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 Video

Updated: May 23, 2026

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging
11:28

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

Published on: June 30, 2018

Multi-source feature learning for joint analysis of incomplete multiple heterogeneous neuroimaging data.

Lei Yuan1, Yalin Wang, Paul M Thompson

  • 1School of Computing, Informatics, and Decision Systems Engineering, Arizona State University, Tempe, AZ 85287, USA.

Neuroimage
|April 14, 2012
PubMed
Summary

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

Author Correction: UKB-MDRMF: a multi-disease risk and multimorbidity framework based on UK biobank data.

Nature communications·2026
Same author

MyESL: A Software for Evolutionary Sparse Learning in Molecular Phylogenetics and Genomics.

Molecular biology and evolution·2025
Same author

Rhizosphere microbial diversity and functional roles in tea cultivars: insights from high-throughput sequencing and functional isolates.

Plant signaling & behavior·2025
Same author

LLaFS++: Few-Shot Image Segmentation With Large Language Models.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

CATI: A medical context-enhanced framework for diagnosis code assignment in the UK Biobank study.

Artificial intelligence in medicine·2025
Same author

UKB-MDRMF: a multi-disease risk and multimorbidity framework based on UK biobank data.

Nature communications·2025

Integrating incomplete brain imaging data is challenging. A new incomplete Multi-Source Feature (iMSF) learning method uses all available data, improving Alzheimer

Area of Science:

  • Neuroimaging
  • Machine Learning
  • Data Science

Background:

  • Large-scale brain imaging datasets often have missing data across modalities like MRI, FDG-PET, CSF, and proteomics.
  • Traditional methods discard subjects with incomplete data, leading to significant information loss.
  • The Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset exemplifies this challenge with substantial missing values.

Purpose of the Study:

  • To propose an incomplete Multi-Source Feature (iMSF) learning method to effectively utilize all available samples, even with missing data.
  • To classify Alzheimer's Disease (AD), mild cognitive impairment (MCI), and normal control (NC) subjects using multi-modality data from ADNI.
  • To develop a robust system by combining iMSF with other missing value estimation techniques into a classifier ensemble.

More Related Videos

Basics of Multivariate Analysis in Neuroimaging Data
06:35

Basics of Multivariate Analysis in Neuroimaging Data

Published on: July 24, 2010

Related Experiment Videos

Last Updated: May 23, 2026

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging
11:28

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

Published on: June 30, 2018

Basics of Multivariate Analysis in Neuroimaging Data
06:35

Basics of Multivariate Analysis in Neuroimaging Data

Published on: July 24, 2010

Main Methods:

  • Developed an incomplete Multi-Source Feature (iMSF) learning approach to integrate multi-modal brain imaging data with missing values.
  • Applied sparse learning methods to identify shared features across available data sources.
  • Constructed a classifier ensemble by integrating iMSF with four complementary missing value imputation methods.
  • Utilized baseline data from 780 ADNI participants with at least one of four data types (MRI, FDG-PET, CSF, proteomics).

Main Results:

  • The proposed iMSF method effectively leverages samples with incomplete data, preventing information loss.
  • Classification experiments using ADNI data demonstrated the efficacy of the iMSF approach.
  • The classifier ensemble, combining iMSF with other imputation methods, yielded stable and promising classification results.
  • Comprehensive experiments confirmed the robustness of the iMSF method and the ensemble model across various parameters.

Conclusions:

  • The incomplete Multi-Source Feature (iMSF) learning method offers a viable solution for analyzing large-scale, incomplete multi-modal brain imaging datasets.
  • The developed ensemble model provides a practical and robust system for subject classification in neurodegenerative disease studies.
  • This approach maximizes data utilization, leading to more comprehensive analyses and potentially improved diagnostic accuracy in Alzheimer's disease research.