Workflow for effective integration of community detection algorithms in brain network analysis
This study presents a workflow utilizing network analysis based on community detection methods and functional magnetic resonance imaging (fMRI) to investigate brain connectomics problems. The objective of the study is to enhance the understanding of brain architecture and its clinical implications,...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | Spanish |
| Published: |
Universidad de las Ciencias Informáticas (UCI)
2025-07-01
|
| Series: | Serie Científica de la Universidad de las Ciencias Informáticas |
| Subjects: | |
| Online Access: | https://publicaciones.uci.cu/index.php/serie/article/view/1845 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This study presents a workflow utilizing network analysis based on community detection methods and functional magnetic resonance imaging (fMRI) to investigate brain connectomics problems. The objective of the study is to enhance the understanding of brain architecture and its clinical implications, particularly in identifying altered connectivity patterns in neurological and psychiatric conditions. Techniques such as intensity normalization and image smoothing were applied to ensure the quality of fMRI data processing. An autoencoder model was employed to analyze functional connectivity networks, and the Louvain algorithm was used to detect communities within these networks. High modularity values were achieved, and validation tests confirmed the robustness of the algorithm used in the analysis. This study advances our understanding of brain architecture and has significant clinical implications by identifying altered connectivity patterns, which may improve the diagnosis and treatment of neurological and psychiatric conditions. |
|---|---|
| ISSN: | 2306-2495 |