Cell Image Analysis Techniques

This paper introduces IMPA, a generative model that predicts cell morphological responses to chemical and genetic perturbations using untreated cell images as input, showing improved performance on structurally related compounds.

The paper introduces MitoProfilerHC and an open-source version of MitoProfiler to quantify mitochondrial morphology in cells using high-content analysis and napari.

NanoPyx improves bioimage analysis speed using adaptive machine learning to optimize algorithm selection and execution.

This paper develops a method to track microfluidic droplets over time using optimal transport and contrastive learning, achieving high accuracy in tracking without labeled data.

This paper introduces a deep learning pipeline for automated morphological and viability assessment of 3D cancer cell spheroids, achieving high accuracy in segmentation and cell viability estimation.

This paper develops DeMemSeg, a deep learning tool for segmenting overlapping prospore membranes in yeast from 2D MIP images, achieving performance comparable to manual annotation.

CellBinDB provides a large-scale multimodal annotated dataset for cell segmentation and benchmarks seven state-of-the-art methods.

Gossamer improves neuronal reconstruction by enabling whole-brain processing with reduced memory usage and higher automated yield compared to existing methods.

This paper develops a high-throughput, objective method to quantify 3D spheroid invasion using image analysis, providing directionally-dependent metrics and code in MATLAB and Python.

The paper develops a convolutional neural network to quantify nuclear localisation of fluorescently tagged proteins in yeast, outperforming existing methods in single-cell time series analysis.

The paper introduces PhaseMetrics, an image analysis pipeline for quantifying biomolecular condensates in vitro and in cells, showing its accuracy across different experimental systems.

ThirdPeak analyzes 2D and 3D single-molecule tracking data, revealing insights from combined 2D and 3D analysis of live-cell diffusion.

This study uses deep learning to segment cytoskeleton structures in plant cells, improving density measurements compared to traditional methods.

The paper introduces a spatial autocorrelation method based on Local Moran's I to segment images without thresholds, showing improved performance in noisy conditions by identifying potassium channel clusters in the thalamus.

This paper predicts single-cell phenotypes from nuclear morphology using pre-labeled microscopy data, achieving high accuracy for some phenotypes but facing generalizability challenges.

This paper introduces a graph theory-based single-cell tracking method to identify clustering behavior in PC3 cells, finding that co-cultured cells form persistent clusters while monocultured cells do not.

The paper describes an open-source protocol for automated high-content multiplex fluorescence in situ transcriptomics analysis using Fiji macros and a Python app for data summarization.

The paper presents a CNN-based model for identifying single neurons in iPSC-derived cultures with high accuracy, and demonstrates its applicability to other cell types.

SpatialQPFs provides an R package for extracting interpretable spatial features from cell imaging data using spatial statistical methods, enabling comprehensive spatial analyses across diverse contexts.

SPACe is an open-source tool for analyzing Cell Painting data, offering faster processing and better handling of cell-to-cell variation compared to existing software.

CelloType is a multi-task learning model for cell segmentation and classification in tissue images, improving accuracy over existing methods.

This study uses explainable AI to analyze live-cell imaging data and identify behavioral changes in TCR T cells with specific genetic knockouts.

ScaleFExSM is a scalable pipeline for extracting interpretable features from high-content imaging data, improving drug response analysis and disease profiling.

The paper quantifies variability in manual and automated cell segmentation and tracking methods, showing their impact on phenotypic metrics and reproducibility.

This paper introduces an immunofluorescence-based method for high-precision cell cycle identification at the single-cell level, offering an alternative to flow cytometry for analyzing cell cycle stages.

The paper presents an image analysis pipeline to quantify structural variations in uterine glands across species, revealing shape changes during embryo implantation.

BIFROST registers diverse Drosophila brain imaging datasets into a common anatomical space, enabling cross-experiment and cross-modality comparisons with sub-10 micron precision.

EasyFlow provides an open-source, user-friendly flow cytometry analysis tool with a GUI, accessible without coding knowledge and supporting both Matlab and Python.

The paper introduces CytoSummaryNet, a contrastive learning method for aggregating single-cell features in image-based profiling, improving mechanism of action prediction by 30-68%.

The paper introduces the Brain Image Library (BIL), a centralized resource for brain microscopy data that enables exploration, visualization, and analysis without data download.