Automated Analysis of Neuronal Morphology in 2D Fluorescence Micrographs through an Unsupervised Semantic Segmentation of Neurons.

Brain function emerges from a highly complex network of specialized cells that are interlinked by billions of synapses. The synaptic connectivity between neurons is established between the elongated processes of their axons and dendrites or, together, neurites. To establish these connections, cellular neurites have to grow in highly specialized, cell-type dependent patterns covering extensive distances and connecting with thousands of other neurons. The outgrowth and branching of neurites are tightly controlled during development and are a commonly used functional readout of imaging in the neurosciences. Manual analysis of neuronal morphology from microscopy images, however, is very time intensive and prone to bias. Most automated analyses of neurons rely on reconstruction of the neuron as a whole without a semantic analysis of each neurite. A fully-automated classification of all neurites still remains unavailable in open-source software. Here we present a standalone, GUI-based software for batch-quantification of neuronal morphology in two-dimensional fluorescence micrographs of cultured neurons with minimal requirements for user interaction. Single neurons are first reconstructed into binarized images using a Hessian-based segmentation algorithm to detect thin neurite structures combined with intensity- and shape-based reconstruction of the cell body. Neurites are then classified into axon, dendrites and their branches of increasing order using a geodesic distance transform of the cell skeleton. The software was benchmarked against a published dataset and reproduced the phenotype observed after manual annotation. Our tool promises accelerated and improved morphometric studies of neuronal morphology by allowing for consistent and automated analysis of large datasets.

Quantifying morphologies of developing neuronal cells using deep learning with imperfect annotations.

The functionality of human intelligence relies on the interaction and health of neurons, hence, quantifying neuronal morphologies can be crucial for investigating the functionality of the human brain. This paper proposes a deep learning (DL) based method for segmenting and quantifying neuronal structures in fluorescence microscopy images of developing neuronal cells cultured in vitro. Compared to the majority of supervised DL-based segmentation methods that heavily rely on creating exact corresponding masks of neuronal structures for the preparation of training samples, the proposed approach allows for imperfect annotation of neurons, as it only requires tracing the centrelines of the neurites. This ability accelerates the preparation of training data by several folds. Our proposed framework is built on a modified version of PSPNet with an EfficientNet backbone pre-trained on the CityScapes dataset. To handle the imperfectness of training samples, we incorporated a weighted combination of two loss functions, namely the Dice loss and Lovász loss functions, into our network. We evaluated the proposed framework and several other state-of-the-art methods on a published dataset of approximately 900 manually quantified cultured mouse neurons. Our results indicate a close correlation between the proposed method and manual quantification in terms of neuron length and the number of branches while demonstrating improved analysis speed. Furthermore, the proposed method achieved high accuracy in neuron segmentation, as evidenced by the evaluation of the neurons' length and number of branches.

Precise measurement of nanoscopic septin ring structures with deep learning-assisted quantitative superresolution microscopy.

The combination of image analysis and superresolution microscopy methods allows for unprecedented insight into the organization of macromolecular assemblies in cells. Advances in deep learning (DL)-based object recognition enable the automated processing of large amounts of data, resulting in high accuracy through averaging. However, while the analysis of highly symmetric structures of constant size allows for a resolution approaching the dimensions of structural biology, DL-based image recognition may introduce bias. This prohibits the development of readouts for processes that involve significant changes in size or shape of amorphous macromolecular complexes. Here we address this problem by using changes of septin ring structures in single molecule localization-based superresolution microscopy data as a paradigm. We identify potential sources of bias resulting from different training approaches by rigorous testing of trained models using real or simulated data covering a wide range of possible results. In a quantitative comparison of our models, we find that a trade-off exists between measurement accuracy and the range of recognized phenotypes. Using our thus verified models, we find that septin ring size can be explained by the number of subunits they are assembled from alone. Furthermore, we provide a new experimental system for the investigation of septin polymerization.

Live-cell imaging of circadian clock protein dynamics in CRISPR-generated knock-in cells.

The cell biology of circadian clocks is still in its infancy. Here, we describe an efficient strategy for generating knock-in reporter cell lines using CRISPR technology that is particularly useful for genes expressed transiently or at low levels, such as those coding for circadian clock proteins. We generated single and double knock-in cells with endogenously expressed PER2 and CRY1 fused to fluorescent proteins allowing us to simultaneously monitor the dynamics of CRY1 and PER2 proteins in live single cells. Both proteins are highly rhythmic in the nucleus of human cells with PER2 showing a much higher amplitude than CRY1. Surprisingly, CRY1 protein is nuclear at all circadian times indicating the absence of circadian gating of nuclear import. Furthermore, in the nucleus of individual cells CRY1 abundance rhythms are phase-delayed (~5 hours), and CRY1 levels are much higher (>5 times) compared to PER2 questioning the current model of the circadian oscillator.

Expansion Stimulated Emission Depletion Microscopy (ExSTED).

Stimulated emission depletion (STED) microscopy is routinely used to resolve the ultrastructure of cells with a ∼10-fold higher resolution compared to diffraction limited imaging. While STED microscopy is based on preparing the excited state of fluorescent probes with light, the recently developed expansion microscopy (ExM) provides subdiffraction resolution by physically enlarging the sample before microscopy. The expansion of the fixed cells by cross-linking and swelling of hydrogels easily enlarges the sample ∼4-fold and hence increases the effective optical resolution by this factor. To overcome the current limits of these complementary approaches, we combined ExM with STED (ExSTED) and demonstrated an increase in resolution of up to 30-fold compared to conventional microscopy (<10 nm lateral and ∼50 nm isotropic). While the increase in resolution is straightforward, we found that high-fidelity labeling via multi-epitopes is required to obtain emitter densities that allow ultrastructural details with ExSTED to be resolved. Our work provides a robust template for super-resolution microscopy of entire cells in the ten nanometer range.