Cell Image Analysis Techniques

SwinCell: a transformer-based framework for dense 3D cellular segmentation

SwinCell is a 3D transformer-based framework that improves segmentation of dense cellular images by balancing local feature recognition and contextual understanding.

Structural Repetition Detector: multi-scale quantitative mapping of molecular complexes through microscopy

The paper introduces SReD, an unsupervised framework for detecting repetitive biological structures in microscopy images, demonstrating its use on three datasets.

Representation Learning Methods for Single-Cell Microscopy are Confounded by Background Cells

This paper evaluates how background cells affect single-cell microscopy models and finds they reduce localization classification accuracy by up to 15.8%.

TransiScope: An Interactive Open-Source Platform for Automated Detection and Analysis of Transient Events in Time-Lapse Microscopy

TransiScope automates and improves the analysis of transient events in time-lapse microscopy by optimizing parameters interactively, enhancing objectivity and reducing false positives.

Corelative light and electron microscopy (CLEM) image registration by blood vessel axes alignment

This paper introduces a method for aligning blood vessel axes in CLEM images to improve registration accuracy.

Accurate Prediction of ecDNA in Interphase Cancer Cells using Deep Neural Networks

The paper introduces interSeg, a deep learning tool that accurately predicts oncogene amplification status from interphase FISH images, achieving high accuracy in detecting ecDNA and chromosomal amplifications.

Deep learning identifies heterogeneous subpopulations in breast cancer cell lines

This study uses deep learning to classify transcriptomic subpopulations in breast cancer cell lines based on morphology, showing that chemotherapy-induced changes and intra-line subpopulations are identifiable.

EZ-FRCNN: A Fast, Accessible and Robust Deep Learning Package for Object Detection Applications from Ethology to Cell Biology

EZ-FRCNN provides a user-friendly, offline deep learning tool for object detection in biological datasets, enabling applications from cell biology to ecological studies.

CloVarS: a simulation of single-cell clonal variability

CloVarS generates synthetic single-cell lineage data to model time-lapse microscopy experiments and test biological hypotheses.

EyeHex toolbox for complete segmentation of ommatidia in fruit fly eyes

EyeHex automates segmentation of Drosophila compound eyes from images, providing accurate metrics on ommatidia structure across different strains and image types.

PB-scope: Contrastive learning of dynamic processing body formation reveals undefined mechanisms of approved compounds

PB-scope uses deep learning to analyze PB dynamics and identifies drugs affecting JAK signaling pathway.

Segment AnyNeuron

Segment AnyNeuron is an active learning framework for neuron segmentation using minimal annotations, achieving high precision on diverse neuron imaging datasets.

Connectivity Is All You Need: Inferring Neuronal Types with NTAC

NTAC infers neuronal cell types from synaptic connectivity, achieving high accuracy with minimal labeled data and outperforming morphology-based methods.

Spotiflow: accurate and efficient spot detection for fluorescence microscopy with deep stereographic flow regression

Spotiflow improves spot detection in microscopy images using deep learning, achieving subpixel accuracy and efficiency across diverse datasets.

Cut-Detector: A Tool for Automated Temporal Analysis of Late Cytokinetic Events

Cut-Detector automates the analysis of cytokinesis timing from time-lapse microscopy movies by detecting microtubule cuts in intercellular bridges.

A Self-Supervised Foundation Model for Robust and Generalizable Representation Learning in STED Microscopy

This paper introduces STED-FM, a foundation model for STED microscopy that learns robust representations without extensive annotations, improving downstream tasks like classification, segmentation, and image denoising.

Estimating full-field displacement in biological images using deep learning

This paper introduces DEFORM-Net, a deep learning method for estimating full-field displacement in biological images, outperforming traditional and recent approaches in accuracy, speed, and spatial sampling.

Live-cell analyses with unsegmented images to study cancer cell response to modified T cell therapy

This paper introduces a segmentation-free method to analyze live-cell imaging data of T cell-cancer cell interactions, revealing how T cell modifications affect aggregate formation dynamics.

Kaizen: Decomposing cellular images with VQ-VAE

Kaizen improves cell segmentation in microscopy images by using a VQ-VAE to iteratively refine object hypotheses.

Encoding Cell Phenotype from Label-Free Imaging Flow Cytometry with Unsupervised Deep Learning

This study uses a Variational Auto-Encoder to predict microalgal lipid content from label-free Imaging Flow Cytometry data, demonstrating a low-cost alternative to traditional methods.

Automated registration of spatial expression data scales multimodal integration to large cohorts

The paper introduces a Bayesian optimization framework for automated registration of spatial expression data across modalities, achieving higher success rates on a large dataset of 954 image pairs.

OmniSegger: A time-lapse image analysis pipeline for bacterial cells

OmniSegger is an updated image analysis pipeline for bacterial cells that improves robustness to cell morphology and supports multiple imaging modalities, providing quantitative cellular analyses.

A Benchmark for Virus Infection Reporter Virtual Staining in Fluorescence and Brightfield Microscopy

The paper introduces a benchmark and datasets for virus infection reporter virtual staining in microscopy, using U-Net and pix2pix models to address the challenge of continuous signal generation.

CRISP: Correlation-Refined Image Segmentation Process

CRISP improves cell segmentation accuracy in dense calcium imaging data by refining user-drawn masks and automatically identifying cell outlines.

Cell Painting in activated cells illuminates phenotypic dark space and uncovers novel drug mechanisms of action.

The paper uses Cell Painting to identify phenotypic effects of compounds in activated cells, revealing novel drug mechanisms and expanding phenotypic understanding.

Cell-TRACTR: A transformer-based model for end-to-end segmentation and tracking of cells

Cell-TRACTR is a transformer-based model that segments and tracks cells in microscopy images, outperforming existing methods in tracking and division accuracy.

Contrastive Representation Learning for Single Cell Phenotyping in Whole Slide Imaging of Enrichment-free Liquid Biopsy

This paper introduces a contrastive learning framework for single-cell phenotyping in whole slide imaging of liquid biopsy samples, achieving high accuracy and enabling automated identification of rare cell phenotypes.

A Self-Supervised Learning Approach for High Throughput and High Content Cell Segmentation

This paper introduces a self-supervised learning method for cell segmentation that outperforms Cellpose in accuracy and reduces reliance on labeled data and computational expertise.

Non-destructive, high-resolution T cell characterization and subtyping via deep-ultraviolet microscopy

This paper introduces deep-ultraviolet microscopy for non-destructive T cell characterization and subtyping, showing high accuracy in viability, activation state, and subtype classification.

MorphoCellSorter: An Andrews plot-based sorting approach to rank microglia according to their morphological features

MorphoCellSorter ranks microglia by morphology using Andrews plots and PCA, showing it works across species, ages, and experimental models.