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