Cell Image Analysis Techniques

inTRACKtive - A Web-Based Tool for Interactive Cell Tracking Visualization

inTRACKtive provides a web-based tool for interactive visualization and sharing of large 3D cell tracking datasets without requiring software installation or data downloads.

Investigating the role of molecular coating in human corneal endothelial cell primary culture using artificial intelligence-driven image analysis

The paper develops an AI-driven image analysis method to improve the assessment of human corneal endothelial cell morphology and compares the effects of 13 extracellular matrix coating molecules.

Ultrack: pushing the limits of cell tracking across biological scales

Ultrack improves cell tracking across 2D, 3D, and multi-channel time-lapse recordings by integrating multiple segmentations and temporal consistency, achieving state-of-the-art performance on benchmark datasets.

Nanoscale Optical Imaging, Reconstruction, and Spatial Analysis of Whole Mouse Glomeruli

The paper develops a pipeline for high-resolution imaging and analysis of whole mouse glomeruli, revealing novel aging and disease-related phenotypes.

Cell morphology and gene expression: tracking changes and complementarity across time and cell lines

The paper analyzes Cell Painting and transcriptomics data to explore how cell morphology and gene expression change over time and across cell lines in response to compounds.

Capturing Nematic Order on Tissue Surfaces of Arbitrary Geometry

The paper introduces a method to analyze nematic order on tissue surfaces of arbitrary geometry, validated in vitro and in vivo, revealing physical insights through 3D reconstruction from 2D image stacks.

Fast, flexible, learning-free organoid quantification and tracking with OrganoSeg2

OrganoSeg2 improves organoid segmentation and tracking, outperforming alternatives and enabling analysis of growth and radiotherapy responses in breast cancer organoids.

Deep learning-based image quantification of epithelial cell shapes and its application to polycystic kidney disease

This paper develops a deep learning pipeline to quantify epithelial cell shape and tight junctions, applied to ADPKD models and Drosophila egg chambers to study morphogenetic changes.

Embodied Intelligence Unlocks Autonomous Microscopy

This paper introduces an Embodied Intelligent Microscope System (EIMS) that autonomously controls microscopes using hierarchical reasoning and large models to execute complex biological tasks.

Nuclear Irregularity as a Universal Diagnostic Tool in Solid Tumors

This paper develops a method to analyze nuclear irregularity in cancer cells using imaging mass cytometry, achieving high accuracy in distinguishing cancerous from non-cancerous nuclei and identifying sub-populations of irregular cells.

Automatic Phenotyping Using Exhaustive Projection Pursuit

This paper introduces EPP, a method for automated phenotype identification in flow cytometry data, and evaluates it on four datasets.

An improved neural network model enables worm tracking in challenging conditions and increases signal-to-noise ratio in phenotypic screens

DeepTangleCrawl, DeepTangle retrained for crawling C. elegans, skeletonises more coiled and overlapping worms than Tierpsy, Omnipose or a PAF tracker, with longer tracks and larger screen effect sizes than Tierpsy.

Extracting biological structure and heterogeneity from the nano to the macro scale

This paper introduces SQUASSH, a convolutional neural network that fits structural models to fluorescence microscopy data to quantify variability across biological scales.

A Comprehensive Framework for Spatio-Temporal Analysis of DNA Damage Foci in Tumor Spheroids.

This paper develops a semi-automated image analysis framework to quantify spatiotemporal DNA damage foci in live tumor spheroids using live imaging and fluorescent sensors.

Morphological map of under- and over-expression of genes in human cells

The paper presents a comprehensive genetic perturbation dataset using Cell Painting to analyze gene expression effects in human cells, revealing novel gene clusters and functional relationships.

Quantifying bristle cell organization in Drosophila melanogaster

The paper quantifies bristle cell organization in Drosophila melanogaster using spatial clustering features to distinguish between wild-type and mutant patterns.

Automated Machine Learning Profiling with MAP-HR for Quantifying Homologous Recombination Foci in Patient Samples

The paper introduces MAP-HR, a machine learning platform for quantifying homologous recombination foci in patient samples to assess HR deficiency and guide therapy.

Scalable automated segmentation quantifies mitochondrial proteins and morphology at the nanoscale

This paper introduces MAPS, a deep-learning approach for automated segmentation of mitochondrial ultrastructure in 3D pan-ExM images, enabling high-throughput quantification of morphology and protein localization.

3DCellComposer - A Versatile Pipeline Utilizing 2D Cell Segmentation Methods for 3D Cell Segmentation

3DCellComposer uses 2D segmentation models to generate accurate 3D cell segmentations without requiring additional training or human annotations.

Triple-effect correction for Cell Painting data with contrastive and domain-adversarial learning

The paper introduces cpDistiller, a method to correct three technical effects in Cell Painting data using contrastive and domain-adversarial learning, improving analysis reliability and phenotypic response detection.

TU_MyCo-Vision: A Deep Learning Tool for Detection of Cell Morphologies in Fungal Microscopic Images

The paper introduces TU_MyCo-Vision, a deep learning tool for detecting 13 fungal morphotypes in bright-field images, showing strong performance on Aureobasidium pullulans and other fungal species.

AutoMorphoTrack: A modular framework for quantitative analysis of organelle morphology, motility, and interactions at single-cell resolution

AutoMorphoTrack automates organelle morphology, motility, and interaction analysis from fluorescence microscopy images, providing reproducible, publication-ready outputs.

Robust Consensus Nuclear and Cell Segmentation

This paper introduces a segmentation software wrapper that combines multiple existing methods to produce an optimized mask for cell segmentation.

Highly adaptable deep-learning platform for automated detection and analysis of vesicle exocytosis

The paper introduces IVEA, a deep-learning platform for automated exocytosis analysis in live-cell imaging, which is faster and more reliable than manual methods.

New Synapse Detection in the Whole-Brain Connectome of Drosophila

The paper improves synapse detection in Drosophila brain connectomes using new neural networks, achieving better performance in challenging regions and improved neuron clustering.

FeatureForest: the power of foundation models, theusability of random forests

FeatureForest uses foundation model embeddings with random forests to enable fast, accurate segmentation of complex biological images with minimal labeling.

Semi-automatic quantification of 3D Histone H3 phosphorylation signals during cell division in Arabidopsis root meristems

The paper develops a semi-automated 3D image analysis pipeline to quantify H3S10 phosphorylation dynamics during mitosis in Arabidopsis root cells, revealing small differences in phosphorylation levels between treated cells and mutants.

TickMotion: A user-friendly tool to measure and visualize muscle contractions and movements in insect and other arthropod tissues.

TickMotion measures and visualizes muscle contractions and movements in insect and arthropod tissues using pixel activity analysis from video recordings.

Interpretable representation learning for 3D multi-piece intracellular structures using point clouds

This paper introduces a morphology-appropriate representation learning framework for 3D multi-piece intracellular structures, showing improved sub-cluster discovery and phenotypic profiling.

A Variational Autoencoder Model for Clustering of Cell Nuclei on Microgroove Substrates: Potential for Disease Diagnosis

This study uses a variational autoencoder to cluster nuclei on microgroove substrates, distinguishing between wildtype and laminopathy myoblasts based on nuclear deformation.