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

Multifocal Pixel/Photon-Reassignment FLIM (MPPR-FLIM): A Super-Resolution Analytical Tool for Characterizing Subcellular Fluorescence Lifetime Heterogeneity via TCSPC.

Analytical chemistry·2026
Same author

In Vivo Hyperspectral CARS Imaging Reveals Photobiomodulation-Driven Remodeling of Fatty Acid Homeostasis in an AD Mouse Model.

Analytical chemistry·2026
Same author

Comparison of Point Spread Function Encoding EPI DWI and Turbo Gradient Spin Echo BLADE DWI for Imaging Intracranial Tumors.

Academic radiology·2026
Same author

Ice-phase optothermal tweezers.

Nature communications·2026
Same author

FLIM Reveals Red Light-Induced Changes in Murine Hair Follicles.

Biosensors·2026
Same author

Simultaneous dual-Raman-shift scanning-free stimulated Raman scattering microscopy for label-free biomolecular imaging.

Nature communications·2026

Related Experiment Video

Updated: May 31, 2026

Generation of Self-assembled Vascularized Human Skin Equivalents
09:04

Generation of Self-assembled Vascularized Human Skin Equivalents

Published on: February 12, 2021

Rapid Generation of Subject-Specific Human Models With Detailed Tissue Structures for Timely Individualized SAR

Jiaqi Hu1,2, Jiamin Liang2, Fangyong Sun2

  • 1College of Physics and Optoelectronic Engineering, Shenzhen University, Shenzhen, China.

Magnetic Resonance in Medicine
|May 29, 2026
PubMed
Summary

This study presents a fast method for creating patient-specific anatomical models using MRI and 3D scanning. These models enable accurate prediction of specific absorption rate (SAR) during MRI scans.

Keywords:
anatomy modeldeep learningpatient‐specific SARtorso‐local SAR

More Related Videos

Creation of Patient-Specific Silicone Cardiac Models with Applications in Pre-surgical Plans and Hands-on Training
09:15

Creation of Patient-Specific Silicone Cardiac Models with Applications in Pre-surgical Plans and Hands-on Training

Published on: February 10, 2022

Scaled Anatomical Model Creation of Biomedical Tomographic Imaging Data and Associated Labels for Subsequent Sub-surface Laser Engraving (SSLE) of Glass Crystals
07:57

Scaled Anatomical Model Creation of Biomedical Tomographic Imaging Data and Associated Labels for Subsequent Sub-surface Laser Engraving (SSLE) of Glass Crystals

Published on: April 25, 2017

Related Experiment Videos

Last Updated: May 31, 2026

Generation of Self-assembled Vascularized Human Skin Equivalents
09:04

Generation of Self-assembled Vascularized Human Skin Equivalents

Published on: February 12, 2021

Creation of Patient-Specific Silicone Cardiac Models with Applications in Pre-surgical Plans and Hands-on Training
09:15

Creation of Patient-Specific Silicone Cardiac Models with Applications in Pre-surgical Plans and Hands-on Training

Published on: February 10, 2022

Scaled Anatomical Model Creation of Biomedical Tomographic Imaging Data and Associated Labels for Subsequent Sub-surface Laser Engraving (SSLE) of Glass Crystals
07:57

Scaled Anatomical Model Creation of Biomedical Tomographic Imaging Data and Associated Labels for Subsequent Sub-surface Laser Engraving (SSLE) of Glass Crystals

Published on: April 25, 2017

Area of Science:

  • Biomedical Engineering
  • Medical Imaging
  • Computational Anatomy

Background:

  • Accurate patient-specific modeling is crucial for predicting radiofrequency-induced heating in Magnetic Resonance Imaging (MRI).
  • Current methods for generating anatomical models are often time-consuming, limiting their clinical applicability for real-time monitoring.

Purpose of the Study:

  • To develop a rapid, automated framework for generating subject-specific whole-body anatomical models.
  • To enable patient-specific prediction of torso-local specific absorption rate (SAR) in clinical MRI settings.

Main Methods:

  • A hybrid approach combining ultrafast 3D gradient-echo MRI and 3D depth camera scanning was employed.
  • Deep learning models with semi-supervised strategies were used for automatic segmentation of major tissue types from MRI data.
  • Full-body geometry was reconstructed from depth data and fused with MRI-derived segmentation for seamless model generation.

Main Results:

  • Subject-specific human models were generated in approximately 20 seconds, including data acquisition and processing.
  • The models demonstrated accurate tissue segmentation and robust external body reconstruction.
  • Validation showed low errors in specific absorption rate (SAR) prediction (<2% peak SAR10g error) and accurate B1+ field mapping (9.50% NRMSE).

Conclusions:

  • The integrated framework enables rapid and accurate construction of subject-specific human models.
  • This technology supports practical, online SAR monitoring in clinical MRI environments.
  • The developed models are suitable for electromagnetic simulations and personalized safety assessments in MRI.