Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

[Investigation of antidepressant active components and mechanisms of total triterpenoids of Wolfiporia cocos based on serum pharmacochemistry combined with network pharmacology and experimental validation].

Zhongguo Zhong yao za zhi = Zhongguo zhongyao zazhi = China journal of Chinese materia medica·2026

Same author

PAC-Net: patch adaptive cut-off network with differentiable module-wise K-learning for robust and efficient medical image segmentation.

Physics in medicine and biology·2026

Same author

Ovoid cell is an inducible small-sized morphotype that enhances proliferation and antifungal drug tolerance in the human fungal pathogen Cryptococcus neoformans.

PLoS pathogens·2026

Same author

Metagenomic profiling of biliary microbiota reveals distinct microbial and functional features in cholelithiasis and cholecystic polyps.

Medicine·2026

Same author

Seasonal and Sex Differences in Children's Body Composition Under In-Term PA Versus Vacation Non-PA Periods: A 40-Month Natural-Experiment Observation.

American journal of human biology : the official journal of the Human Biology Council·2026

Same author

Advances in Foodborne Pathogen Detection: From Conventional Confirmation to Integrated and Intelligent Platforms.

Foods (Basel, Switzerland)·2026

Same journal

Mapping brain-wide monosynaptic inputs to single neurons with ROInet-seq.

Cell reports methods·2026

Same journal

Framework for evaluating in vitro vasculogenic mimicry using structural and metabolic parameters.

Cell reports methods·2026

Same journal

A standardized and reproducible behavioral framework to elicit multiple aspects of visual spatial attention in mice.

Cell reports methods·2026

Same journal

TACTIC: A transfer learning framework to predict drug interactions in emerging pathogens.

Cell reports methods·2026

Same journal

Large-scale discovery platform enables identification of peptides targeting drug-resistant candidiasis.

Cell reports methods·2026

Same journal

A computational method to design broad-spectrum T cell-inducing vaccines applied to Betacoronaviruses.

Cell reports methods·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Oct 10, 2025

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

A deep learning-based segmentation pipeline for profiling cellular morphodynamics using multiple types of live cell

Junbong Jang^1,2,3, Chuangqi Wang^1,3, Xitong Zhang⁴

¹Department of Biomedical Engineering, Worcester Polytechnic Institute, Worcester, MA 01609, USA.

Cell Reports Methods

|December 10, 2021

Summary

This summary is machine-generated.

We developed MARS-Net, a deep learning pipeline for accurate cell edge segmentation in live-cell imaging. This method improves quantitative analysis of cellular morphodynamics across various microscopy techniques.

More Related Videos

Live Imaging Followed by Single Cell Tracking to Monitor Cell Biology and the Lineage Progression of Multiple Neural Populations

Live Imaging Followed by Single Cell Tracking to Monitor Cell Biology and the Lineage Progression of Multiple Neural Populations

Published on: December 16, 2017

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

Published on: September 28, 2019

Related Experiment Videos

Last Updated: Oct 10, 2025

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

Live Imaging Followed by Single Cell Tracking to Monitor Cell Biology and the Lineage Progression of Multiple Neural Populations

Live Imaging Followed by Single Cell Tracking to Monitor Cell Biology and the Lineage Progression of Multiple Neural Populations

Published on: December 16, 2017

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

Published on: September 28, 2019

Area of Science:

Cell Biology
Biophysics
Image Analysis

Background:

Accurate cell segmentation is crucial for quantifying cellular morphodynamics from live-cell imaging.
Conventional methods struggle with artifacts and noise in fluorescence and phase-contrast microscopy.
Challenges include phototoxicity, photobleaching, and artifacts like halo and shade-off.

Purpose of the Study:

To develop a robust deep learning pipeline for accurate cell edge localization in live-cell imaging.
To enable precise quantitative profiling of cellular morphodynamics.
To overcome limitations of existing segmentation algorithms for diverse microscopy data.

Main Methods:

Developed MARS-Net (Multiple-microscopy-type-based Accurate and Robust Segmentation Network), a deep learning pipeline.
Utilized transfer learning with a pretrained VGG19 encoder and U-Net decoder architecture.
Trained the network on diverse live-cell microscopy data (phase-contrast, spinning-disk confocal, TIRF).

Main Results:

MARS-Net achieved high accuracy in cell edge localization.
The pipeline demonstrated superior performance compared to models trained on single-microscopy-type datasets.
Enabled accurate pixel-level segmentation of complex live-cell imaging datasets.

Conclusions:

MARS-Net provides an accurate and robust solution for cell edge segmentation in live-cell imaging.
The method effectively handles challenges posed by different microscopy techniques.
MARS-Net is expected to accelerate research in cellular morphodynamics.