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

7.3K
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...
7.3K

You might also read

Related Articles

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

Sort by
Same authorSame journal

Accelerating Stroke MRI With Diffusion Probabilistic Models Through Large-Scale Pre-Training and Target-Specific Fine-Tuning.

Magnetic resonance in medicine·2026
Same author

Fast and Robust Diffusion Posterior Sampling for MR Image Reconstruction Using the Preconditioned Unadjusted Langevin Algorithm.

Magnetic resonance in medicine·2026
Same author

Robust multi-coil MRI reconstruction via self-supervised denoising.

Magnetic resonance in medicine·2025
Same author

A critical assessment of artificial intelligence in magnetic resonance imaging of cancer.

Npj imaging·2025
Same author

MRI acquisition and reconstruction cookbook: recipes for reproducibility, served with real-world flavour.

Magma (New York, N.Y.)·2025
Same author

Review of encephalocraniocutaneous lipomatosis.

Seminars in pediatric neurology·2024

Related Experiment Video

Updated: Sep 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

2.5K

Diffusion probabilistic generative models for accelerated, in-NICU permanent magnet neonatal MRI.

Yamin Arefeen1,2, Brett Levac1, Bhairav Patel3

  • 1Chandra Family Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, Texas, USA.

Magnetic Resonance in Medicine
|June 18, 2025
PubMed
Summary
This summary is machine-generated.

Accelerating neonatal MRI in the NICU using diffusion probabilistic generative models significantly reduces scan times. This method improves image reconstruction for sick infants, aiding early brain abnormality assessment.

Keywords:
clinical validationdiffusion modelsgenerative modelsin‐NICU MRI

More Related Videos

Early Pathological and Magnetic Resonance Detection of Cerebral Injury Using a Rat Model of Neonatal Hypoxic Ischemic Encephalopathy
05:52

Early Pathological and Magnetic Resonance Detection of Cerebral Injury Using a Rat Model of Neonatal Hypoxic Ischemic Encephalopathy

Published on: October 28, 2022

850
Registered Bioimaging of Nanomaterials for Diagnostic and Therapeutic Monitoring
17:16

Registered Bioimaging of Nanomaterials for Diagnostic and Therapeutic Monitoring

Published on: December 9, 2010

10.4K

Related Experiment Videos

Last Updated: Sep 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

2.5K
Early Pathological and Magnetic Resonance Detection of Cerebral Injury Using a Rat Model of Neonatal Hypoxic Ischemic Encephalopathy
05:52

Early Pathological and Magnetic Resonance Detection of Cerebral Injury Using a Rat Model of Neonatal Hypoxic Ischemic Encephalopathy

Published on: October 28, 2022

850
Registered Bioimaging of Nanomaterials for Diagnostic and Therapeutic Monitoring
17:16

Registered Bioimaging of Nanomaterials for Diagnostic and Therapeutic Monitoring

Published on: December 9, 2010

10.4K

Area of Science:

  • Medical Imaging
  • Neonatal Neuroscience
  • Artificial Intelligence in Medicine

Background:

  • Neonatal intensive care unit (NICU) MRI is crucial for assessing infant brain abnormalities.
  • Permanent magnet scanners in NICUs face challenges like low signal-to-noise ratio (SNR) and limited coils, leading to long scan times.
  • Accelerating MRI scans is vital to minimize discomfort and motion artifacts in neonates.

Purpose of the Study:

  • To develop and validate a method for accelerating Magnetic Resonance Imaging (MRI) in the NICU setting.
  • To address the challenges of low SNR and limited data in neonatal MRI using diffusion probabilistic generative models.
  • To reduce MRI scan times for sick infants without compromising diagnostic image quality.

Main Methods:

  • Established a novel training dataset of 1 Tesla neonatal MR images from clinical settings.
  • Developed a pipeline including network architecture modification, unified model training with learned embeddings, self-supervised denoising, and posterior sample averaging for reconstruction.
  • Evaluated the methodology through retrospective under-sampling experiments and a clinical reader study with pediatric neuroradiologists.

Main Results:

  • The proposed pipeline quantitatively improved image reconstruction by combining data, denoising, and sample averaging.
  • The generative model achieved acceleration at two rates without retraining, decoupling the prior from the measurement model.
  • Reader studies indicated that images reconstructed from R ≈ 1.5 under-sampled data are clinically adequate.

Conclusions:

  • Diffusion probabilistic generative models, coupled with the proposed pipeline, can effectively handle challenging real-world neonatal MRI datasets.
  • This approach shows promise in significantly reducing scan times for in-NICU neonatal MRI.
  • The findings support the clinical utility of accelerated MRI for early detection of brain abnormalities in neonates.