Cell Image Analysis Techniques

LapTrack improves particle tracking by solving a linear assignment problem with customizable metrics and parallel parameter tuning, enhancing tracking accuracy on real and artificial datasets.

This study compares automated tools for quantifying fibrous network structures in images, finding that tools reliably measure relative changes but not absolute values.

CaPTure is a scalable pipeline for analyzing calcium imaging data from cultured neurons, enabling high-throughput phenotypic discovery.

microbeSEG provides a deep learning tool for automated cell segmentation in microbial cultures, achieving accurate results within 45 minutes of user time.

The paper introduces two methods to improve tissue segmentation in highly multiplexed images using real augmentations and nuclear envelope imaging, resulting in more accurate models.

RS-FISH detects FISH spots accurately and efficiently in 2D and 3D images, supporting applications like smFISH and spatial genomics.

The paper introduces a method called Dye Drop for high-throughput single-cell assays in 384-well plates, enabling detailed dose-response analysis of small molecules in breast cancer cell lines.

The paper introduces a GAN-based method to predict protein localization in fluorescence images and manipulate protein activity to study localization-based functions.

This study develops a deep learning algorithm for analyzing label-free brightfield microscopy images to detect cancer stem-like cell fate, showing improved accuracy and speed compared to other methods.

This paper introduces TOBLERONE, a topological image analysis tool for automated cell segmentation and membrane order quantification using confocal microscopy images.

Cellpose 2.0 enables training specialist segmentation models with minimal user effort and data, achieving state-of-the-art results on new image categories.

Scellseg is a cell segmentation tool that uses pre-training and contrastive fine-tuning, outperforming existing methods on three datasets with minimal training data.

The paper compares morphology and gene expression data to determine their complementary roles in mapping cell states across drug perturbations.

SOPRA is a method for analyzing high-content screens by regressing non-averaged cell feature data to identify significant changes in cell populations.

The paper improves GAN-based deep learning models for cell organization and introduces evaluation criteria to assess synthetic cell images' accuracy.

SATINN automates testis histology analysis using CNNs to classify cell types and tubule stages in mouse mutants with high accuracy.

BioImageIT integrates FAIR data management with analysis to address challenges in bioimaging data sharing and annotation.

The paper introduces a method to decompose neuropil calcium imaging data into bouton-like structures and finds the resulting network is scale-free.

This paper introduces a polymer physics-based method to classify neurons using 3D coordinates, showing it complements existing methods and provides a physical understanding of neuronal morphology.

CardioVinci uses deep learning to automate the analysis of 3D cardiac ultrastructure changes from large EM imaging datasets.

The paper introduces a method for precise single-cell tracking and lineage reconstruction using cell region fingerprints, improving tracking performance across species and data types.

This paper introduces a method for automated lineage reconstruction in developing embryos using sparse annotations, achieving 75.8% accuracy on mouse embryos compared to 31.8% previously.

The paper identifies small molecule regulators of biological pathways by matching compound effects to known pathway phenotypes in public cell image data.

pcnaDeep tracks single-cells and assigns mother-daughter relationships using deep-learning and cell cycle profiling from fluorescent biosensors.

The paper develops a method to remove technical artifacts from high-throughput imaging assays using systematic replication, improving biological signal clarity.

The paper introduces Zellige, a software tool for extracting multiple surfaces from 3D microscopy images, demonstrating its performance on synthetic and biological samples.

ASHLAR is a Python tool that stitches and registers highly multiplexed whole slide images to generate accurate mosaics, outperforming existing software.

Griottes generates network representations of segmented tissue images to extract cell interactions and properties efficiently.

The paper presents a similarity search tool for comparing neural morphologies across species and brain regions using morphometric and vectorized descriptors.

The paper uses deep generative networks to predict nuclear position from actin filament arrangements in cells, achieving over 70% accuracy in localization.