Cell Image Analysis Techniques

Characterising cancer-stroma interactions through high-content phenotyping from microscopy time-lapses

This study uses live-cell imaging and automated phenotyping to characterize cancer-stromal interactions, revealing phenotypic changes in breast cancer cells exposed to cancer-associated fibroblasts.

Automated classification of cellular expression in multiplexed imaging data with Nimbus

The paper introduces Nimbus, a deep learning model for predicting marker positivity in multiplexed imaging data using a pre-trained dataset, and shows its integration with clustering for cell subtype identification.

TrueSpot: A robust automated tool for quantifying signal puncta in fluorescent imaging

TrueSpot is an automated tool for quantifying signal puncta in fluorescent imaging, outperforming 2D methods in 3D spot detection.

Combinatorial protein barcodes enable self-correcting neuron tracing with nanoscale molecular context

The paper introduces PRISM, a platform that uses combinatorial protein barcodes to enable self-correcting neuron tracing with molecular context, improving tracing accuracy and handling spatial gaps.

Beyond Agreement: Standardizing Crowdsourced Synapse Annotations through Proofreading in EM Connectomics

The paper introduces a standardized proofreading protocol for improving synapse annotations in EM connectomics by combining machine learning with multi-rater calibration and probabilistic modeling.

Cell-APP: A generalizable method for cell annotation and cell-segmentation model training

Cell-APP automates the creation of high-quality training data for cell segmentation models by combining nuclear fluorescence images with transmitted-light images to generate masks and classify cells.

Software and pipelines for registration and analyses of rodent brain image data in reference atlas space

The paper presents software tools for registering and analyzing rodent brain image data in reference atlas space, enabling spatially informed analysis of anatomical and molecular features.

On the Utility of Virtual Staining for Downstream Applications as it relates to Task Network Capacity

This study evaluates how virtual staining affects downstream tasks like segmentation and classification, showing its effectiveness depends on the task network's capacity.

scPortrait integrates single-cell images into multimodal modeling

scPortrait integrates single-cell images with proteomics and transcriptomics data to identify cancer-associated macrophage subpopulations and embed images into transcriptome atlases.

MicroNucML: A machine learning approach for micronuclei segmentation and the refinement of nuclei-micronuclei relationships

This paper introduces a machine learning tool for micronuclei segmentation and refines nuclei-micronuclei relationships using a two-phase labeling approach and a Mask-RCNN model.

Deep Learning Detection and Classification of Red Blood Cells: Towards a Universal Dataset

This study evaluates YOLOv11 for detecting and classifying red blood cell morphologies using synthetic datasets to address data scarcity and cross-dataset bias.

NanTex enables computational multiplexing and phenotyping of organelles across super-resolution modalities

NanTex enables multiplexing and phenotyping of organelles using nanotexture descriptors from single-channel super-resolution microscopy data across multiple modalities.

Autofluorescence-based Label-free Cell Counting Method in Suspension Culture with Microcarriers

This paper introduces an autofluorescence-based cell counting method for suspension cultures using microcarriers, demonstrating accurate cell number estimation without parameter tuning or fluorescence labeling.

Automated Image-Based Profiling of Pluripotent Stem Cell Colonies

ColonyQuant automates image analysis of pluripotent stem cell colonies, revealing dose-dependent morphological and functional changes in response to a KDM4 inhibitor.

Generative semantic multiplexing (SemaPlex) for accessible and scalable multiplexed fluorescence imaging

This paper introduces SemaPlex, a method that enhances multiplexed fluorescence imaging by semantically unmixing markers, enabling higher plexity and accurate cell phenotype classification.

In silico prediction of cellular organelles from computationally super-resolved (SR) phase-modulated optical micrographs

The paper develops deep neural networks to predict cellular organelles from super-resolved DIC and PCM micrographs, showing good correlation with ground truth images.

HyPhy: A Skeletonization-Based Approach For Fungal Network Analysis

HyPhy quantifies hyphal network growth and complexity from time-lapse images, enabling non-destructive analysis of fungal mycelium dynamics.

High-throughput virus quantification using cytopathic effect area analysis by deep learning

This paper develops a deep learning-based method to quantify infectious viruses using cytopathic effect area analysis, improving throughput and reducing manual bias.

SpinePy enables automated 3D spatiotemporal quantification of multicellular in vitro systems

SpinePy provides a framework for 3D spatiotemporal quantification of multicellular systems by aligning data to dynamic internal coordinate systems, revealing patterning classes influenced by gastruloid volume.

SAMCell: Generalized Label-Free Biological Cell Segmentation with Segment Anything

SAMCell automates cell segmentation in microscopy images using a modified Segment Anything Model, achieving high-quality results without requiring annotated data or technical expertise.

Prediction of cellular morphology change under perturbations with transcriptome-guided diffusion model

This paper introduces MorphDiff, a transcriptome-guided diffusion model that predicts cell morphology changes under perturbations and improves MOA identification.

Flexible and robust cell type annotation for highly multiplexed tissue images

This paper introduces RIBCA, a tool for automated cell type annotation in multiplexed tissue images, capable of annotating over 3 million cells across 40 human tissues without manual intervention.

PyCLM: programming-free, closed-loop microscopy for real-time measurement, segmentation, and optogenetic stimulation

PyCLM enables real-time measurement, segmentation, and optogenetic stimulation of cells without programming, showcasing applications in tissue dynamics and cell behavior control.

VNC-Dist: A machine learning-based semi-automated pipeline for quantification of neuronal positioning in the C. elegans ventral nerve cord

VNC-Dist quantifies neuronal positioning in C. elegans VNC using machine learning, improving efficiency and accuracy over manual methods.

Alternate dyes for image-based profiling assays

This study evaluates alternative dyes for image-based profiling assays, finding that some substitutions maintain performance while enabling live-cell imaging and expanded feature space.

Morphological cell profiling for drug repurposing against SARS-CoV-2 infection

The paper identifies host-targeting antivirals against SARS-CoV-2 using morphological profiling, finding compounds that reverse infected cell phenotypes and validate host processes hijacked by viruses.

Automated segmentation of soft X-ray tomography: native cellular structure with sub-micron resolution at high throughput for whole-cell quantitative imaging in yeast

This paper introduces an auto-segmentation pipeline for soft X-ray tomography to enable high-throughput, precise 3D morphometric analysis of yeast cells and organelles.

SynapseNet: Deep Learning for Automatic Synapse Reconstruction

SynapseNet automatically segments synapses in electron micrographs using deep learning, enabling efficient analysis of synaptic structures.

SPAGHETTI leverages massive H\&E morphological models for phase contrast microscopy images with a generative deep learning approach

SPAGHETTI translates phase contrast microscopy images into H&E-like images to improve cell segmentation and analysis using existing deep learning models.

Segmentation Matters: Recognizing the Cell Segmentation Challenge in Spatial Transcriptomics

The paper evaluates segmentation methods in spatial transcriptomics, showing that manual review is necessary due to model-specific errors.