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

¹³C NMR: Distortionless Enhancement by Polarization Transfer (DEPT)01:20

¹³C NMR: Distortionless Enhancement by Polarization Transfer (DEPT)

1.0K
When proton-coupled carbon-13 spectra are simplified by a broadband proton decoupling technique, structural information about the coupled protons is lost. Distortionless enhancement by polarization transfer (DEPT) is a technique that provides information on the number of hydrogens attached to each carbon in a molecule. While the DEPT experiment utilizes complex pulse sequences, the pulse delay and flip angle are specifically manipulated. The resulting signals have different phases depending on...
1.0K

You might also read

Related Articles

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

Sort by
Same author

Prediction modeling in transdiagnostic risk: results from the PROCAN study.

Brain imaging and behavior·2026
Same author

Student-Athletes' Perceptions of the Serial 7s Dual-Task Concussion Testing Paradigm.

Journal of athletic training·2026
Same author

GABA+-Edited Magnetic Resonance Spectroscopy Deep Learning Quality Assessment Framework.

Magnetic resonance in medicine·2026
Same author

LobePrior segments lung lobes on computed tomography images in the presence of severe abnormalities.

Scientific reports·2026
Same author

The Role of Artificial Intelligence in Acute Stroke Imaging: Current Status and Future Directions.

Seminars in interventional radiology·2026
Same author

Hypothalamic Atrophy and Textural Changes in Polyglutamine Ataxias.

Cerebellum (London, England)·2026

Related Experiment Video

Updated: Jun 18, 2025

The Use of Magnetic Resonance Spectroscopy as a Tool for the Measurement of Bi-hemispheric Transcranial Electric Stimulation Effects on Primary Motor Cortex Metabolism
13:56

The Use of Magnetic Resonance Spectroscopy as a Tool for the Measurement of Bi-hemispheric Transcranial Electric Stimulation Effects on Primary Motor Cortex Metabolism

Published on: November 19, 2014

20.1K

Spectro-ViT: A vision transformer model for GABA-edited MEGA-PRESS reconstruction using spectrograms.

Gabriel Dias1, Rodrigo Pommot Berto2, Mateus Oliveira1

  • 1School of Electrical and Computer Engineering, University of Campinas, Campinas, Brazil.

Magnetic Resonance Imaging
|July 28, 2024
PubMed
Summary

This study introduces Spectro-ViT, a Vision Transformer model that accurately reconstructs GABA-edited Magnetic Resonance Spectroscopy (MRS) data using fewer samples. This accelerates scan times without compromising data quality.

Keywords:
Deep learningGABA-edited MEGA-PRESSMRS denoisingVision transformer

More Related Videos

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench
11:38

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

Published on: August 23, 2017

9.8K
A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells
12:49

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

Published on: September 28, 2019

12.7K

Related Experiment Videos

Last Updated: Jun 18, 2025

The Use of Magnetic Resonance Spectroscopy as a Tool for the Measurement of Bi-hemispheric Transcranial Electric Stimulation Effects on Primary Motor Cortex Metabolism
13:56

The Use of Magnetic Resonance Spectroscopy as a Tool for the Measurement of Bi-hemispheric Transcranial Electric Stimulation Effects on Primary Motor Cortex Metabolism

Published on: November 19, 2014

20.1K
Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench
11:38

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

Published on: August 23, 2017

9.8K
A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells
12:49

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

Published on: September 28, 2019

12.7K

Area of Science:

  • Neuroimaging
  • Biomedical Engineering
  • Artificial Intelligence

Background:

  • Magnetic Resonance Spectroscopy (MRS) is crucial for non-invasively quantifying brain metabolites.
  • Acquiring high-quality MRS data typically requires a significant number of transients, leading to long scan times.
  • Reducing scan time is essential for improving patient comfort and increasing data acquisition throughput.

Purpose of the Study:

  • To evaluate the efficacy of a Vision Transformer (ViT) model, named Spectro-ViT, for reconstructing GABA-edited MRS data from a reduced number of transients.
  • To assess the performance of Spectro-ViT in terms of data quality and metabolite concentration accuracy compared to conventional methods.
  • To enable faster MRS acquisitions through advanced AI-driven data reconstruction.

Main Methods:

  • GABA-edited MEGA-PRESS MRS data were acquired using 80 transients, significantly fewer than the standard 320 transients.
  • The reduced transient data were pre-processed and transformed into spectrogram images via Short-Time Fourier Transform (STFT).
  • A pre-trained Vision Transformer (ViT) was fine-tuned (Spectro-ViT) and compared against existing reconstruction pipelines using quantitative metrics and metabolite concentrations.

Main Results:

  • Spectro-ViT demonstrated superior overall quality metrics compared to other evaluated reconstruction pipelines.
  • Reconstructed GABA+ metabolite concentrations using Spectro-ViT achieved an excellent average R² of 0.67 and an average MAPE of 9.68%.
  • No statistically significant differences were observed in metabolite concentrations between Spectro-ViT reconstructions and the reference 320-transient scans.

Conclusions:

  • Spectro-ViT effectively reconstructs GABA-edited MRS data from a reduced number of transients, enabling significantly shorter scan times.
  • The model achieves high accuracy in metabolite quantification, comparable to standard acquisition protocols.
  • This AI-driven approach holds promise for accelerating MRS acquisition and improving clinical feasibility.