Explore the vast range of titles available.

Deep learning algorithms are powerful tools for analyzing, restoring and transforming bioimaging data. One promise of deep learning is parameter-free one-click image analysis with expert-level performance in a fraction of the time previously required. However, as with most emerging technologies, the potential for inappropriate use is raising concerns among the research community. In this Comment, we discuss key concepts that we believe are important for researchers to consider when using deep learning for their microscopy studies. We describe how results obtained using deep learning can be validated and propose what should, in our view, be considered when choosing a suitable tool. We also suggest what aspects of a deep learning analysis should be reported in publications to ensure reproducibility. We hope this perspective will foster further discussion among developers, image analysis specialists, users and journal editors to define adequate guidelines and ensure the appropriate use of this transformative technology.

Metastasis is associated with poor prognosis in breast cancer patients. Not all cancer cells within a tumor are capable of metastasizing. The microRNA-200 (miR-200) family, which regulates the mesenchymal-to-epithelial transition, is enriched in the serum of patients with metastatic cancers. Ectopic expression of miR-200 can confer metastatic ability to poorly metastatic tumor cells in some settings. Here, we investigated whether metastatic capability could be transferred between metastatic and nonmetastatic cancer cells via extracellular vesicles. miR-200 was secreted in extracellular vesicles from metastatic murine and human breast cancer cell lines, and miR-200 levels were increased in sera of mice bearing metastatic tumors. In culture, murine and human metastatic breast cancer cell extracellular vesicles transferred miR-200 microRNAs to nonmetastatic cells, altering gene expression and promoting mesenchymal-to-epithelial transition. In murine cancer and human xenograft models, miR-200-expressing tumors and extracellular vesicles from these tumors promoted metastasis of otherwise weakly metastatic cells either nearby or at distant sites and conferred to these cells the ability to colonize distant tissues in a miR-200-dependent manner. Together, our results demonstrate that metastatic capability can be transferred by the uptake of extracellular vesicles.

Despite significant progress, high-speed live-cell super-resolution studies remain limited to specialized optical setups, generally requiring intense phototoxic illumination. Here, we describe a new analytical approach, super-resolution radial fluctuations (SRRF), provided as a fast graphics processing unit-enabled ImageJ plugin. In the most challenging data sets for super-resolution, such as those obtained in low-illumination live-cell imaging with GFP, we show that SRRF is generally capable of achieving resolutions better than 150 nm. Meanwhile, for data sets similar to those obtained in PALM or STORM imaging, SRRF achieves resolutions approaching those of standard single-molecule localization analysis. The broad applicability of SRRF and its performance at low signal-to-noise ratios allows super-resolution using modern widefield, confocal or TIRF microscopes with illumination orders of magnitude lower than methods such as PALM, STORM or STED. We demonstrate this by super-resolution live-cell imaging over timescales ranging from minutes to hours. Super-resolution fluorescent imaging typically makes use of intense phototoxic illumination. Here the authors achieve live-cell super-resolution imaging using low-illumination standard microscopes with the aid of a new analytical approach called Super-Resolution Radial Fluctuations (SRRF), provided as an ImageJ plugin.

Super-resolution microscopy depends on steps that can contribute to the formation of image artifacts, leading to misinterpretation of biological information. We present NanoJ-SQUIRREL, an ImageJ-based analytical approach that provides quantitative assessment of super-resolution image quality. By comparing diffraction-limited images and super-resolution equivalents of the same acquisition volume, this approach generates a quantitative map of super-resolution defects and can guide researchers in optimizing imaging parameters.

Fluorescence microscopy is a key driver of discoveries in the life sciences, with observable phenomena being limited by the optics of the microscope, the chemistry of the fluorophores, and the maximum photon exposure tolerated by the sample. These limits necessitate trade-offs between imaging speed, spatial resolution, light exposure, and imaging depth. In this work we show how content-aware image restoration based on deep learning extends the range of biological phenomena observable by microscopy. We demonstrate on eight concrete examples how microscopy images can be restored even if 60-fold fewer photons are used during acquisition, how near isotropic resolution can be achieved with up to tenfold under-sampling along the axial direction, and how tubular and granular structures smaller than the diffraction limit can be resolved at 20-times-higher frame rates compared to state-of-the-art methods. All developed image restoration methods are freely available as open source software in Python, FIJI, and KNIME.

