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

Magnetic Resonance Imaging01:24

Magnetic Resonance Imaging

5.0K
Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...
5.0K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Use of Wearable Sensors in Angelman Syndrome: A Systematic Review.

Journal of intellectual disability research : JIDR·2026
Same author

TransVort: A Temporally-Coherent Physics-Guided Neural Network for Super-Resolving and Denoising 4D Flow MRI of Cerebrospinal Fluid.

IEEE transactions on bio-medical engineering·2026
Same author

2000 Peripheral Pulmonary Lesions Sampled by Shape-Sensing Robotic-Assisted Bronchoscopy and Mobile Cone-Beam Computed Tomography: The Mayo Clinic Experience.

Mayo Clinic proceedings·2026
Same author

Long-term outcomes of abnormal global longitudinal left ventricular strain during sepsis: A retrospective cohort study.

Journal of critical care·2026
Same author

Sleep in Children With Developmental Disabilities: How Can Videosomnography Inform Intervention?

Journal of pediatric health care : official publication of National Association of Pediatric Nurse Associates & Practitioners·2026
Same author

The influence of service dog partnerships on perceived and objective sleep quality for military veterans with PTSD.

Frontiers in sleep·2025

Related Experiment Video

Updated: Jun 14, 2025

Brain Slice Stimulation Using a Microfluidic Network and Standard Perfusion Chamber
27:58

Brain Slice Stimulation Using a Microfluidic Network and Standard Perfusion Chamber

Published on: October 1, 2007

10.9K

Super-Resolving and Denoising 4D flow MRI of Neurofluids Using Physics-Guided Neural Networks.

Neal M Patel1, Emily R Bartusiak2, Sean M Rothenberger1

  • 1Biomedical Engineering, Purdue University, West Lafayette, IN, USA.

Annals of Biomedical Engineering
|September 2, 2024
PubMed
Summary

A new physics-guided neural network, div-mDCSRN-Flow, enhances 4D flow MRI resolution for cerebrospinal fluid and blood flow. This method improves accuracy in visualizing flow dynamics, aiding in cerebrovascular health assessments.

Keywords:
4D flow MRICSFMachine learningPhysics-guided neural networks

More Related Videos

In vitro Assessment of Aortic Regurgitation Using Four-Dimensional Flow Magnetic Resonance Imaging
11:16

In vitro Assessment of Aortic Regurgitation Using Four-Dimensional Flow Magnetic Resonance Imaging

Published on: February 25, 2022

3.2K
Two-Dimensional Super-Resolution Visualization of Rat Brain Microvasculature Using Ultrasound Localization Microscopy
07:33

Two-Dimensional Super-Resolution Visualization of Rat Brain Microvasculature Using Ultrasound Localization Microscopy

Published on: March 28, 2025

330

Related Experiment Videos

Last Updated: Jun 14, 2025

Brain Slice Stimulation Using a Microfluidic Network and Standard Perfusion Chamber
27:58

Brain Slice Stimulation Using a Microfluidic Network and Standard Perfusion Chamber

Published on: October 1, 2007

10.9K
In vitro Assessment of Aortic Regurgitation Using Four-Dimensional Flow Magnetic Resonance Imaging
11:16

In vitro Assessment of Aortic Regurgitation Using Four-Dimensional Flow Magnetic Resonance Imaging

Published on: February 25, 2022

3.2K
Two-Dimensional Super-Resolution Visualization of Rat Brain Microvasculature Using Ultrasound Localization Microscopy
07:33

Two-Dimensional Super-Resolution Visualization of Rat Brain Microvasculature Using Ultrasound Localization Microscopy

Published on: March 28, 2025

330

Area of Science:

  • Medical Imaging
  • Computational Fluid Dynamics
  • Artificial Intelligence

Background:

  • 4D flow MRI provides crucial insights into cerebrospinal fluid (CSF) and blood flow dynamics.
  • Improving the spatial resolution and reducing noise in 4D flow MRI is essential for accurate quantitative analysis.
  • Existing methods face limitations in achieving high-resolution velocity fields for complex flow patterns.

Purpose of the Study:

  • To develop and validate a physics-guided neural network (div-mDCSRN-Flow) for super-resolution and denoising of 4D flow MRI.
  • To obtain high-resolution velocity fields of CSF and cerebral blood flow.
  • To assess the network's performance against established techniques.

Main Methods:

  • Developed the div-mDCSRN-Flow network incorporating physics-based constraints (mass conservation).
  • Trained the network on synthetic 4D flow MRI data from computational fluid dynamics simulations of CSF flow.
  • Evaluated performance using synthetic, in vitro, and in vivo 4D flow MRI data, comparing against multiple established methods.

Main Results:

  • The div-mDCSRN-Flow network significantly outperformed other methods in reconstructing high-resolution velocity fields.
  • Achieved substantial error reduction compared to trilinear interpolation for both in vitro core (22.5%) and edge (49.5%) voxels.
  • Demonstrated superior performance in both healthy and Alzheimer's disease cases.

Conclusions:

  • The div-mDCSRN-Flow approach shows generalizability for 4D flow MRI super-resolution and denoising.
  • Physics-based constraints and training on flow patches contribute to the network's robustness.
  • This method can advance MRI studies of CSF flow and its association with cerebrovascular health.