Cell Image Analysis Techniques

FlowGateNIST automates bacterial flow cytometry data analysis by gating cells, distinguishing singlets from multiplets, and calibrating fluorescence signals.

easyXpress is an R package for analyzing and visualizing high-throughput C. elegans microscopy data from CellProfiler, offering customizable filtering and interactive visualization tools.

QuantifyPolarity is a tool for measuring planar polarized protein distributions and cell properties, showing robustness to cell geometry variations.

CelltrackR provides an R package for analyzing immune cell migration data with tools for data management, quality control, migration statistics, clustering, and simulation.

The paper develops a method to analyze PVD neuron dendritic architecture in C. elegans, revealing symmetrical three-way-junctions and morphological changes due to git-1 mutations.

This paper evaluates AxonDeepSeg's performance in automated axon histomorphometry on light micrographs of rat peripheral nerves, finding it robust and faster than manual analysis.

This paper introduces a fully unsupervised deep learning method to cluster cellular images by Mode-of-Action using only pixel intensity values, achieving high accuracy on a labeled dataset.

The paper introduces LocalZProjector and DeProj, tools for accurate 2D projection and morphometric analysis of 3D microscopy images, showing they handle complex data and correct projection distortions.

COUNTEN is an AI tool that rapidly and objectively enumerates and classifies enteric neurons in murine ileal plexus tissue, improving upon manual methods by reducing time and bias.

This paper presents a machine learning approach for cell classification in glioma tissue and identifies cell niches using graph neural networks.

The paper applies Cellpose and a new ImageJ plugin to automatically and accurately segment myofibers in murine skeletal muscle, enabling unbiased quantification across different staining and fixation conditions.

The paper introduces a deep learning algorithm for automated 3D detection of neuronal somata in whole mouse brain images, demonstrating its effectiveness on fluorescently labeled cell populations.

The paper introduces a cell tracking method using B-spline active contours to extract neuronal activity signals from moving contractile tissues, improving signal extraction in dynamic and overlapping cellular environments.

Segmentor is a tool for manual refinement of 3D microscopy annotations, improving efficiency without sacrificing accuracy.

WaveletSEG provides a robust, automatic 3D nuclei segmentation method for multicellular embryo analysis without preprocessing, achieving high accuracy in noisy data.

The paper provides high-quality fluorescence microscopy datasets for training deep neural networks to improve image quality and reduce photobleaching and phototoxicity.

The paper introduces SMorph, a tool for automated morphometric analysis of nervous system cells, revealing structural remodeling in hippocampal astrocytes after chronic antidepressant treatment.

This study quantifies 4D nuclear morphology changes in human astrocytes treated with valproic acid, showing significant size and shape differences by day 7.

Cheetah is a computational toolkit that integrates real-time microscopy analysis with cellular control algorithms, demonstrating improved segmentation accuracy over thresholding methods in bacterial and mammalian cells.

CeLaVi is a web-based tool for visualizing and interacting with cell lineages, integrating spatial distribution and cell properties.

ZeroCostDL4Mic provides a platform to use deep learning in microscopy, enabling tasks like segmentation and denoising through Google Colab.

SplineDist improves cell segmentation by using spline curves instead of star-convex polygons, achieving comparable quality with a smaller network and better handling of complex shapes.

This paper introduces an unsupervised method for tracing neurons in multispectral Brainbow images, achieving more accurate results than existing methods by reducing segmentation and continuity errors.

This paper introduces an automated cell tracking pipeline, Oligo-Track, to analyze oligodendrocyte dynamics in vivo, revealing suppressed oligodendrogenesis in deeper cortical layers after demyelination.

SNT provides a unified framework for neuronal morphometry and single-cell connectomics analysis, integrating with Fiji and ImageJ to support tracing, quantification, and modeling of neuroanatomy.

The paper develops a deep-learning-based pipeline for segmenting and tracking cells in 3D brain imaging data, achieving high accuracy across different conditions and datasets.

AIDeveloper is an open-source software for training neural networks in image classification, demonstrated on biological datasets with comparable results to conventional methods.

This study compares convolutional and capsule neural networks for classifying microfluidic images of dividing yeast cells, finding convolutional networks more accurate overall while capsule networks excel at specific categories.

YeastNet improves yeast cell segmentation in bright-field microscopy using a U-Net model, outperforming existing tools and providing a Python package for automated analysis.

This paper introduces a fuzzy-registration algorithm for tracking cell divisions in time-lapse fluorescence microscopy, validated on Arabidopsis root mitotic events.