Explore the vast range of titles available.

Deep neural networks have enabled astonishing transformations from low-resolution (LR) to super-resolved images. However, whether, and under what imaging conditions, such deep-learning models outperform super-resolution (SR) microscopy is poorly explored. Here, using multimodality structured illumination microscopy (SIM), we first provide an extensive dataset of LR–SR image pairs and evaluate the deep-learning SR models in terms of structural complexity, signal-to-noise ratio and upscaling factor. Second, we devise the deep Fourier channel attention network (DFCAN), which leverages the frequency content difference across distinct features to learn precise hierarchical representations of high-frequency information about diverse biological structures. Third, we show that DFCAN’s Fourier domain focalization enables robust reconstruction of SIM images under low signal-to-noise ratio conditions. We demonstrate that DFCAN achieves comparable image quality to SIM over a tenfold longer duration in multicolor live-cell imaging experiments, which reveal the detailed structures of mitochondrial cristae and nucleoids and the interaction dynamics of organelles and cytoskeleton.This study explores the performance of deep-learning models for super-resolution imaging and introduces models that utilize frequency content information in the Fourier domain to improve SIM reconstruction under low-SNR conditions.

Cryo-electron microscopy (cryo-EM) is rapidly becoming an attractive method in the field of structural biology. With the exploding popularity of cryo-EM, sample preparation must evolve to prevent congestion in the workflow. The dire need for improved microscopy samples has led to a diversification of methods. This Review aims to categorize and explain the principles behind various techniques in the preparation of vitrified samples for the electron microscope. Various aspects and challenges in the workflow are discussed, from sample optimization and carriers to deposition and vitrification. Reliable and versatile specimen preparation remains a challenge, and we hope to give guidelines and posit future directions for improvement.The quality of structural data obtained in cryo-EM is affected by multiple factors pertaining to sample preparation. This Review discusses available techniques and current challenges.

The role and importance of mechanical properties of cells and tissues in cellular function, development and disease has widely been acknowledged, however standard techniques currently used to assess them exhibit intrinsic limitations. Recently, Brillouin microscopy, a type of optical elastography, has emerged as a non-destructive, label- and contact-free method that can probe the viscoelastic properties of biological samples with diffraction-limited resolution in 3D. This led to increased attention amongst the biological and medical research communities, but it also sparked debates about the interpretation and relevance of the measured physical quantities. Here, we review this emerging technology by describing the underlying biophysical principles and discussing the interpretation of Brillouin spectra arising from heterogeneous biological matter. We further elaborate on the technique’s limitations, as well as its potential for gaining insights in biology, in order to guide interested researchers from various fields.

U-ExM enables near-native expansion microscopy of samples in vitro and in cells. The combination of U-ExM with confocal microscopy and HyVolution revealed details of centriole chirality that were previously accessible only by electron microscopy.

Accurate segmentation of objects in microscopy images remains a bottleneck for many researchers despite the number of tools developed for this purpose. Here, we present Segment Anything for Microscopy (μSAM), a tool for segmentation and tracking in multidimensional microscopy data. It is based on Segment Anything, a vision foundation model for image segmentation. We extend it by fine-tuning generalist models for light and electron microscopy that clearly improve segmentation quality for a wide range of imaging conditions. We also implement interactive and automatic segmentation in a napari plugin that can speed up diverse segmentation tasks and provides a unified solution for microscopy annotation across different microscopy modalities. Our work constitutes the application of vision foundation models in microscopy, laying the groundwork for solving image analysis tasks in this domain with a small set of powerful deep learning models. Segment Anything for Microscopy (μSAM) builds on the vision foundation model Segment Anything for high-quality image segmentation over a wide range of imaging conditions including light and electron microscopy.

