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

Brain Imaging01:14

Brain Imaging

320
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...
320

You might also read

Related Articles

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

Sort by
Same author

Evaluation of the BT-50 Automatic Quality Control Unit on the XN9000 Hematology Analyzer.

International journal of laboratory hematology·2026
Same author

A Hybrid CNN-Transformer Network for fMRI-Based Feature Encoding in Alzheimer's Disease Classification.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

Smart hospital: achieving interoperability and raw data collection from medical devices in clinical routine.

Frontiers in digital health·2024
Same author

DWT-CNNTRN: a Convolutional Transformer for ECG Classification with Discrete Wavelet Transform.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2023
Same author

Heartbeat Classification by Random Forest With a Novel Context Feature: A Segment Label.

IEEE journal of translational engineering in health and medicine·2022
Same author

GeneExpressionSignature: an R package for discovering functional connections using gene expression signatures.

Omics : a journal of integrative biology·2013

Related Experiment Video

Updated: Sep 16, 2025

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

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

Published on: October 24, 2012

14.8K

Transformer attention-based neural network for cognitive score estimation from sMRI data.

Songheng Li1, Yanteng Zhang2, Congyu Zou3

  • 1College of Artificial Intelligence (CUIT Shuangliu Industrial College), Chengdu University of Information Technology, Chengdu, 610225, China; National Intelligent Society Comprehensive Governance Experimental Base (CUIT Shuangliu Industrial College), Chengdu University of Information Technology, Chengdu, 610225, China.

Computers in Biology and Medicine
|July 4, 2025
PubMed
Summary

This study introduces a novel deep learning model using Transformer attention to predict cognitive scores from structural MRI, improving Alzheimer's disease (AD) diagnosis. The method effectively identifies key brain regions, enhancing prediction accuracy for dementia progression.

Keywords:
Alzheimer’s diseaseCNN encoderCognitive score estimationStructural MRITransformer attention

More Related Videos

Neuroimaging-Guided TMS–EEG for Real-Time Cortical Network Mapping
09:55

Neuroimaging-Guided TMS–EEG for Real-Time Cortical Network Mapping

Published on: June 13, 2025

1.1K
Exploring the Neural Correlates of Cognitive Reappraisal in Obsessive-Compulsive Disorder Using Task-based Functional Magnetic Resonance Imaging
09:14

Exploring the Neural Correlates of Cognitive Reappraisal in Obsessive-Compulsive Disorder Using Task-based Functional Magnetic Resonance Imaging

Published on: March 14, 2025

353

Related Experiment Videos

Last Updated: Sep 16, 2025

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

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

Published on: October 24, 2012

14.8K
Neuroimaging-Guided TMS–EEG for Real-Time Cortical Network Mapping
09:55

Neuroimaging-Guided TMS–EEG for Real-Time Cortical Network Mapping

Published on: June 13, 2025

1.1K
Exploring the Neural Correlates of Cognitive Reappraisal in Obsessive-Compulsive Disorder Using Task-based Functional Magnetic Resonance Imaging
09:14

Exploring the Neural Correlates of Cognitive Reappraisal in Obsessive-Compulsive Disorder Using Task-based Functional Magnetic Resonance Imaging

Published on: March 14, 2025

353

Area of Science:

  • Neuroimaging
  • Artificial Intelligence
  • Neurology

Background:

  • Accurate prediction of cognitive scores from structural MRI is crucial for understanding dementia and forecasting Alzheimer's disease (AD).
  • Existing deep learning methods often overlook individual structural variations in AD progression.
  • There is a need for advanced models that can capture subtle, region-specific brain changes related to cognitive decline.

Purpose of the Study:

  • To develop a deep neural network incorporating Transformer attention for joint prediction of multiple cognitive scores (ADAS, CDRSB, MMSE) from structural MRI.
  • To improve the accuracy of cognitive decline prediction in Alzheimer's disease by focusing on individual-specific structural differences.
  • To enhance the clinical utility of neuroimaging in diagnosing and monitoring dementia.

Main Methods:

  • A 3D convolutional neural network (CNN) backbone was used to encode sMRI data, capturing local structural information.
  • An improved Transformer attention block with 3D positional encoding and convolutional layers adaptively identified discriminative imaging features across the brain.
  • An attention-aware regression network facilitated the joint prediction of multiple cognitive scores.

Main Results:

  • The proposed method demonstrated superior performance compared to existing traditional and deep learning approaches on the ADNI dataset.
  • Qualitative analysis confirmed that the identified dementia-related brain regions possess significant biological relevance.
  • The model effectively enhanced the performance of cognitive score prediction by focusing on critical cognitive-related areas.

Conclusions:

  • The developed deep learning model with Transformer attention offers a promising approach for accurate cognitive score prediction from structural MRI.
  • This method holds potential for improved early detection, diagnosis, and monitoring of Alzheimer's disease and other dementias.
  • The findings highlight the importance of incorporating attention mechanisms to capture individual-specific brain alterations in neurodegenerative diseases.