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 Experiment Video

Updated: Dec 31, 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

3.3K

A Transfer-Learning Approach for Accelerated MRI Using Deep Neural Networks.

Salman Ul Hassan Dar1,2, Muzaffer Özbey1,2, Ahmet Burak Çatlı1,2

  • 1Department of Electrical and Electronics Engineering, Bilkent University, Ankara, Turkey.

Magnetic Resonance in Medicine
|January 4, 2020
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Magnetic Resonance Imaging01:24

Magnetic Resonance Imaging

8.9K
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...
8.9K

You might also read

Related Articles

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

Sort by
Same author

Unconditional latent diffusion models memorize patient imaging data.

Nature biomedical engineering·2025
Same author

Self-consistent recursive diffusion bridge for medical image translation.

Medical image analysis·2025
Same author

Combined conventional factors and the radiomics signature of coronary plaque texture could improve cardiac risk prediction.

Insights into imaging·2024
Same author

Assessing the Capacity of a Denoising Diffusion Probabilistic Model to Reproduce Spatial Context.

IEEE transactions on medical imaging·2024
Same author

One model to unite them all: Personalized federated learning of multi-contrast MRI synthesis.

Medical image analysis·2024
Same author

Parallel-stream fusion of scan-specific and scan-general priors for learning deep MRI reconstruction in low-data regimes.

Computers in biology and medicine·2023

Transfer learning enables deep neural networks for accelerated MRI reconstruction using limited data. This approach achieves high performance comparable to models trained on large datasets, overcoming data scarcity challenges.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Machine Learning

Background:

  • Deep neural networks show promise for reconstructing undersampled magnetic resonance imaging (MRI) data.
  • Training these networks typically requires large datasets, which are often unavailable in practice for specific MRI protocols.

Purpose of the Study:

  • To introduce a transfer-learning approach to mitigate data scarcity issues in training deep neural networks for accelerated MRI.
  • To enable effective MRI reconstruction without the need for extensive, protocol-specific imaging datasets.

Main Methods:

  • Neural networks were initially trained on large public datasets (natural images or brain MRI) and subsequently fine-tuned with a small number of brain MRI images from a distinct testing domain.
  • Performance of transfer-learned networks was compared against networks trained from scratch on the testing domain data.
Keywords:
accelerated MRIcompressive sensingdeep learningimage reconstructiontransfer learning

Related Experiment Videos

Last Updated: Dec 31, 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

3.3K
  • Evaluations considered various acceleration factors (4-10) and training/fine-tuning sample sizes.

    • Main Results:

    • The transfer-learning approach demonstrated successful domain adaptation between different MRI contrasts (T1- and T2-weighted) and between natural and MR images.
    • Networks fine-tuned with only tens of images achieved performance nearly identical to networks trained on thousands of images.

    Conclusions:

    • Transfer learning facilitates the application of neural networks for MRI reconstruction, reducing the dependency on large, curated imaging datasets.
    • This method can significantly lower the barrier to entry for using advanced deep learning techniques in MRI acquisition.