Cryo-electron microscopy is a popular method for the determination of protein structures; however, identifying a sufficient number of particles for analysis can take months of manual effort. Current computational approaches find many false positives and require ad hoc postprocessing, especially for unusually shaped particles. To address these shortcomings, we develop Topaz, an efficient and accurate particle-picking pipeline using neural networks trained with a general-purpose positive-unlabeled learning method. This framework enables particle detection models to be trained with few sparsely labeled particles and no labeled negatives. Topaz retrieves many more real particles than conventional picking methods while maintaining low false-positive rates, is capable of picking challenging unusually shaped proteins (for example, small, non-globular and asymmetric particles), produces more representative particle sets and does not require post hoc curation. We demonstrate the performance of Topaz on two difficult datasets and three conventional datasets. Topaz is modular, standalone, free and open source (http://topaz.csail.mit.edu).

Cryo-electron microscopy (cryo-EM) single-particle analysis has proven powerful in determining the structures of rigid macromolecules. However, many imaged protein complexes exhibit conformational and compositional heterogeneity that poses a major challenge to existing three-dimensional reconstruction methods. Here, we present cryoDRGN, an algorithm that leverages the representation power of deep neural networks to directly reconstruct continuous distributions of 3D density maps and map per-particle heterogeneity of single-particle cryo-EM datasets. Using cryoDRGN, we uncovered residual heterogeneity in high-resolution datasets of the 80S ribosome and the RAG complex, revealed a new structural state of the assembling 50S ribosome, and visualized large-scale continuous motions of a spliceosome complex. CryoDRGN contains interactive tools to visualize a dataset’s distribution of per-particle variability, generate density maps for exploratory analysis, extract particle subsets for use with other tools and generate trajectories to visualize molecular motions. CryoDRGN is open-source software freely available at http://cryodrgn.csail.mit.edu.CryoDRGN is an unsupervised machine learning algorithm that reconstructs continuous distributions of three-dimensional density maps from heterogeneous single-particle cryo-EM data.

The acquisition of cryo-electron microscopy (cryo-EM) data from biological specimens must be tightly coupled to data preprocessing to ensure the best data quality and microscope usage. Here we describe Warp, a software that automates all preprocessing steps of cryo-EM data acquisition and enables real-time evaluation. Warp corrects micrographs for global and local motion, estimates the local defocus and monitors key parameters for each recorded micrograph or tomographic tilt series in real time. The software further includes deep-learning-based models for accurate particle picking and image denoising. The output from Warp can be fed into established programs for particle classification and 3D-map refinement. Our benchmarks show improvement in the nominal resolution, which went from 3.9 Å to 3.2 Å, of a published cryo-EM data set for influenza virus hemagglutinin. Warp is easy to install from http://github.com/cramerlab/warp and computationally inexpensive, and has an intuitive, streamlined user interface.

Segmenting the nuclei of cells in microscopy images is often the first step in the quantitative analysis of imaging data for biological and biomedical applications. Many bioimage analysis tools can segment nuclei in images but need to be selected and configured for every experiment. The 2018 Data Science Bowl attracted 3,891 teams worldwide to make the first attempt to build a segmentation method that could be applied to any two-dimensional light microscopy image of stained nuclei across experiments, with no human interaction. Top participants in the challenge succeeded in this task, developing deep-learning-based models that identified cell nuclei across many image types and experimental conditions without the need to manually adjust segmentation parameters. This represents an important step toward configuration-free bioimage analysis software tools.The 2018 Data Science Bowl challenged competitors to develop an accurate tool for segmenting stained nuclei from diverse light microscopy images. The winners deployed innovative deep-learning strategies to realize configuration-free segmentation.

Light-field microscopy has emerged as a technique of choice for high-speed volumetric imaging of fast biological processes. However, artifacts, nonuniform resolution and a slow reconstruction speed have limited its full capabilities for in toto extraction of dynamic spatiotemporal patterns in samples. Here, we combined a view-channel-depth (VCD) neural network with light-field microscopy to mitigate these limitations, yielding artifact-free three-dimensional image sequences with uniform spatial resolution and high-video-rate reconstruction throughput. We imaged neuronal activities across moving Caenorhabditis elegans and blood flow in a beating zebrafish heart at single-cell resolution with volumetric imaging rates up to 200 Hz.Reconstruction of light-field microscopy data with a deep-learning network achieves high reconstruction speed and reduces artifacts, as illustrated for moving C. elegans and beating zebrafish hearts.