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

Robust Construction of Diffusion MRI Atlases with Correction for Inter-Subject Fiber Dispersion.

Computational diffusion MRI : MICCAI Workshop·2017
Same author

Robust Fusion of Diffusion MRI Data for Template Construction.

Scientific reports·2017
Same author

Learning-Based Multimodal Image Registration for Prostate Cancer Radiation Therapy.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2017
Same author

Segmenting hippocampal subfields from 3T MRI with multi-modality images.

Medical image analysis·2017
Same author

Joint Discriminative and Representative Feature Selection for Alzheimer's Disease Diagnosis.

Machine learning in medical imaging. MLMI (Workshop)·2017
Same author

Single- and Multiple-Shell Uniform Sampling Schemes for Diffusion MRI Using Spherical Codes.

IEEE transactions on medical imaging·2017

Related Experiment Video

Updated: Sep 29, 2025

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging
11:28

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

11.8K

Deep attentive spatio-temporal feature learning for automatic resting-state fMRI denoising.

Keun-Soo Heo1, Dong-Hee Shin1, Sheng-Che Hung2

  • 1Department of Artificial Intelligence, Korea University, Seoul, Republic of Korea.

Neuroimage
|March 26, 2022
PubMed
Summary

A new deep learning framework automatically identifies noise in resting-state functional MRI (rs-fMRI) data, improving speed and accuracy across diverse datasets, including infant brains.

Keywords:
Convolutional neural networkDeep learningDenoisingIndependent component analysisResting-state fMRI

More Related Videos

Author Spotlight: Methodologies and Advancements of Chronic Pain Management Research
08:33

Author Spotlight: Methodologies and Advancements of Chronic Pain Management Research

Published on: January 5, 2024

1.3K
Best Current Practice for Obtaining High Quality EEG Data During Simultaneous fMRI
10:35

Best Current Practice for Obtaining High Quality EEG Data During Simultaneous fMRI

Published on: June 3, 2013

32.9K

Related Experiment Videos

Last Updated: Sep 29, 2025

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging
11:28

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

11.8K
Author Spotlight: Methodologies and Advancements of Chronic Pain Management Research
08:33

Author Spotlight: Methodologies and Advancements of Chronic Pain Management Research

Published on: January 5, 2024

1.3K
Best Current Practice for Obtaining High Quality EEG Data During Simultaneous fMRI
10:35

Best Current Practice for Obtaining High Quality EEG Data During Simultaneous fMRI

Published on: June 3, 2013

32.9K

Area of Science:

  • Neuroimaging
  • Machine Learning
  • Signal Processing

Background:

  • Resting-state functional magnetic resonance imaging (rs-fMRI) is crucial for studying brain functional connectomes.
  • Raw rs-fMRI data contains significant noise from physiological activities, necessitating effective denoising during preprocessing.
  • Current denoising methods often rely on component decomposition and regression of noise-related components, which can be limited by manual feature engineering.

Purpose of the Study:

  • To develop a novel, automatic, and end-to-end deep learning framework for accurate identification of noise-related components in rs-fMRI data.
  • To overcome limitations of manual feature engineering and improve the generalizability of noise detection across diverse populations and datasets.
  • To enhance the speed and efficiency of noise component identification in rs-fMRI preprocessing pipelines.

Main Methods:

  • Proposed a deep learning framework utilizing a multi-layer feature extraction strategy to learn embedded spatio-temporal features.
  • Developed an automatic and end-to-end approach for noise-related component identification.
  • Validated the framework on heterogeneous rs-fMRI datasets, including adult and infant cohorts.

Main Results:

  • Achieved remarkable performance in identifying noise-related components across various rs-fMRI datasets.
  • Demonstrated high accuracy on heterogeneous datasets, including challenging infant rs-fMRI data.
  • Significantly increased noise detection speed, classifying single components in under 1 second.

Conclusions:

  • The proposed deep learning framework offers a fast, accurate, and automatic solution for rs-fMRI noise component identification.
  • The framework's ability to learn deep spatio-temporal features enhances its robustness and generalizability.
  • This approach can be seamlessly integrated into existing rs-fMRI preprocessing pipelines, improving overall data quality.