Cell Image Analysis Techniques

An accessible digital imaging workflow for multiplexed quantitative analysis of adult eye phenotypes in Drosophila melanogaster

This paper presents a digital imaging workflow for standardized, multiplexed quantitative analysis of adult Drosophila eye phenotypes, reducing variability and enabling precise morphometric comparisons.

An optimized live imaging and growth analysis approach for Arabidopsis Sepals

The paper develops an optimized live imaging and analysis pipeline for tracking growth in Arabidopsis sepal epidermal layers.

When the pen is mightier than the sword: semi-automatic 2 and 3D image labelling

The paper introduces a semi-automatic annotation tool for 2D and 3D image labelling to reduce expert effort in creating object-based labels.

Pseudo-spectral angle mapping for automated pixel-level analysis of highly multiplexed tissue image data

This paper introduces pSAM, a method for analyzing high-plex immunofluorescence images, and shows it can generalize across different staining panels and tissues without manual annotation.

nf-root: a best-practice pipeline for deep learning-based analysis of apoplastic pH in microscopy images of developmental zones in plantroot tissue

nf-root automates apoplastic pH analysis in plant root images using deep learning, achieving near-human performance and reducing analysis time.

Spontaneous breaking of symmetry in overlapping cell instance segmentation using diffusion models

This paper introduces a diffusion model-based method for instance segmentation that spontaneously breaks symmetry, allowing overlapping labels in cell instance segmentation.

3D Nuclei Segmentation by Combining GAN Based Image Synthesis and Existing 3D Manual Annotations

The paper presents a method to segment 3D nuclei in low signal-to-noise ratio images using a combination of 2D Stardist and a conditional GAN to generate synthetic 3D masks.

Bridging the Gap: Integrating Cutting-edge Techniques into Biological Imaging with deepImageJ

This paper introduces enhancements to deepImageJ, a Fiji/ImageJ plugin, by integrating the Java Deep Learning Library (JDLL) to support multiple deep learning frameworks, enabling complex bioimage analysis tasks.

CellBoost: A pipeline for machine assisted annotation in neuroanatomy

CellBoost reduces annotation labor in neuroanatomy by combining human judgment and machine learning, achieving accuracy comparable to human agreement while decreasing time by up to ten-fold.

Microsnoop: A Generalized Tool for Unbiased Representation of Diverse Microscopy Images

Microsnoop is a deep learning tool that provides unbiased representation of diverse microscopy images, outperforming existing methods across multiple datasets.

ActSort: An active-learning accelerated cell sorting algorithm for large-scale calcium imaging datasets

ActSort reduces human labor in cell sorting for calcium imaging by 1-3% and improves accuracy through active learning and expert features.

Development of an optimized machine learning approach to enhance brain metastatic burden assessment in preclinical models.

The paper develops a semi-automatic machine learning approach to quantify brain metastatic burden in mouse whole-brain images using QuPath.

Live Cell Fluorescence Microscopy - An End-to-End Workflow for High-Throughput Image and Data Analysis

The paper introduces a workflow for high-throughput fluorescence microscopy analysis that enables unbiased, automated processing of live-cell data.

Cellos: High-throughput deconvolution of 3D organoid dynamics at cellular resolution for cancer pharmacology

Cellos is a high-throughput image analysis pipeline for 3D organoid segmentation and analysis, enabling accurate quantification of drug responses and cell interactions in cancer organoids.

CellStitch: 3D Cellular Anisotropic Image Segmentation via Optimal Transport

CellStitch improves 3D cell segmentation in anisotropic images using optimal transport, outperforming existing methods on anisotropic datasets.

Three-dimensional reconstruction of fetal rhesus macaque kidneys at single-cell resolution reveals complex inter-relation of structures

This paper uses deep learning to label 17 kidney microstructures in 3D fetal rhesus macaque kidneys, revealing spatial relationships between glomeruli, arteries, and nephrons.

CellWalker: A user-friendly and modular computational pipeline for morphological analysis of microscopy images

CellWalker provides a modular, open-source pipeline for segmentation and morphological analysis of microscopy images using deep learning and Blender tools.

PEPSI: Polarity measurements from spatial proteomics imaging suggest immune cell engagement

The paper introduces a metric to measure surface protein polarity from immunofluorescence imaging and shows it identifies immune cell states linked to tumor engagement, improving survival prediction models.

A Graph Matching Approach to Tracking Neurons in Freely-Moving C. elegans

This paper introduces a graph matching method to track neurons in freely-moving C. elegans, achieving over 75% accuracy with five labeled frames.

Multi-ContrastiveVAE disentangles perturbation effects in single cell images from optical pooled screens

The paper introduces a contrastive analysis framework to disentangle perturbation effects from natural cell variation in optical pooled screens, showing improved performance in generating embeddings and reducing technical artifacts.

CellTool: an open source software combining bio-image analysis and mathematical modeling

CellTool is an open-source software for image analysis and mathematical modeling, offering tools for processing time-lapse microscopy data and custom model fitting.

A deep learning convolutional neural network distinguishes neuronal models of Parkinson's disease from matched controls

This study uses a convolutional neural network to classify Parkinson's disease models from control cells with high accuracy using microscopy images.

Quantitative cell morphology in C. elegans embryos reveals regulations of cell volume asymmetry

The paper quantifies cell morphology in C. elegans embryos, revealing that signaling pathways regulate both cell fate asymmetry and volume asymmetry.

Multi-Layered Maps of Neuropil with Segmentation-Guided Contrastive Learning

SegCLR, a self-supervised learning method, enables classification of cellular subcompartments and cell types from 3D electron microscopy data with minimal labeled data.

CellSAM: A Foundation Model for Cell Segmentation

Bounding boxes from a transformer detector let the Segment Anything Model segment cells automatically; one generalist model beats generalist Cellpose and matches inter-annotator agreement across mammalian, yeast and bacterial images.

Cell Spotter (CSPOT): A machine-learning approach to automated cell spotting and quantification of highly multiplexed tissue images

Cell Spotter (CSPOT) uses supervised machine learning to automate cell spotting and quantification in highly multiplexed tissue images, improving speed, accuracy, and reproducibility.

Label-free deep learning-based species classification of bacteria imaged by phase-contrast microscopy

The paper uses deep learning to classify bacteria species from phase-contrast microscopy images without staining or fixation, achieving over 98% accuracy.

Deep learning-based image analysis identifies a DAT-negative subpopulation of dopaminergic neurons in the lateral Substantia nigra.

The paper uses deep learning to identify a DAT-negative subpopulation of dopaminergic neurons in the lateral substantia nigra in mouse and human brain sections.

MEM-GAN: A Pseudo Membrane Generator for Single-cell Imaging in Fluorescent Microscopy

The paper introduces a GAN-based method to generate high-quality membranes for cells with poor staining in fluorescent microscopy images, improving segmentation accuracy.

HiTIPS: High-Throughput Image Processing Software for the Study of Nuclear Architecture and Gene Expression

HiTIPS provides a flexible, open-source platform for high-throughput image analysis in cell biology, supporting customization and integration of new algorithms for tasks like segmentation, tracking, and quantification.