Search research articles

Related Concept Videos

Brain Imaging

Brain Imaging

Brain imaging technologies provide critical insights into both the structure and function of the human brain, enabling medical professionals and researchers to diagnose, study, and treat neurological disorders or psychiatric disorders more effectively.
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans), magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and Transcranial Magnetic...

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

Home
Explorations Of Using A Convolutional Neural Network To Understand Brain Activations During Movie Watching.

Home
Explorations Of Using A Convolutional Neural Network To Understand Brain Activations During Movie Watching.

Related Experiment Video

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

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

Published on: June 30, 2018

Explorations of using a convolutional neural network to understand brain activations during movie watching.

Wonbum Sohn^1,2, Xin Di¹, Zhen Liang³

¹Department of Biomedical Engineering, New Jersey Institute of Technology, Newark, NJ, 07029, USA.

Biorxiv : the Preprint Server for Biology

|February 8, 2024

View abstract on PubMed

Summary

This summary is machine-generated.

Deep neural networks like VGG-16 link video features to brain activity. Lower layers map to visual areas, while deeper layers connect to complex cognitive regions, revealing insights into brain function.

Keywords:

Convolutional neural network Default mode network Lateral occipital complex Naturalistic condition Supramarginal gyrus Visual cortex

More Related Videos

Dynamic Inter-subject Functional Connectivity Reveals Moment-to-Moment Brain Network Configurations Driven by Continuous or Communication Paradigms

Dynamic Inter-subject Functional Connectivity Reveals Moment-to-Moment Brain Network Configurations Driven by Continuous or Communication Paradigms

Published on: March 21, 2019

Extracting Visual Evoked Potentials from EEG Data Recorded During fMRI-guided Transcranial Magnetic Stimulation

Extracting Visual Evoked Potentials from EEG Data Recorded During fMRI-guided Transcranial Magnetic Stimulation

Published on: May 12, 2014

Related Experiment Videos

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

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

Published on: June 30, 2018

Dynamic Inter-subject Functional Connectivity Reveals Moment-to-Moment Brain Network Configurations Driven by Continuous or Communication Paradigms

Dynamic Inter-subject Functional Connectivity Reveals Moment-to-Moment Brain Network Configurations Driven by Continuous or Communication Paradigms

Published on: March 21, 2019

Extracting Visual Evoked Potentials from EEG Data Recorded During fMRI-guided Transcranial Magnetic Stimulation

Extracting Visual Evoked Potentials from EEG Data Recorded During fMRI-guided Transcranial Magnetic Stimulation

Published on: May 12, 2014

Area of Science:

Neuroscience
Computer Science
Cognitive Science

Background:

Neuroimaging studies use naturalistic stimuli (e.g., videos) to understand brain activation during complex tasks like social interaction.
The complexity of naturalistic stimuli makes it challenging to link specific brain activations to higher-level cognitive functions.
Deep neural networks (DNNs), particularly convolutional neural networks (CNNs), offer a hierarchical feature extraction approach valuable for analyzing complex visual data.

Approach:

Utilized a pre-trained VGG-16 CNN model to extract hierarchical features from video stimuli.
Analyzed functional magnetic resonance imaging (fMRI) data from participants watching a cartoon movie.
Correlated VGG-16 layer activations with brain activity patterns using a voxel-wise model.

Key Points:

Lower convolutional layers of VGG-16 associated with primary visual processing regions.
Specific kernels in lower layers unexpectedly linked to the posterior cingulate cortex (default mode network).
Deeper convolutional layers correlated with higher-level visual areas (e.g., lateral occipital complex) and the supramarginal gyrus.

Conclusions:

CNNs, like VGG-16, can map hierarchical visual features to distinct brain regions and networks.
The study demonstrates the potential of using DNNs to decode brain responses to complex visual stimuli.
Identified both the promise and limitations of CNNs in linking video content to specific brain functions and processing hierarchies.