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

Orientation-tuned surround suppression exhibits a unique laminar signature in the human primary visual cortex.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

Reading speed, visual deficits, and cerebral white matter integrity in veterans with and without mild traumatic brain injury.

Frontiers in neuroscience·2026
Same author

Frame-wise multi-echo distortion correction for superior functional MRI.

Imaging neuroscience (Cambridge, Mass.)·2026
Same author

Predictive acoustical processing in human cortical layers.

Nature communications·2026
Same author

An 80-channel receive array for 10.5T neuroimaging: Key considerations for SNR optimization.

bioRxiv : the preprint server for biology·2026
Same author

Functional MRI of the Human Hippocampus at 10.5T: Pushing the Boundaries of Spatial Resolution.

bioRxiv : the preprint server for biology·2026

Related Experiment Video

Updated: Oct 10, 2025

Author Spotlight: Advancing 3D Cytoarchitecture Analysis - Rapid Volumetric Reconstruction of the Human Brain
06:52

Author Spotlight: Advancing 3D Cytoarchitecture Analysis - Rapid Volumetric Reconstruction of the Human Brain

Published on: January 26, 2024

2.4K

20-fold Accelerated 7T fMRI Using Referenceless Self-Supervised Deep Learning Reconstruction.

Omer Burak Demirel, Burhaneddin Yaman, Logan Dowdle

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
    |December 11, 2021
    PubMed
    Summary
    This summary is machine-generated.

    Self-supervised deep learning reconstruction enables 20-fold accelerated 7T fMRI with high spatio-temporal resolution. This advanced technique improves image quality and maintains functional precision, outperforming standard acceleration methods.

    More Related Videos

    High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain
    10:06

    High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain

    Published on: May 10, 2012

    13.1K
    Simultaneous Data Collection of fMRI and fNIRS Measurements Using a Whole-Head Optode Array and Short-Distance Channels
    08:19

    Simultaneous Data Collection of fMRI and fNIRS Measurements Using a Whole-Head Optode Array and Short-Distance Channels

    Published on: October 20, 2023

    1.2K

    Related Experiment Videos

    Last Updated: Oct 10, 2025

    Author Spotlight: Advancing 3D Cytoarchitecture Analysis - Rapid Volumetric Reconstruction of the Human Brain
    06:52

    Author Spotlight: Advancing 3D Cytoarchitecture Analysis - Rapid Volumetric Reconstruction of the Human Brain

    Published on: January 26, 2024

    2.4K
    High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain
    10:06

    High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain

    Published on: May 10, 2012

    13.1K
    Simultaneous Data Collection of fMRI and fNIRS Measurements Using a Whole-Head Optode Array and Short-Distance Channels
    08:19

    Simultaneous Data Collection of fMRI and fNIRS Measurements Using a Whole-Head Optode Array and Short-Distance Channels

    Published on: October 20, 2023

    1.2K

    Area of Science:

    • Neuroimaging
    • Magnetic Resonance Imaging (MRI)
    • Artificial Intelligence

    Background:

    • High spatial and temporal resolution is crucial for functional MRI (fMRI) to accurately capture neural activity.
    • Accelerated imaging techniques like Simultaneous Multi-slice (SMS) and in-plane acceleration are vital for ultrahigh field fMRI but face limitations with higher acceleration rates due to artifacts.
    • Deep learning (DL) offers potential for reconstructing highly accelerated MRI, but supervised methods require unavailable fully-sampled datasets for high-resolution fMRI.

    Purpose of the Study:

    • To investigate the efficacy of self-supervised, physics-guided deep learning (DL) for reconstructing highly accelerated 7T fMRI data.
    • To evaluate the performance of this DL reconstruction method at a 20-fold acceleration (5-fold SMS and 4-fold in-plane).
    • To compare the quality and functional analysis outcomes of the DL-reconstructed data against standard acceleration methods.

    Main Methods:

    • Utilized a self-supervised, physics-guided deep learning (DL) reconstruction approach.
    • Applied the method to 7 Tesla (7T) fMRI data with a combined 20-fold acceleration (5-fold SMS and 4-fold in-plane).
    • Compared the reconstructed images and subsequent functional analysis results against a standard 10-fold accelerated acquisition.

    Main Results:

    • The self-supervised DL reconstruction successfully produced high-quality 7T fMRI images at a 20-fold acceleration.
    • The method significantly improved image quality compared to existing techniques at this high acceleration rate.
    • Functional precision and temporal effects in subsequent analyses were comparable to a standard 10-fold accelerated acquisition.

    Conclusions:

    • Self-supervised deep learning reconstruction is a viable and effective method for achieving highly accelerated 7T fMRI.
    • This approach overcomes limitations of traditional acceleration methods, enabling high-quality neuroimaging at 20-fold acceleration.
    • The technique maintains functional precision, offering a promising advancement for large-scale fMRI studies.