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

The Ritz Adjoint Method for MRI Pulse Design.

IEEE transactions on medical imaging·2026
Same authorSame journal

Equivariant Filters for Efficient Tracking in 3D Imaging.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
Same author

Improved, rapid fetal-brain localization and orientation detection for auto-slice prescription.

Proceedings of the International Society for Magnetic Resonance in Medicine ... Scientific Meeting and Exhibition. International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition·2026
Same author

Fast, automated slice prescription of standard anatomical planes for fetal brain MRI.

Proceedings of the International Society for Magnetic Resonance in Medicine ... Scientific Meeting and Exhibition. International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition·2026
Same author

Evaluating reliability of automated quantitative brain morphometry from fetal T2-weighted MRI.

Frontiers in neuroscience·2026
Same author

Toward real-time alignment of 3D CT and 2D X-ray with multi-stage CNNs.

Computer assisted surgery (Abingdon, England)·2026

Related Experiment Video

Updated: Dec 19, 2025

Human Fetal Blood Flow Quantification with Magnetic Resonance Imaging and Motion Compensation
06:56

Human Fetal Blood Flow Quantification with Magnetic Resonance Imaging and Motion Compensation

Published on: January 7, 2021

2.7K

Fetal Pose Estimation in Volumetric MRI using a 3D Convolution Neural Network.

Junshen Xu1, Molin Zhang2, Esra Abaci Turk3

  • 1Department of Electrical Engineering and Computer Science, MIT, Cambridge, MA, USA.

Medical Image Computing and Computer-Assisted Intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
|June 5, 2020
PubMed
Summary

Fetal motion during magnetic resonance imaging (MRI) hinders image quality. This study uses deep learning to estimate fetal pose from MRI scans, improving diagnostic capabilities and enabling motion artifact mitigation.

Keywords:
Convolutional neural network (CNN)Deep learningFetal magnetic resonance imaging (MRI)Pose estimation

More Related Videos

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
10:44

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Published on: June 21, 2024

965
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

43.3K

Related Experiment Videos

Last Updated: Dec 19, 2025

Human Fetal Blood Flow Quantification with Magnetic Resonance Imaging and Motion Compensation
06:56

Human Fetal Blood Flow Quantification with Magnetic Resonance Imaging and Motion Compensation

Published on: January 7, 2021

2.7K
Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
10:44

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Published on: June 21, 2024

965
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

43.3K

Area of Science:

  • Medical Imaging
  • Computational Biology
  • Fetal Medicine

Background:

  • Fetal motion during magnetic resonance imaging (MRI) significantly degrades image quality and diagnostic utility.
  • Current MRI techniques are limited by unpredictable fetal movements, necessitating compromises in image resolution and contrast.

Purpose of the Study:

  • To develop and validate a deep learning-based framework for estimating fetal pose from MRI data.
  • To quantify fetal motion characteristics during MRI acquisition in the gravid abdomen.
  • To explore the potential for improving MRI acquisition and diagnostic accuracy by mitigating fetal motion artifacts.

Main Methods:

  • Utilized a repository of MRI scans of the gravid abdomen acquired at high temporal and low spatial resolution over extended durations.
  • Applied deep learning algorithms to detect key fetal landmarks and estimate fetal pose per frame within MRI volumes.
  • Evaluated the accuracy and performance of the fetal pose estimation framework.

Main Results:

  • The proposed framework achieved a quantitative average error of 4.47 mm in fetal pose estimation.
  • The system demonstrated high accuracy, with 96.4% of estimations having an error less than 10 mm.
  • Successfully enabled novel quantification of fetal movements and laid groundwork for kinematic model development.

Conclusions:

  • Deep learning-based fetal pose estimation offers a robust method for analyzing fetal motion during MRI.
  • This approach can significantly enhance the diagnostic utility of MRI in pregnancy by addressing motion-related artifacts.
  • The developed framework facilitates the creation of kinematic models for proactive mitigation of fetal motion during MRI acquisition.