Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jul 29, 2025

Functional Mapping with Simultaneous MEG and EEG

Functional Mapping with Simultaneous MEG and EEG

Published on: June 14, 2010

Multi-head attention-based masked sequence model for mapping functional brain networks.

Mengshen He^1,2, Xiangyu Hou², Enjie Ge²

¹Key Laboratory of Modern Teaching Technology, Ministry of Education, Shaanxi Normal University, Xi'an, China.

Frontiers in Neuroscience

|May 22, 2023

Summary

This summary is machine-generated.

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

Exploring ChatGPT's potential in dialogic teaching: A comparative neurocognitive study of AI and human instruction.

Acta psychologica·2026

Same author

Landscape screening identifies the lactate-modifying enzyme AARS2 as a master regulator and therapeutic target in hepatocellular carcinoma.

Gut·2026

Same author

Proteomic Analysis of Differentially Expressed Proteins in Ischemic Stroke Recovery and Their Implications for Therapeutic Outcomes.

Translational stroke research·2026

Same author

JOSD1 drives hepatocellular carcinoma malignancy by modulating the ubiquitination-lactylation switch on PGAM1.

Gut·2026

Same author

Runoff to the Abyss: A Large-Scale Investigation of the Occurrence, Transport, and Risk-Driven Prioritization of Rubber Vulcanization Accelerators.

Environmental science & technology·2026

Same author

STFusion: A Spatial-Temporal Dual-Pathway Network with Multi-scale Attention Fusion for Early Diagnosis of Parkinson's Disease.

Interdisciplinary sciences, computational life sciences·2026

Same journal

Evaluation of an open-face 8-channel transmit 64-channel receive 7T head coil for neuroimaging.

Frontiers in neuroscience·2026

Same journal

Acoustic stimulation in pain management: neurobiological mechanisms and clinical applications-a narrative review.

Frontiers in neuroscience·2026

Same journal

Local brain connectome parameters across the spectrum of clinical cognitive decline.

Frontiers in neuroscience·2026

Same journal

Body mass index affects EEG microstate dynamics through blood viscosity in high-altitude environments.

Frontiers in neuroscience·2026

Same journal

Disrupted glymphatic function and its relationship with sleep and cognitive impairment in ME/CFS assessed via DTI-ALPS.

Frontiers in neuroscience·2026

Same journal

Neuromorphic-inspired multi-view global-local fusion for IR-UWB radar dynamic gesture recognition.

Frontiers in neuroscience·2026

See all related articles

A new model, Multi-head Attention-based Masked Sequence Model (MAMSM), improves functional brain network (FBN) analysis in task-based functional MRI (tfMRI). It captures complex brain states and enhances understanding of brain function.

Area of Science:

Neuroimaging
Computational Neuroscience
Machine Learning

Background:

Functional brain networks (FBNs) are crucial for understanding brain function, often studied using task-based functional magnetic resonance imaging (tfMRI).
Existing methods for FBN construction, like GLM and STAAE, have limitations in capturing dynamic brain states and incorporating prior task knowledge.
Current approaches may misinterpret fMRI signals, as identical values can represent different brain states across time.

Purpose of the Study:

To develop a novel, efficient model for FBN construction that addresses limitations of current methods.
To leverage natural language processing (NLP) techniques to better model fMRI data characteristics.
To improve the accuracy and interpretability of FBNs derived from tfMRI data.

Main Methods:

Keywords:

feature selection functional brain networks masked sequence modeling multi-head attention task fMRI

More Related Videos

Modeling the Functional Network for Spatial Navigation in the Human Brain

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

Related Experiment Videos

Last Updated: Jul 29, 2025

Functional Mapping with Simultaneous MEG and EEG

Functional Mapping with Simultaneous MEG and EEG

Published on: June 14, 2010

Modeling the Functional Network for Spatial Navigation in the Human Brain

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

Introduction of the Multi-head Attention-based Masked Sequence Model (MAMSM), inspired by NLP.
Implementation of a multi-headed attention mechanism and mask training to discern distinct brain states from similar voxel values.
Development of a novel loss function combining cosine similarity and task design curves for enhanced model training.

Main Results:

MAMSM achieved an average Pearson correlation coefficient above 0.95 with task design curves on HCP tfMRI datasets.
The model successfully extracted meaningful brain networks beyond those directly associated with the tasks.
Experimental results demonstrate the model's effectiveness in capturing nuanced functional brain dynamics.

Conclusions:

MAMSM offers a significant advancement in analyzing functional brain networks from tfMRI data.
The model's ability to learn dynamic brain states and incorporate task information enhances understanding of brain function.
MAMSM shows great potential for future neuroimaging research and clinical applications.