, and span vastly different spatial scales. Filamentous structures in biological systems fulfill different functions and often form dynamic networks that respond to perturbations. Therefore, characterizing the properties of filamentous structures and the networks they form is important to gain better understanding of systems level functions and dynamics. Filamentous structures are captured by various imaging technologies, and analysis of the resulting imaging data addresses two problems: (i) identification (tracing) of filamentous structures in a single snapshot and (ii) characterizing the dynamics (i.e., tracking) of filamentous structures over time. Therefore, considerable research efforts have been made in developing automated methods for tracing and tracking of filamentous structures. Here, we provide a systematic review in which we present, categorize, and discuss the state-of-the-art methods for tracing and tracking of filamentous structures in sparse and dense networks. We highlight the mathematical approaches, assumptions, and constraints particular for each method, allowing us to pinpoint outstanding challenges and offer perspectives for future research aimed at gaining better understanding of filamentous structures in biological systems.

Acquiring structural and mechanical information of a fibrous network through deep learning

Fibrous networks play an essential role in the structure and properties of a variety of biological and engineered materials, such as cytoskeletons, protein filament-based hydrogels, and entangled or crosslinked polymer chains. Therefore, insight into the structural features of these fibrous networks and their constituent filaments is critical for discovering the structure-property-function relationships of these material systems. In this paper, a fibrous network-deep learning system (FN-DLS) is established to extract fibrous network structure information from atomic force microscopy images. FN-DLS accurately assesses the structural and mechanical characteristics of fibrous networks, such as contour length, number of nodes, persistence length, mesh size and fractal dimension. As an open-source system, FN-DLS is expected to serve a vast community of scientists working on very diverse disciplines and pave the way for new approaches on the study of biological and synthetic polymer and filament networks found in current applied and fundamental sciences.

Quantitative mapping of keratin networks in 3D

Mechanobiology requires precise quantitative information on processes taking place in specific 3D microenvironments. Connecting the abundance of microscopical, molecular, biochemical, and cell mechanical data with defined topologies has turned out to be extremely difficult. Establishing such structural and functional 3D maps needed for biophysical modeling is a particular challenge for the cytoskeleton, which consists of long and interwoven filamentous polymers coordinating subcellular processes and interactions of cells with their environment. To date, useful tools are available for the segmentation and modeling of actin filaments and microtubules but comprehensive tools for the mapping of intermediate filament organization are still lacking. In this work, we describe a workflow to model and examine the complete 3D arrangement of the keratin intermediate filament cytoskeleton in canine, murine, and human epithelial cells both, in vitro and in vivo. Numerical models are derived from confocal airyscan high-resolution 3D imaging of fluorescence-tagged keratin filaments. They are interrogated and annotated at different length scales using different modes of visualization including immersive virtual reality. In this way, information is provided on network organization at the subcellular level including mesh arrangement, density and isotropic configuration as well as details on filament morphology such as bundling, curvature, and orientation. We show that the comparison of these parameters helps to identify, in quantitative terms, similarities and differences of keratin network organization in epithelial cell types defining subcellular domains, notably basal, apical, lateral, and perinuclear systems. The described approach and the presented data are pivotal for generating mechanobiological models that can be experimentally tested.