Cell Image Analysis Techniques

Robust and generalizable segmentation of human functional tissue units

The paper evaluates five algorithms for segmenting functional tissue units in kidney and colon tissues using histological stains, comparing their accuracy and generalizability.

CellSighter - A neural network to classify cells in highly multiplexed images

CellSighter is a deep-learning pipeline that classifies cells in multiplexed images with high accuracy, reducing manual effort and improving consistency.

Brightest path tracing: A Python package to trace the brightest path in 2D and 3D images.

The paper introduces a Python package for tracing the brightest path in 2D and 3D images, providing a tool for analyzing image structures.

OME-Zarr: a cloud-optimized bioimaging file format with international community support

This paper describes OME-Zarr, a cloud-optimized bioimaging file format developed through community collaboration to improve scalability and data access.

A label-free method to track individuals and lineages of budding cells

This paper introduces BABY, a label-free method to track budding yeast cells and estimate growth rates using machine learning, revealing sizer- and timer-controlled bud growth and Sfp1 dynamics.

WormSwin: Instance segmentation of C. elegans using vision transformer

WormSwin segments C. elegans in videos using a vision transformer, achieving high accuracy and enabling tracking of overlapping worms.

Label-free imaging of 3D pluripotent stem cell differentiation dynamics on chip

The paper introduces a label-free deep learning method to predict nuclear staining in 3D stem cell cultures from bright-field images, enabling high-resolution tracking of differentiation dynamics.

Easing OMERO adoption with ezomero

The paper introduces ezomero, a Python library that simplifies OMERO API usage by providing a convenience layer for bioimaging data analysis.

Automated Microbial Classification System based on Deep Convolutional Neural Networks using Images from Colony Picker

The paper develops a deep CNN-based system for automated microbial classification using colony images, achieving high accuracy in identifying five species.

MIA: An Open Source Standalone Deep Learning Application for Microscopic Image Analysis

MIA is a deep learning tool for microscopic image analysis that combines a user-friendly interface with segmentation, detection, and classification capabilities, performing top three in public competitions.

Optimizing the Cell Painting assay for image-based profiling

The paper updates the Cell Painting assay protocol to improve morphological profiling, finding that simplified steps and reduced stain concentrations maintain robust outputs.

Unbiased single-cell morphology with self-supervised vision transformers

Self-supervised DINO features, learned without labels, describe cell morphology from subcellular detail to experimental groups and expose a hierarchy of biological and technical variation in three public datasets.

mEMbrain: an interactive deep learning MATLAB tool for connectomic segmentation on commodity desktops

mEMbrain provides an interactive MATLAB tool for connectomic segmentation, enabling user-friendly analysis of EM datasets with pre-trained networks and ground truth annotations.

Training deep learning models for cell image segmentation with sparse annotations

The paper shows that deep learning models for cell image segmentation can be trained effectively with sparse annotations and demonstrates the use of SAM to build such models quickly.

DeepIFC: virtual fluorescent labeling of blood cells in imaging flow cytometry data with deep learning

DeepIFC uses deep learning to generate fluorescent marker images from imaging flow cytometry data, enabling accurate cell typing and recognition of unseen cell types.

DeXtrusion: Automatic recognition of epithelial cell extrusion through machine learning in vivo

DeXtrusion automatically detects cell extrusion and death in epithelial tissues using machine learning, improving efficiency over manual methods.

Automatic inference of cell neighborhood in 2D and 3D using nuclear markers

The paper develops an automatic method to infer cell neighborhood using nuclear markers, achieving high accuracy across diverse organisms.

A deep learning framework for quantitative analysis of actin microridges

The paper develops a deep learning framework to segment actin microridges in zebrafish epidermal cells, enabling quantitative analysis of their mechanical and dynamic properties.

Cell shape characterization, alignment and comparison using FlowShape

The paper introduces FlowShape, a framework for analyzing cell shapes using spherical harmonics decomposition, and applies it to study shape changes in C. elegans embryos.

DeepSea: An efficient deep learning model for single-cell segmentation and tracking of time-lapse microscopy images

DeepSea is a deep learning model for segmenting and tracking single cells in time-lapse microscopy images, showing cell size control in embryonic stem cells during G1 phase.

But, what are the cells doing? Image Analysis pipeline to follow single cells in the zebrafish embryo

The paper introduces a user-friendly image analysis pipeline for tracking single cells in zebrafish embryos, enabling spatiotemporal analysis of cellular dynamics.

PXPermute: Unveiling staining importance in multichannel fluorescence microscopy

PXPermute identifies important fluorescent channels in IFC data by permuting pixel values and evaluating model performance, showing superior accuracy in channel selection.

Deep Learning models for retinal cell classification

This paper develops and evaluates Deep Learning models for classifying retinal cell types from cross-sectional images, showing improved performance with extended datasets.

Brainways: An AI-based Tool for Automated Registration, Quantification and Generation of Brain-wide Activity Networks Based on Fluorescence in Coronal Slices

Brainways automates registration, quantification, and network analysis of brain activity from fluorescence images, improving accuracy and efficiency in studying neural circuits.

Quantitative Geometric Modeling of Blood Cells from X-ray Histotomograms of Whole Zebrafish Larvae

The paper develops a semi-automated method to segment and model blood cells in zebrafish larvae using X-ray histotomography, enabling quantitative geometric analysis across developmental stages and mutants.

Seg2Link: an efficient and versatile solution for semi-automatic cell segmentation in 3D image stacks

Seg2Link provides a semi-automated tool for cell segmentation in 3D image stacks, combining deep learning predictions with manual corrections to improve accuracy and efficiency.

The CaliAli tool for long-term tracking of neuronal population dynamics in calcium imaging

CaliAli improves neuronal tracking in calcium imaging by aligning sessions before extracting features, enhancing detection of weak signals and enabling long-term dynamics analysis.

Spatial Tracking Across Time (STAT): Tracking Neurons Across In-Vivo Imaging Sessions through Optimizing Local Neighborhood Motion Consistency

The paper introduces a method to track neurons across multiple in-vivo imaging sessions without requiring full field-of-view registration, validated on simulated and experimental datasets.

Quantifying the relationship between cell proliferation and morphology during development of the face

The paper develops an imaging pipeline to quantify 3D cellular proliferation and morphology during mouse facial development, showing their tight correlation.

Sex-, strain and lateral differences in brain cytoarchitecture across a large mouse population

The paper analyzes brain cytoarchitecture in a large mouse population, finding non-uniform scaling of cell density and volume with brain size and significant sex, strain, and lateral differences.