Cell Image Analysis Techniques

Cellpose as a reliable method for single-cell segmentation of autofluorescence microscopy images

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

Unraveling Microglial Spatial Organization in the Developing Human Brain with DeepCellMap, a Deep Learning Approach Coupled to Spatial Statistics

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

PoreVision: A Program for Enhancing Efficiency and Accuracy in SEM Pore Analyses

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

Automated Cytometric Gating with Human-Level Performance Using Bivariate Segmentation

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: one-click image restoration for improved cellular segmentation

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

Segment Anything for Microscopy

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.

A Statistical Framework for Robust and Reproducible BioImage Analysis

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

MicroSplit: Semantic Unmixing of Fluorescent Microscopy Data

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.

Self-supervision advances morphological profiling by unlocking powerful image representations

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

DeepKymoTracker: A tool for accurate construction of cell lineage trees for highly motile cells

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: An image analysis toolbox for cell polarity, junction and morphology quantification

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: Generating Synthetic Datasets for Accurate Subcellular Segmentation with U-net

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

WormAI: Artificial Intelligence Networks for Nematode Phenotyping

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

Semi-automated analysis of beading in degenerating axons

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

High-content morphological profiling by Cell Painting in 3D spheroids.

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.

Predicting characterization of microbiome taxonomy from imaging using machine learning approaches

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

Leveraging AI to Automate Detection and Quantification of Extrachromosomal DNA (ecDNA) to Decode Drug Responses

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

A scoping study of the whole-cell imaging literature: a foundational corpus, potential for data-mining and research synthesis, and a call for standardization of an emerging field

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: A machine-learning based approach to mouse ovarian follicle counting and classification

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

An Open-Source Image Analysis Method for Quantifying Reporter Fluorescence

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

Bell Jar: A Semi-Automated Registration and Cell Counting Tool for Mouse Neurohistology Analysis

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.

Comparative Extraction of Cellular Features from High-Resolution Volume Imaging

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.

Machine Learning Models for Segmentation and Classification of Cyanobacterial Cells

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

Virtual staining from bright-field microscopy for label-free quantitative analysis of plant cell structures

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.

Spherical harmonics texture extraction for versatile analysis of biological objects

This paper introduces a method to quantify intensity distribution in 3D and 2D microscopy data using spherical harmonics, demonstrating its application across various biological systems.

A genome-wide atlas of human cell morphology

The paper presents a genome-wide perturbation atlas using CRISPR-Cas9 knockouts to link genes to cellular phenotypes, identifying TMEM251/LYSET as a Golgi-resident protein involved in lysosomal enzyme trafficking.

The Batch-Resourcing Angiogenesis Tool (BRAT) to enable high-content microscopy screening of microvascular networks.

BRAT is a tool for high-content microscopy screening of microvascular networks, offering fast and accurate analysis of vascular images.

Inferring single-cell dynamics of a molecular reporter from unlabeled live-cell light microscopy data analyzed with delay embedding

The paper uses delay embedding and VAE features to predict single-cell dynamics of a molecular reporter from unlabeled live-cell imaging data.

Deep learning-driven morphology analysis enables label-free classification of therapeutic agent- naive versus resistant cancer cells

This study uses deep learning to classify drug-naive and resistant cancer cells based on morphology, achieving high accuracy across multiple cancer types and drug classes.

Automatic detection of fluorescently labeled synapses in volumetric in vivo imaging data

The paper develops a convolutional neural network to detect and segment fluorescently labeled synapses in vivo, enabling large-scale analysis of synapses in living mice.