Related Experiment Video
Updated: Mar 6, 2026
11:15
Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy
Published on: June 27, 2013
34.4K
Applications of Epsilon Radial Networks in Neuroimage Analyses
Nagesh Adluru1, Moo K Chung2, Nicholas T Lange3
1Waisman Center, University of Wisconsin-Madison, USA.
Advances in Image and Video Technology : Pacific Rim Symposium, PSIVT ... Proceedings. IEEE Pacific Rim Symposium on Image and Video Technology
|March 3, 2017
Summary
New brain network analysis methods, epsilon radial networks (ERNs), efficiently reveal structural differences in populations. ERNs aid in identifying topological and quantitative variations, useful for autism studies and machine learning applications.
Area of Science:
- Neuroimaging
- Network Science
- Computational Neuroscience
Background:
- Advances in diffusion MRI and network analysis tools enable population-based brain wiring comparisons.
- Existing frameworks for brain network extraction can be computationally intensive.
Purpose of the Study:
- To extend existing frameworks for brain network extraction using epsilon radial networks (ERNs).
- To demonstrate ERNs' utility in analyzing structural brain network properties and performing region-of-interest (ROI) analyses.
- To showcase ERNs as a novel tool for statistical and machine learning-based neuroimage analysis.
Main Methods:
- Development of extended epsilon radial networks (ERNs) for brain network analysis.
- Application of ERNs to extract topo-physical properties of structural brain networks.
- Integration of ERNs for efficient region-of-interest (ROI) analyses.
Main Results:
- ERNs enable efficient mining of topo-physical properties of structural brain networks.
- ERNs facilitate efficient classical region-of-interest (ROI) analyses.
- Demonstrated application in an autism study for identifying group differences and performing classification.
Conclusions:
- Epsilon radial networks (ERNs) offer a novel and efficient approach for neuroimage analysis.
- ERNs are effective for both topological and quantitative analyses of brain networks.
- The proposed framework is applicable to population studies using computationally efficient network extraction methods.
