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 Videos

Bayesian kernel methods for analysis of functional neuroimages.

Ana S Lukic¹, Miles N Wernick, Dimitris G Tzikas

¹Department of Biomedical Engineering, Illinois Institute of Technology, Chicago, IL 60616, USA.

IEEE Transactions on Medical Imaging

|December 21, 2007

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

Chinese expert consensus on additional surgery following endoscopic resection for early colorectal cancer (2025 edition).

Cancer biology & medicine·2026

Same author

Oxime-modified pillar[5]arene-based hybrid supramolecular polymers: construction and antibacterial performance.

Chemical communications (Cambridge, England)·2026

Same author

Transcriptional Regulation and WGCNA Studies of Leaf Abscission in Cotton Cultivars FU75 and 518-48 Under Chemical Defoliant Treatment.

Biology·2026

Same author

Encapsulation of <sup>211</sup>At(Ø)<sup>+</sup> into a Nanoscale Covalent Organic Framework Prevents Deastatination In Vivo.

Journal of the American Chemical Society·2026

Same author

Inhibitory activity and antifungal mechanism of venturicidin A against Pyricularia oryzae.

Pesticide biochemistry and physiology·2025

Same author

Dementia Care Research and Psychosocial Factors.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2025

Same journal

BrainCL: Transformer-Based Brain Network Contrastive Learning with Multi-Order Topology and Salience Masking.

IEEE transactions on medical imaging·2026

Same journal

LLM-enhanced Neuron Segmentation and Reconstruction in Complex Mouse Brain Images.

IEEE transactions on medical imaging·2026

Same journal

Matrixed-Spectrum Decomposition Accelerated Linear Boltzmann Transport Equation Solver for Fast Scatter Correction in Multi-Spectral CT.

IEEE transactions on medical imaging·2026

Same journal

The Ritz Adjoint Method for MRI Pulse Design.

IEEE transactions on medical imaging·2026

Same journal

Physiology-guided Self-supervised Learning for Simultaneous Dual-Tracer PET Separation.

IEEE transactions on medical imaging·2026

Same journal

Informed-Exploration Reinforcement Learning for Automated Virtual Coronary Intervention Planning.

IEEE transactions on medical imaging·2026

See all related articles

This study introduces a novel kernel-based approach for analyzing functional neuroimages, utilizing machine learning techniques to detect neuronal activation. The relevance vector machine (RVM) method proved more computationally efficient than Reversible-Jump Markov-chain Monte-Carlo (RJMCMC) for neuroimage analysis.

Area of Science:

Neuroimaging
Machine Learning
Statistical Analysis

Background:

Functional neuroimaging generates complex data requiring advanced analytical methods.
Kernel methods are powerful machine learning tools with potential for neuroimage analysis.
Accurate detection of neuronal activation is crucial for understanding brain function.

Purpose of the Study:

To develop and evaluate a novel approach for analyzing functional neuroimages using kernel methods.
To compare the efficacy and computational efficiency of two Bayesian estimation techniques: RJMCMC and RVM.
To detect regions of neuronal activation using a generalized likelihood ratio test (GLRT).

Main Methods:

Modeling spatial activation patterns as a superposition of kernel functions.

Related Experiment Videos

Estimating kernel function parameters using Maximum A Posteriori (MAP) via RJMCMC and Relevance Vector Machines (RVM).

Employing a Generalized Likelihood Ratio Test (GLRT) for activation detection.

Main Results:

Both RVM and RJMCMC methods successfully estimated activation patterns and detected neuronal activity.
RVM demonstrated significantly faster computation times compared to RJMCMC.
Receiver operating characteristic (ROC) curves indicated good performance for both methods on simulated and real fMRI data.

Conclusions:

Kernel-based methods offer a promising approach for functional neuroimage analysis.
RVM is a computationally efficient and effective technique for modeling and detecting neuronal activation in neuroimaging data.
The proposed GLRT framework combined with kernel methods provides a robust tool for neuroimage analysis.