Cell Image Analysis Techniques

FISH-quant v2 is a modular tool for analyzing smFISH images, enabling detection, segmentation, quantification, and visualization of RNA localization at the single-cell level.

This study proposes a method to identify regions in developing tissues with distinct cellular dynamics and deformation, using image segmentation, clustering, and boundary smoothing.

MICRA-Net is a weakly-supervised neural network that uses a simple classification task to perform segmentation, detection, and enumeration on microscopy images with limited annotated data.

The paper improves a competitive cell tracking algorithm by optimizing training parameters and data augmentation, achieving better performance in the Cell Tracking Challenge 2021.

OSCAR quantifies densely packed 3D biological samples by reconstructing objects in 3D space and identifying cell fates in zebrafish retina.

MethodsJ2 is a software tool that collects metadata and generates text for the methods section of microscopy publications.

The paper introduces PIE, a software tool for automatically tracking microbial colony growth in low-resolution images, enabling large-scale analysis of growth and fluorescence properties.

The paper introduces MorphVAE, a variational autoencoder for generating neural morphologies from 3D-walks, showing improved cell type discrimination and efficient morphology generation.

The paper introduces DeepCytometer, a deep learning pipeline for segmenting whole slides of mouse white adipose tissue, and uses it to analyze phenotypes in Klf14 mouse models.

Micro-Meta App is an open-source tool that helps collect and organize microscopy metadata according to community standards, improving reproducibility and data sharing.

This paper introduces DeepHACX, a self-training deep learning framework for interpretable fine-grained phenotyping of live cell dynamics, revealing specific responses to pharmacological perturbations in migrating epithelial cells.

The paper presents a method for automated 3D mitochondria segmentation in electron microscopy data, achieving high performance on rat and human cortex samples.

The paper develops an unsupervised deep learning model for two-photon imaging data that incorporates structural knowledge to improve interpretability and modeling of neural activity.

The paper develops a deep learning algorithm to predict neurite structure and length in fluorescence imaging, achieving near-human accuracy and efficiency for large datasets.

The paper introduces ME-VAE, a multi-encoder VAE for single-cell image analysis that extracts transform-invariant biologically meaningful features, improving cell population separation and phenotypic differences.

ShapoGraphy provides an interactive visualisation tool for creating pictorial representations of bioimaging data to enhance understanding and analysis of complex phenotypic information.

MARS-Net is a deep learning pipeline that improves cell edge segmentation across multiple live cell microscopy types, enabling accurate morphodynamics analysis.

The paper introduces next-generation file formats (NGFF) to improve the FAIRness of bioimaging data by addressing limitations of translation and conversion approaches.

The paper improves microscopy video segmentation by retraining a CNN with a Siamese network setup using unlabelled video frames.

EXTRACT, a GPU-based cell extraction method using one-sided Huber robust regression, processed 199 Allen Brain Observatory sessions (~12 TB) in a day and gave cleaner traces than CAIMAN or CNMF-E.

MicroMator enables reactive microscopy experiments by integrating real-time data with machine learning for single-cell control and recombination.

This paper develops CNNs to segment tissues and proliferating cells in light-sheet microscopy images, achieving results comparable to manual segmentation.

PuBliCiTy provides a Python toolkit for biological image analysis, including tools for large image processing, web annotation, and machine learning model development.

The paper introduces a transfer learning framework for cell segmentation that incorporates geometric features to improve performance on in situ tissue images using in vitro data.

The paper develops a method to quantify clearing efficiency in 3D cell spheroids using a deep convolutional neural network and local contrast metrics.

The paper generates fluorescent labels from bright-field images using deep learning to enable virtual staining of adipocyte cells, improving feature extraction for downstream analysis.

The paper introduces MorphoHub, a platform for generating petabyte-scale multi-morphometry data, enabling high-quality analysis of neuronal structures in whole brain datasets.

This paper introduces a self-supervised machine learning algorithm for automated live cell segmentation and analysis without user supervision or adjustable parameters.

MAPPER identifies differential regulation of Drosophila wing features through automated image analysis, revealing scaling patterns and the role of Piezo in bilateral symmetry.