Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

Evidence of off-target probe binding affecting 10x Genomics Xenium gene panels compromise accuracy of spatial transcriptomic profiling.

eLife·2026
Same author

Deep-learning-enabled morphodynamic analysis of drug responses in a biomimetic fibrin-based 3D glioblastoma invasion model.

bioRxiv : the preprint server for biology·2026
Same author

Spatial Transcriptomics As Rasterized Image Tensors (STARIT) characterizes cell states with subcellular molecular heterogeneity.

bioRxiv : the preprint server for biology·2026
Same author

Impact of Data Quality on Deep Learning Prediction of Spatial Transcriptomics from Histology Images.

bioRxiv : the preprint server for biology·2025
Same author

Combined application of deep learning and conventional computer vision for kidney ultrasound image classification in chronic kidney disease: preliminary study.

Ultrasonography (Seoul, Korea)·2025
Same author

Spatial mutual nearest neighbors for spatial transcriptomics data.

Bioinformatics (Oxford, England)·2025
Same journal

Computational protocol for modeling supported nanoparticle catalysts with strong metal-support interactions.

STAR protocols·2026
Same journal

Protocol for genomic mapping of chromatin targets using high-throughput CUT&RUN.

STAR protocols·2026
Same journal

A protocol for noninvasive quantification of dietary fat absorption in mice.

STAR protocols·2026
Same journal

Protocol for an AlCl<sub>3</sub>-induced Alzheimer's model in zebrafish larvae with optimized pH and behavioral assessment.

STAR protocols·2026
Same journal

Protocol for live cell barcoding and immunophenotyping of human hematological malignancies using cytometry by time of flight.

STAR protocols·2026
Same journal

Generating drug resistance models in human and murine cancer cell lines and assessing cross-resistance to chemotherapeutics and KRAS inhibitors.

STAR protocols·2026
See all related articles

Related Experiment Video

Updated: Sep 7, 2025

Co-culture of Glioblastoma Stem-like Cells on Patterned Neurons to Study Migration and Cellular Interactions
10:08

Co-culture of Glioblastoma Stem-like Cells on Patterned Neurons to Study Migration and Cellular Interactions

Published on: February 24, 2021

6.1K

Protocol for live cell image segmentation to profile cellular morphodynamics using MARS-Net.

Junbong Jang1, Caleb Hallinan1, Kwonmoo Lee2

  • 1Vascular Biology Program, Boston Children's Hospital, Boston, MA 02115, USA.

STAR Protocols
|June 23, 2022
PubMed
Summary
This summary is machine-generated.

This study introduces MARS-Net, a deep learning model for precise cell edge localization in live cell imaging. MARS-Net improves quantitative analysis of cellular morphodynamics, overcoming limitations of traditional imaging techniques.

Keywords:
BioinformaticsCell BiologyComputer sciencesMicroscopy

More Related Videos

Mapping the Emergent Spatial Organization of Mammalian Cells using Micropatterns and Quantitative Imaging
09:56

Mapping the Emergent Spatial Organization of Mammalian Cells using Micropatterns and Quantitative Imaging

Published on: April 30, 2019

6.7K
Quantitative Approaches for Studying Cellular Structures and Organelle Morphology in Caenorhabditis elegans
08:47

Quantitative Approaches for Studying Cellular Structures and Organelle Morphology in Caenorhabditis elegans

Published on: July 5, 2019

9.8K

Related Experiment Videos

Last Updated: Sep 7, 2025

Co-culture of Glioblastoma Stem-like Cells on Patterned Neurons to Study Migration and Cellular Interactions
10:08

Co-culture of Glioblastoma Stem-like Cells on Patterned Neurons to Study Migration and Cellular Interactions

Published on: February 24, 2021

6.1K
Mapping the Emergent Spatial Organization of Mammalian Cells using Micropatterns and Quantitative Imaging
09:56

Mapping the Emergent Spatial Organization of Mammalian Cells using Micropatterns and Quantitative Imaging

Published on: April 30, 2019

6.7K
Quantitative Approaches for Studying Cellular Structures and Organelle Morphology in Caenorhabditis elegans
08:47

Quantitative Approaches for Studying Cellular Structures and Organelle Morphology in Caenorhabditis elegans

Published on: July 5, 2019

9.8K

Area of Science:

  • Cell Biology
  • Bioimaging
  • Computational Biology

Background:

  • Accurate cell segmentation is crucial for quantitative studies of cellular morphodynamics in live cell imaging.
  • Fluorescence and phase contrast microscopy present challenges for precise cell edge localization, impacting data accuracy.

Purpose of the Study:

  • To develop and present a protocol for MARS-Net, a deep learning model designed for accurate cell edge localization.
  • To enable robust quantitative profiling of cellular morphodynamics using improved image analysis.

Main Methods:

  • MARS-Net integrates an ImageNet-pretrained VGG19 encoder with a U-Net decoder.
  • The model was trained on diverse microscopy image datasets, including fluorescence and phase contrast images.
  • The protocol details installation, image labeling, model training, performance evaluation, and quantitative profiling.

Main Results:

  • MARS-Net demonstrates effective cell edge localization, addressing limitations of conventional imaging methods.
  • The developed protocol facilitates the application of MARS-Net for detailed cellular morphodynamics analysis.
  • Successful training and evaluation on multiple microscopy image types were achieved.

Conclusions:

  • MARS-Net provides a powerful deep learning solution for accurate cell segmentation and edge localization in live cell imaging.
  • This protocol enables researchers to leverage MARS-Net for enhanced quantitative analysis of cellular morphodynamics.
  • The model's versatility across different microscopy image types makes it a valuable tool for cell biology research.