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

Structural studies and functional engineering of NanX: an anhydro-sialic acid transporter from Escherichia coli.

FEBS open bio·2026
Same author

Electron tomography reveals mitochondrial network and cristae remodelling during cell differentiation in the human placenta.

Nature communications·2026
Same author

MAHRP2 is required for tether formation and cytoadherence in <i>Plasmodium falciparum</i> infected red blood cells.

Frontiers in cellular and infection microbiology·2026
Same author

Exploring placental ultrastructure: A review of electron microscopy techniques and emerging methods for resolving 3D organelle architecture.

Placenta·2026
Same author

Structural basis of isethionate transport by a TRAP transporter from a sulfate-reducing bacterium.

Structure (London, England : 1993)·2025
Same author

The Human Cardiac "Age-OME": Age-Specific Changes in Myocardial Molecular Expression.

Aging cell·2025

Related Experiment Video

Updated: Aug 26, 2025

Developing 3D Organized Human Cardiac Tissue within a Microfluidic Platform
10:42

Developing 3D Organized Human Cardiac Tissue within a Microfluidic Platform

Published on: June 15, 2021

5.1K

CardioVinci: building blocks for virtual cardiac cells using deep learning.

Afshin Khadangi1, Thomas Boudier2, Eric Hanssen3

  • 1Department of Biomedical Engineering, Faculty of Engineering and Information Technology, University of Melbourne, Parkville, Australia.

Philosophical Transactions of the Royal Society of London. Series B, Biological Sciences
|October 3, 2022
PubMed
Summary

CardioVinci uses deep learning to automatically analyze 3D cardiac ultrastructures from electron microscopy data, overcoming bottlenecks in manual segmentation for faster, quantitative insights into cardiomyocyte architecture.

Keywords:
cardiac cellcell architectureelectron microscopygenerative adversarial networksthree-dimensional model

More Related Videos

Preclinical Cardiac Electrophysiology Assessment by Dual Voltage and Calcium Optical Mapping of Human Organotypic Cardiac Slices
09:35

Preclinical Cardiac Electrophysiology Assessment by Dual Voltage and Calcium Optical Mapping of Human Organotypic Cardiac Slices

Published on: June 16, 2020

10.0K
Fabrication of 3D Cardiac Microtissue Arrays using Human iPSC-Derived Cardiomyocytes, Cardiac Fibroblasts, and Endothelial Cells
10:37

Fabrication of 3D Cardiac Microtissue Arrays using Human iPSC-Derived Cardiomyocytes, Cardiac Fibroblasts, and Endothelial Cells

Published on: March 14, 2021

6.7K

Related Experiment Videos

Last Updated: Aug 26, 2025

Developing 3D Organized Human Cardiac Tissue within a Microfluidic Platform
10:42

Developing 3D Organized Human Cardiac Tissue within a Microfluidic Platform

Published on: June 15, 2021

5.1K
Preclinical Cardiac Electrophysiology Assessment by Dual Voltage and Calcium Optical Mapping of Human Organotypic Cardiac Slices
09:35

Preclinical Cardiac Electrophysiology Assessment by Dual Voltage and Calcium Optical Mapping of Human Organotypic Cardiac Slices

Published on: June 16, 2020

10.0K
Fabrication of 3D Cardiac Microtissue Arrays using Human iPSC-Derived Cardiomyocytes, Cardiac Fibroblasts, and Endothelial Cells
10:37

Fabrication of 3D Cardiac Microtissue Arrays using Human iPSC-Derived Cardiomyocytes, Cardiac Fibroblasts, and Endothelial Cells

Published on: March 14, 2021

6.7K

Area of Science:

  • Biophysics
  • Cell Biology
  • Medical Imaging

Background:

  • Electron microscopy (EM) provides detailed 3D views of cardiac ultrastructures.
  • Large EM datasets (GBs-TBs) present significant challenges for manual analysis due to low contrast and high detail.
  • Manual segmentation is time-consuming and often incomplete, hindering quantitative 3D analysis.

Purpose of the Study:

  • To develop an automated deep learning workflow, CardioVinci, for segmenting and quantifying cardiac ultrastructures.
  • To address the bottleneck in analyzing large 3D EM datasets of cardiomyocytes.
  • To enable efficient statistical analysis of cardiac cell architecture.

Main Methods:

  • Developed CardioVinci, a deep learning workflow utilizing a generative adversarial network.
  • Employed a probabilistic model of 3D cardiomyocyte architecture.
  • Minimal manual annotation required for segmentation and quantification.

Main Results:

  • CardioVinci automatically segments and quantifies mitochondria, myofibrils, and Z-discs.
  • The workflow generates new models of cardiomyocyte architecture reflecting dataset variations.
  • Enables statistical analysis of 3D cardiac ultrastructures.

Conclusions:

  • CardioVinci significantly accelerates the analysis of 3D EM data in cardiac research.
  • Automated segmentation and quantification improve the feasibility of studying cardiomyocyte architecture.
  • This approach facilitates a deeper understanding of cardiac function and disease.