Cell Image Analysis Techniques

Cecelia provides a user-friendly image analysis toolbox for processing and analyzing microscopy data to study spatial cellular interactions and behavior.

LivecellX corrects segmentation and tracking errors in live-cell imaging using deep learning and provides tools for lineage reconstruction and dynamic analysis.

The paper introduces a method to separate signal and noise in flow cytometry data to improve genome copy number estimation in E. coli.

The paper introduces an AI model to analyze mitochondrial morphology in TNBC using TEM images, finding significant structural changes in response to chemotherapy and metastasis.

DMC-BrainMap is an open-source tool for analyzing anatomical data across species, enabling streamlined processing, registration, segmentation, and visualization of brain data without programming expertise.

EASI-ORC automates smFISH image analysis in yeast to measure RNA-organelle colocalization, offering a fast, accurate, and user-friendly solution.

This paper validates Cellpose as a reliable method for segmenting single cells in autofluorescence microscopy images, showing high accuracy compared to manual segmentation.

The paper introduces DeepCellMap, a deep learning tool for analyzing spatial cellular organization in developing brains, revealing microglial phenotypes and spatial clustering patterns.

PoreVision develops a Python-based software tool to streamline and standardize pore characterization in porous materials, improving efficiency and accuracy in tissue engineering research.

This paper introduces UNITO, a deep learning framework for automated cytometric gating that matches human performance and provides interpretable results without requiring manual input.

Cellpose3 improves cellular segmentation in noisy, blurry, or undersampled microscopy images through one-click image restoration tools.

micro_sam finetunes Segment Anything into a light microscopy generalist and a cell/neurite-focused electron microscopy model, plus napari tools for interactive 2d, volumetric and tracking annotation.

This study reanalyzes image datasets to emphasize robust experimental design and effect sizes over statistical significance, providing open-access code to improve reproducibility.

MicroSplit uses deep learning to computationally unmix fluorescent microscopy data, enabling faster imaging and reduced photon exposure by separating multiple cellular structures from a single channel.

This study uses self-supervised learning to improve image representation for Cell Painting, outperforming traditional tools in classification tasks and reducing computational costs.

DeepKymoTracker constructs accurate cell lineage trees for highly motile cells by combining tracking and segmentation with 3D CNNs, outperforming existing tools in benchmark tests.

Polarity-JaM is an open-source image analysis tool for quantifying cell polarity, junctions, and morphology using deep learning and provides statistical analysis features.

SynSeg generates synthetic datasets to train a U-net model for subcellular segmentation, outperforming traditional methods in vesicle and cytoskeletal filament detection.

This paper introduces WormAI, an AI framework with three models for nematode phenotyping, improving efficiency and accuracy in analysis.

The paper develops a semi-automated Python tool to quantify axonal beading in time-lapse microscopy images, showing strong agreement with manual analysis.

This paper introduces a method to apply Cell Painting to 3D spheroids for morphological profiling, detecting phenotypic changes in colorectal cancer cells under compound treatments.

This paper uses machine learning on microscopy images to predict microbial community taxonomic diversity and dominant bacterial classes, achieving high accuracy and low error.

This study introduces an automated pipeline for detecting and quantifying ecDNA in FISH images to analyze drug response mechanisms in cancer cells.

This paper curates a corpus of whole-cell imaging studies, identifies trends and variability in research practices, and calls for standardization in the field.

OoCount provides an automated method for counting and classifying oocytes in 3D fluorescent microscopy images of mouse ovaries using machine learning.

The paper develops an open-source image analysis tool to quantify CRM fluorescence in limb development, testing four methods for standardized quantification.

Bell Jar is a semi-automated tool for registering brain tissue to a reference atlas and counting cells, showing reliability comparable to manual methods and better accuracy with less user input.

The paper introduces M-VEST, a method for extracting structural features from high-resolution imaging data, and applies it to study Aurora kinase A in mitotic cells.

The paper develops ML models for segmenting and classifying cyanobacterial cells, showing improved performance over traditional methods in dense colonies and artifact resistance.

This paper develops a deep learning model for virtual staining of plant cells using bright-field microscopy, demonstrating its utility in morphometry and classification of cell states.