Cell Image Analysis Techniques

Odon is a fast, interactive viewer for spatial proteomics data that outperforms existing tools in loading and rendering large-scale imaging datasets.

This paper develops a shape factor analysis method to quantify spheroid and organoid morphology, showing it provides more reliable morphology assessments than standard shape descriptors.

NucleiSky registers microscopy images across scales and modalities by aligning nuclei constellations, achieving accurate localization with minimal landmarks.

Penumbria improves 3D cell segmentation in biomedical imaging by addressing challenges like diverse morphologies and optical aberrations, achieving state-of-the-art accuracy across multiple datasets.

The paper introduces Apical3DTip, a method for 3D and 4D analysis of Arabidopsis embryo initial cell morphology using elliptic cross-sections and coordinate normalization, enabling accurate geometric characterization without mesh reconstruction.

The paper uses temporal convolutional networks to classify bacterial mixture compositions from motion features in microscopy videos, achieving 93.3% accuracy without fluorescent labeling.

The paper develops an imaging and analysis framework to map human microglial activation states using handcrafted and deep learning features, showing deep learning features achieve high classification accuracy and correlate with biological states.

InVitroGap is an open-source tool for automated quantification of wound closure in scratch assays, showing strong agreement with commercial software.

V3Cell predicts organoid responses to chemical perturbations using non-invasive bright-field microscopy, creating virtual 3D cell models that mimic real organoids in structure and developmental dynamics.

This study benchmarks deep learning models for classifying dormant versus proliferative breast tumor cells using spatiotemporal data from a 3D BME system, finding EfficientNet-B7 achieves high accuracy.

This paper introduces an enhanced cell-tracking algorithm using open multi-agent systems to model and track heterogeneous cell populations in co-culture experiments, showing improved performance over existing methods.

The paper introduces an interactive spatial proteomics workflow for analyzing imaging data, enabling reproducible and customizable analysis of protein expression and localization in tissues.

BioBrain translates natural language into reproducible microscopy analysis pipelines, outperforming language models in accuracy while enabling non-experts to analyze complex imaging data.

SenoQuant is an AI software for analyzing and predicting senescence markers in tissues, offering spatial quantification across imaging modalities and supporting custom models.

Biom3d is a modular deep learning framework for 3D image segmentation that improves code sustainability and reproducibility.

MorphoStat is a pipeline that normalizes and statistically analyzes morphological data from high-content imaging, recovering known mechanism-of-action classes in a benchmark dataset.

This study uses automated dendrite tracing and categorization to show that aging and cold shock cause distinct dendritic beading patterns driven by branching history and systemic effects, respectively.

PhenoBIC is a deep learning model that automates cell phenotyping in multiplex imaging data, outperforming manual methods and other ML approaches with an F1-score of ~0.88.

Orion, an AI agent, automates biomedical image analysis by integrating large language models with software execution and reasoning, generating research reports and hypotheses from imaging data.

This study evaluates how preprocessing techniques affect classification consistency in high-content assays, finding that non-repeatability is inherent and irreducible.

SCALLOPS improves processing of optical pooled screens by enabling efficient alignment and analysis of large-scale image data, demonstrating superior performance over existing methods.

CASC reduces microscopy image file sizes by removing spatial redundancy while preserving object-level biological structures.

The paper introduces a computational framework to extract mechanistic hypotheses from morphological dynamics data by analyzing correlations and gene perturbations in C. elegans embryos.

PixelDeck organizes and manages large biomedical image and video libraries with duplicate detection and metadata extraction, enabling efficient curation and preparation for downstream analysis.

This paper introduces STERN, a framework that quantitatively compares developmental trajectories across embryos by learning spatiotemporal representations from 4D imaging data.

ConnectoFM is a foundation model for connectomics that outperforms existing methods in low-data regimes and improves accuracy for critical biological structures.

Cytomove provides a browser-based tool for quantifying scratch wound healing assays with reviewable segmentation and export of analysis results.

FLAG-X provides a Python package with hybrid workflows for automated flow cytometry gating, integrating manual and machine learning methods to improve consistency and efficiency in clinical settings.

The paper introduces a method to analyze organelle spatial organization in branched cells, finding distinct spatial programs in microglia under different conditions.