In this study, we employed a clustering approach to analyze fMRI data from a publicly available dataset of patients with mild depression. We utilized the CONN toolbox, a widely recognized tool, to extract functional networks from the fMRI data. Subsequently, these networks were aligned using MULTIMAGNA++, a global multiple alignment software, to ensure consistency across individual datasets. The aligned data was then subjected to a clustering analysis to investigate the presence of distinct patterns. Our findings demonstrate that not only is it feasible to accurately cluster patients using this approach, but there is also potential to uncover previously unidentified subgroups among both control subjects and those affected by the disease. These results suggest new avenues for understanding the neurobiological underpinnings of mild depression and for developing targeted interventions.

A Graph-Theory Based fMRI Analysis

Barillaro L.;Milano M.;Caligiuri M. E.;Agapito G.;Cannataro M.
2024-01-01

Abstract

In this study, we employed a clustering approach to analyze fMRI data from a publicly available dataset of patients with mild depression. We utilized the CONN toolbox, a widely recognized tool, to extract functional networks from the fMRI data. Subsequently, these networks were aligned using MULTIMAGNA++, a global multiple alignment software, to ensure consistency across individual datasets. The aligned data was then subjected to a clustering analysis to investigate the presence of distinct patterns. Our findings demonstrate that not only is it feasible to accurately cluster patients using this approach, but there is also potential to uncover previously unidentified subgroups among both control subjects and those affected by the disease. These results suggest new avenues for understanding the neurobiological underpinnings of mild depression and for developing targeted interventions.
2024
9783031637773
9783031637780
Clustering
Functional Magnetic Resonance Imaging
Global Network alignment
Graph theory
Machine learning
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.12317/98078
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact