We present ilastik, an easy-to-use interactive tool that brings machine-learning-based (bio)image analysis to end users without substantial computational expertise. It contains pre-defined workflows for image segmentation, object classification, counting and tracking. Users adapt the workflows to the problem at hand by interactively providing sparse training annotations for a nonlinear classifier. ilastik can process data in up to five dimensions (3D, time and number of channels). Its computational back end runs operations on-demand wherever possible, allowing for interactive prediction on data larger than RAM. Once the classifiers are trained, ilastik workflows can be applied to new data from the command line without further user interaction. We describe all ilastik workflows in detail, including three case studies and a discussion on the expected performance.

BACKGROUND: Kidney epithelial cells perform complex vectorial fluid and solute transport at high volumes and rapid rates. Their structural organization both reflects and enables these sophisticated physiological functions. However, our understanding of the nanoscale spatial organization and intracellular ultrastructure that underlies these crucial cellular functions remains limited.

METHODS: To address this knowledge gap, we generated and reconstructed an extensive electron microscopic dataset of renal proximal tubule (PT) epithelial cells at isotropic resolutions down to 4nm. We employed artificial intelligence-based segmentation tools to identify, trace, and measure all major subcellular components. We complemented this analysis with immunofluorescence microscopy to connect subcellular architecture to biochemical function.

RESULTS: Our ultrastructural analysis revealed complex organization of membrane-bound compartments in proximal tubule cells. The apical endocytic system featured deep invaginations connected to an anastomosing meshwork of dense apical tubules, rather than discrete structures. The endoplasmic reticulum displayed distinct structural domains: fenestrated sheets in the basolateral region and smaller, disconnected clusters in the subapical region. We identified, quantified, and visualized membrane contact sites between endoplasmic reticulum, plasma membrane, mitochondria, and apical endocytic compartments. Immunofluorescence microscopy demonstrated distinct localization patterns for endoplasmic reticulum resident proteins at mitochondrial and plasma membrane interfaces.

CONCLUSIONS: This study provides novel insights into proximal tubule cell organization, revealing specialized compartmentalization and unexpected connections between membrane-bound organelles. We identified previously uncharacterized structures, including mitochondria-plasma membrane bridges and an interconnected endocytic meshwork, suggesting mechanisms for efficient energy distribution, cargo processing and structural support. Morphological differences between 4nm and 8nm datasets indicate subsegment-specific specializations within the proximal tubule. This comprehensive open-source dataset provides a foundation for understanding how subcellular architecture supports specialized epithelial function in health and disease.

Context plays a foundational role in determining how to interpret potentially fear-producing stimuli, yet the precise neurobiological substrates of context are poorly understood. In this issue of Cell, Xu et al. elegantly show that parallel neuronal circuits are necessary for two distinct roles of context in fear conditioning.

The olfactory system encodes information about molecules by spatiotemporal patterns of activity across distributed populations of neurons and extracts information from these patterns to control specific behaviors. Recent studies used in vivo recordings, optogenetics, and other methods to analyze the mechanisms by which odor information is encoded and processed in the olfactory system, the functional connectivity within and between olfactory brain areas, and the impact of spatiotemporal patterning of neuronal activity on higher-order neurons and behavioral outputs. The results give rise to a faceted picture of olfactory processing and provide insights into fundamental mechanisms underlying neuronal computations. This review focuses on some of this work presented in a Mini-Symposium at the Annual Meeting of the Society for Neuroscience in 2012.

Fluorescence image co-localization analysis is widely utilized to suggest biomolecular interaction. However, there exists some confusion as to its correct implementation and interpretation. In reality, co-localization analysis consists of at least two distinct sets of methods, termed co-occurrence and correlation. Each approach has inherent and often contrasting strengths and weaknesses. Yet, neither one can be considered to always be preferable for any given application. Rather, each method is most appropriate for answering different types of biological question. This Review discusses the main factors affecting multicolor image co-occurrence and correlation analysis, while giving insight into the types of biological behavior that are better suited to one approach or the other. Further, the limits of pixel-based co-localization analysis are discussed in the context of increasingly popular super-resolution imaging techniques.

