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 Experiment Videos

Research on hemodynamic state prediction based on feature-enhanced multi-model ensemble.

Shuai Yan1, Minghua Liu1, Xiaoyan Wang1

  • 1School of Electrical Engineering, Northwest Minzu University, Lanzhou Gansu, China.

Methodsx
|June 12, 2026
PubMed
Summary

This study introduces a novel framework for accurately inverting neural and vasodilatory signals from BOLD-fMRI data, significantly improving prediction performance for both signals.

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

In Situ Probing the Effects of Lipid Packing Density and Concentration of CPPs on the Transmembrane Process at the Air-Water Interface.

The journal of physical chemistry letters·2025
Same author

Effects and Mechanisms of Lonicerin Against Atopic Dermatitis: An Integration of Bioinformatics Analysis and Experimental Validation.

FASEB journal : official publication of the Federation of American Societies for Experimental Biology·2025
Same author

Lutein Alleviate Acute Lung Injury Induced by Limb Ischemia-Reperfusion Through PPAR-γ/PI3K/AKT/NLRP3 Signaling.

Mediators of inflammation·2025
Same author

Identification of Protein Markers for Chronic Ischemic Heart Disease Through Integrated Analysis of the Human Plasma Proteome and Genome-Wide Association Data.

Proteomes·2025
Same author

N-doping enhanced catalytic mechanism of Co-loaded biochar cathode for degrading organic phosphorus flame retardants in heterogeneous electro-Fenton system.

Journal of colloid and interface science·2025
Same author

Amino Acid Directed Helical Assemblies of Natural Berberine for Chirality-Dependent Photodynamic Antibacterial Therapy.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2025

Area of Science:

  • Neuroimaging
  • Biophysics
  • Machine Learning

Background:

  • Blood-oxygen-level-dependent (BOLD) functional magnetic resonance imaging (fMRI) is crucial for neuroscience research.
  • Accurately inverting BOLD signals to understand neural activity and vasodilation remains a significant challenge.
  • Existing methods often struggle with the complexity and non-linearity of the BOLD signal.

Purpose of the Study:

  • To develop and validate a novel framework for high-fidelity inversion of neural and vasodilatory signals from BOLD-fMRI data.
  • To enhance the accuracy of predicting underlying physiological signals compared to current benchmarks.
  • To provide a new computational pathway for reconstructing microscopic neural activity from macroscopic BOLD signals.

Main Methods:

  • Multi-scale dynamic feature extraction to capture comprehensive BOLD signal characteristics.
Keywords:
BOLD-fMRIFeature enhancementGradient boosting treesHemodynamic state predictionStacking ensemble

Related Experiment Videos

  • A stacking ensemble architecture integrating multiple heterogeneous base learners.
  • Hierarchical model fusion using a meta-learner for robust prediction integration and capturing non-linear mappings.

    • Main Results:

    • Achieved R² of 0.92 for vasodilatory signal and 0.78 for neural drive signal on synthetic data (Balloon model).
    • Outperformed existing benchmark methods in signal inversion accuracy.
    • Validated on real fMRI data, demonstrating successful neural activity reconstruction with high correlation (up to 0.9931) between reconstructed and measured BOLD signals.

    Conclusions:

    • The proposed framework significantly enhances the accuracy of inverting neural and vasodilatory signals from BOLD-fMRI data.
    • This method offers a robust approach for understanding the relationship between neural activity, hemodynamic responses, and BOLD signals.
    • Paves the way for more precise investigations into brain function using fMRI.