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

You might also read

Related Articles

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

Sort by
Same author

HyperCOCO: Multi-sensory HyperCOgnitive COmputing for learning population level brain connectivity.

Medical image analysis·2026
Same author

Reservoir-Based Graph Convolutional Networks.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Metadata-Driven Federated Learning of Connectional Brain Templates in Non-IID Multi-Domain Scenarios.

IEEE transactions on medical imaging·2025
Same author

Predicting infant brain connectivity with federated multi-trajectory GNNs using scarce data.

Medical image analysis·2025
Same author

FALCON: Feature-Label Constrained Graph Net Collapse for Memory-Efficient GNNs.

IEEE transactions on neural networks and learning systems·2025
Same author

Replica tree-based federated learning using limited data.

Neural networks : the official journal of the International Neural Network Society·2025
Same journal

Self-supervised isotropic reconstruction for abnormality detection in anisotropic MRI.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same journal

WDBDM: Wavelet-based dual-branch diffusion model for low-dose CT and PET denoising.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same journal

ScribSAM: A robust scribble-supervised framework for spatiotemporal segmentation of breast lesions in ultrasound videos.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same journal

Anatomically and biochemically guided deep image prior for sodium MRI denoising.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same journal

Segment Anything Model for medical image segmentation: A review.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same journal

HiCAF-Net: A Hierarchical Cross-Attention Fusion framework for cross-cancer subtype classification using histopathological and genomic data.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
See all related articles

Related Experiment Video

Updated: Jul 20, 2025

Modeling the Functional Network for Spatial Navigation in the Human Brain
05:55

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

1.1K

Graph neural network based unsupervised influential sample selection for brain multigraph population fusion.

Mert Can Kurucu1, Islem Rekik2,

  • 1BASIRA Lab, Imperial-X and Computing Department, Imperial College London, London, UK; Istanbul Technical University, Istanbul, Turkey.

Computerized Medical Imaging and Graphics : the Official Journal of the Computerized Medical Imaging Society
|August 2, 2023
PubMed
Summary
This summary is machine-generated.

Selecting influential brain graphs improves Graph Neural Network (GNN) training for population-based connectional brain templates (CBTs). This method enhances CBTs for network neuroscience applications, aiding in understanding neurological disorders.

Keywords:
Connectional brain templatesGraph neural networksMultigraph population fusionSample selectionUnsupervised learning

More Related Videos

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
12:27

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

7.0K
Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

5.7K

Related Experiment Videos

Last Updated: Jul 20, 2025

Modeling the Functional Network for Spatial Navigation in the Human Brain
05:55

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

1.1K
Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
12:27

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

7.0K
Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

5.7K

Area of Science:

  • Network Neuroscience
  • Machine Learning
  • Computational Biology

Background:

  • Graph Neural Networks (GNNs) are increasingly used for graph-structured data, including in network neuroscience for estimating population representative connectional brain templates (CBTs).
  • Existing GNN-based population fusion methods for CBT estimation do not account for the influence of individual training brain multigraphs on GNN training quality.

Purpose of the Study:

  • To propose and validate unsupervised methods for quantifying the influence of individual training brain multigraphs on GNN-based CBT population fusion.
  • To demonstrate that selecting influential training samples improves the quality of learned CBTs.

Main Methods:

  • Introduced two sample selection methods: GraphGradIn (using gradients to trace centeredness loss changes) and GraphTestIn (excluding training graphs during testing to infer influence).
  • Selected most influential multigraphs to construct training datasets for GNN-based CBT population fusion.
  • Conducted experiments on brain multigraph datasets to evaluate the impact of influential sample selection.

Main Results:

  • Using datasets of influential training samples significantly improved the learned connectional brain template (CBT) in terms of centeredness, discriminativeness, and topological soundness.
  • The proposed methods successfully identified influential brain multigraphs, leading to enhanced CBTs.
  • Demonstrated the application of these methods in discovering connectional fingerprints for healthy and neurological disorder populations (Alzheimer's disease, Autism spectrum disorder).

Conclusions:

  • The proposed unsupervised sample selection methods (GraphGradIn and GraphTestIn) effectively quantify the influence of individual brain multigraphs in GNN-based population fusion.
  • Selecting influential training samples is crucial for improving the quality and reliability of connectional brain templates.
  • These findings advance network neuroscience by enabling more accurate CBTs and facilitating the discovery of disease-specific brain network characteristics.