Deep Learning (DL) methods are powerful analytical tools for microscopy and can outperform conventional image processing pipelines. Despite the enthusiasm and innovations fuelled by DL technology, the need to access powerful and compatible resources to train DL networks leads to an accessibility barrier that novice users often find difficult to overcome. Here, we present ZeroCostDL4Mic, an entry-level platform simplifying DL access by leveraging the free, cloud-based computational resources of Google Colab. ZeroCostDL4Mic allows researchers with no coding expertise to train and apply key DL networks to perform tasks including segmentation (using U-Net and StarDist), object detection (using YOLOv2), denoising (using CARE and Noise2Void), super-resolution microscopy (using Deep-STORM), and image-to-image translation (using Label-free prediction - fnet, pix2pix and CycleGAN). Importantly, we provide suitable quantitative tools for each network to evaluate model performance, allowing model optimisation. We demonstrate the application of the platform to study multiple biological processes. Deep learning methods show great promise for the analysis of microscopy images but there is currently an accessibility barrier to many users. Here the authors report a convenient entry-level deep learning platform that can be used at no cost: ZeroCostDL4Mic.

With the widespread uptake of two-dimensional (2D) and three-dimensional (3D) single-molecule localization microscopy (SMLM), a large set of different data analysis packages have been developed to generate super-resolution images. In a large community effort, we designed a competition to extensively characterize and rank the performance of 2D and 3D SMLM software packages. We generated realistic simulated datasets for popular imaging modalities—2D, astigmatic 3D, biplane 3D and double-helix 3D—and evaluated 36 participant packages against these data. This provides the first broad assessment of 3D SMLM software and provides a holistic view of how the latest 2D and 3D SMLM packages perform in realistic conditions. This resource allows researchers to identify optimal analytical software for their experiments, allows 3D SMLM software developers to benchmark new software against the current state of the art, and provides insight into the current limits of the field.This study reports results from the second community-wide single-molecule localization microscopy software challenge, which tested over 30 software packages on realistic simulated data for multiple popular 3D image acquisition modes, as well as 2D localization microscopy.

Despite the central role of division in bacterial physiology, how division proteins work together as a nanoscale machine to divide the cell remains poorly understood. Cell division by cell wall synthesis proteins is guided by the cytoskeleton protein FtsZ, which assembles at mid-cell as a dense Z-ring formed of treadmilling filaments. However, although FtsZ treadmilling is essential for cell division, the function of FtsZ treadmilling remains unclear. Here, we systematically resolve the function of FtsZ treadmilling across each stage of division in the Gram-positive model organism Bacillus subtilis using a combination of nanofabrication, advanced microscopy, and microfluidics to measure the division-protein dynamics in live cells with ultrahigh sensitivity. We find that FtsZ treadmilling has two essential functions: mediating condensation of diffuse FtsZ filaments into a dense Z-ring, and initiating constriction by guiding septal cell wall synthesis. After constriction initiation, FtsZ treadmilling has a dispensable function in accelerating septal constriction rate. Our results show that FtsZ treadmilling is critical for assembling and initiating the bacterial cell division machine. Bacterial cell division by cell wall synthesis proteins is guided by treadmilling filaments of the cytoskeleton protein FtsZ. Here authors use nanofabrication, advanced microscopy, and microfluidics to resolve the function of FtsZ treadmilling in the Gram-positive model organism Bacillus subtilis .

Live-cell super-resolution microscopy enables the imaging of biological structure dynamics below the diffraction limit. Here we present enhanced super-resolution radial fluctuations (eSRRF), substantially improving image fidelity and resolution compared to the original SRRF method. eSRRF incorporates automated parameter optimization based on the data itself, giving insight into the trade-off between resolution and fidelity. We demonstrate eSRRF across a range of imaging modalities and biological systems. Notably, we extend eSRRF to three dimensions by combining it with multifocus microscopy. This realizes live-cell volumetric super-resolution imaging with an acquisition speed of ~1 volume per second. eSRRF provides an accessible super-resolution approach, maximizing information extraction across varied experimental conditions while minimizing artifacts. Its optimal parameter prediction strategy is generalizable, moving toward unbiased and optimized analyses in super-resolution microscopy. Enhanced super-resolution radial fluctuations (eSRRF) offers improved image fidelity and resolution compared to the popular SRRF method and further enables volumetric live-cell super-resolution imaging at high speeds.

correspondence: We hope that the code and suggestions provided here will inspire other researchers to take advantage of the benefits of using MLE for analyzing Poisson-distributed data, reducing biases and errors in parametric results from histogram-based analysis.