Light sheet microscopy is a powerful technique for high-speed three-dimensional imaging of subcellular dynamics and large biological specimens. However, it often generates datasets ranging from hundreds of gigabytes to petabytes in size for a single experiment. Conventional computational tools process such images far slower than the time to acquire them and often fail outright due to memory limitations. To address these challenges, we present PetaKit5D, a scalable software solution for efficient petabyte-scale light sheet image processing. This software incorporates a suite of commonly used processing tools that are optimized for memory and performance. Notable advancements include rapid image readers and writers, fast and memory-efficient geometric transformations, high-performance Richardson-Lucy deconvolution and scalable Zarr-based stitching. These features outperform state-of-the-art methods by over one order of magnitude, enabling the processing of petabyte-scale image data at the full teravoxel rates of modern imaging cameras. The software opens new avenues for biological discoveries through large-scale imaging experiments.

MOTIVATION: Serial section microscopy is an established method for detailed anatomy reconstruction of biological specimen. During the last decade, high resolution electron microscopy (EM) of serial sections has become the de-facto standard for reconstruction of neural connectivity at ever increasing scales (EM connectomics). In serial section microscopy, the axial dimension of the volume is sampled by physically removing thin sections from the embedded specimen and subsequently imaging either the block-face or the section series. This process has limited precision leading to inhomogeneous non-planar sampling of the axial dimension of the volume which, in turn, results in distorted image volumes. This includes that section series may be collected and imaged in unknown order.

RESULTS: We developed methods to identify and correct these distortions through image-based signal analysis without any additional physical apparatus or measurements. We demonstrate the efficacy of our methods in proof of principle experiments and application to real world problems.

AVAILABILITY AND IMPLEMENTATION: We made our work available as libraries for the ImageJ distribution Fiji and for deployment in a high performance parallel computing environment. Our sources are open and available at http://github.com/saalfeldlab/section-sort, http://github.com/saalfeldlab/z-spacing and http://github.com/saalfeldlab/z-spacing-spark CONTACT: : [email protected] information: Supplementary data are available at Bioinformatics online.

Genome-wide CRISPR screens have transformed our ability to systematically interrogate human gene function, but are currently limited to a subset of cellular phenotypes. We report a novel pooled screening approach for a wider range of cellular and subtle subcellular phenotypes. Machine learning and convolutional neural network models are trained on the subcellular phenotype to be queried. Genome-wide screening then utilizes cells stably expressing dCas9-KRAB (CRISPRi), photoactivatable fluorescent protein (PA-mCherry), and a lentiviral guide RNA (gRNA) pool. Cells are screened by using microscopy and classified by artificial intelligence (AI) algorithms, which precisely identify the genetically altered phenotype. Cells with the phenotype of interest are photoactivated and isolated via flow cytometry, and the gRNAs are identified by sequencing. A proof-of-concept screen accurately identified PINK1 as essential for Parkin recruitment to mitochondria. A genome-wide screen identified factors mediating TFEB relocation from the nucleus to the cytosol upon prolonged starvation. Twenty-one of the 64 hits called by the neural network model were independently validated, revealing new effectors of TFEB subcellular localization. This approach, AI-photoswitchable screening (AI-PS), offers a novel screening platform capable of classifying a broad range of mammalian subcellular morphologies, an approach largely unattainable with current methodologies at genome-wide scale.

We present STIM, an imaging-based computational framework for exploring, visualizing, and processing high-throughput spatial sequencing datasets. STIM is built on the powerful ImgLib2, N5 and BigDataViewer (BDV) frameworks enabling transfer of computer vision techniques to datasets with irregular measurement-spacing and arbitrary spatial resolution, such as spatial transcriptomics data generated by multiplexed targeted hybridization or spatial sequencing technologies. We illustrate STIM’s capabilities by representing, visualizing, and automatically registering publicly available spatial sequencing data from 14 serial sections of mouse brain tissue.