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

Computed Tomography and Magnetic Resonance Imaging.

Recent results in cancer research. Fortschritte der Krebsforschung. Progres dans les recherches sur le cancer·2026
Same author

Neural network reveals platelet age from fluorescence microscopy images.

Platelets·2026
Same author

Chromatin dynamics of the Klf4 locus in mouse pluripotent cells.

Scientific reports·2026
Same author

3SD: Rotational symmetry single-shot denoising in fluorescence microscopy.

Journal of microscopy·2026
Same author

Closed-loop optogenetic control of cell biology enables outcome-driven microscopy.

Nature communications·2025
Same author

Differential roles of DNA double strand break repair pathways in response to X-ray, proton, and alpha-particle irradiation.

International journal of radiation biology·2025

Related Experiment Video

Updated: Jun 21, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K

Self-adaptive deep learning-based segmentation for universal and functional clinical and preclinical CT image

Anne-Wietje Zwijnen1, Leon Watzema2, Yanto Ridwan3

  • 1Department of Molecular Genetics, Erasmus University Medical Center, Rotterdam, the Netherlands.

Computers in Biology and Medicine
|July 16, 2024
PubMed
Summary

Deep learning automates cardiac imaging analysis for both human CT and mouse micro-CT (μCT) scans. This method accurately quantifies cardiac function, aiding heart failure research in preclinical and clinical settings.

Keywords:
Cardiac imagingComputed tomographyDeep learningHeart failureSegmentationnnU-net

More Related Videos

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.7K
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.6K

Related Experiment Videos

Last Updated: Jun 21, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.7K
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.6K

Area of Science:

  • Biomedical Imaging
  • Cardiovascular Research
  • Artificial Intelligence in Medicine

Background:

  • Non-invasive cardiac monitoring is crucial for heart failure research.
  • Manual analysis of cardiac CT and micro-CT (μCT) images is time-consuming and prone to errors.
  • Existing automated methods for clinical CT are difficult to apply to preclinical μCT data.

Purpose of the Study:

  • To develop a deep learning approach for automated quantitative data extraction from both human CT and preclinical μCT cardiac images.
  • To overcome the challenges of translating automated segmentation methods from clinical CT to μCT data.
  • To enable efficient and accurate monitoring of cardiac function in both human patients and animal models.

Main Methods:

  • Utilized a public dataset of human cardiac CT images and acquired μCT images from mice.
  • Manually segmented cardiac substructures (left ventricle, myocardium, right ventricle) in the μCT training set.
  • Employed the nnU-Net framework to train two distinct deep learning segmentation networks after template-based heart detection.

Main Results:

  • Achieved a mean Dice score of 0.925 ± 0.019 for CT segmentation, outperforming state-of-the-art algorithms.
  • Demonstrated near-identical automated and manual segmentations for the μCT training set.
  • Reported an estimated median Dice score of 0.940 for μCT test set results, comparable to existing methods.
  • Automated volume metrics closely matched manual expert observations.
  • Observed significantly decreased ejection fractions and increased myocardial volume in aging mice by 24 weeks.

Conclusions:

  • Automated data extraction using deep learning enhances the utility of (μ)CT imaging for cardiac analysis.
  • The method reduces subjectivity and workload in quantitative cardiac assessments.
  • The approach accurately measures ventricular ejection fraction and myocardial mass.
  • Enables consistent monitoring of cardiac function across human and animal studies, facilitating diastolic and systolic phase analysis.