RESUMO
From molecular mechanisms to global brain networks, atypical fluctuations are the hallmark of neurodegeneration. Yet, traditional fMRI research on resting-state networks (RSNs) has favored static and average connectivity methods, which by overlooking the fluctuation dynamics triggered by neurodegeneration, have yielded inconsistent results. The present multicenter study introduces a data-driven machine learning pipeline based on dynamic connectivity fluctuation analysis (DCFA) on RS-fMRI data from 300 participants belonging to three groups: behavioral variant frontotemporal dementia (bvFTD) patients, Alzheimer's disease (AD) patients, and healthy controls. We considered non-linear oscillatory patterns across combined and individual resting-state networks (RSNs), namely: the salience network (SN), mostly affected in bvFTD; the default mode network (DMN), mostly affected in AD; the executive network (EN), partially compromised in both conditions; the motor network (MN); and the visual network (VN). These RSNs were entered as features for dementia classification using a recent robust machine learning approach (a Bayesian hyperparameter tuned Gradient Boosting Machines (GBM) algorithm), across four independent datasets with different MR scanners and recording parameters. The machine learning classification accuracy analysis revealed a systematic and unique tailored architecture of RSN disruption. The classification accuracy ranking showed that the most affected networks for bvFTD were the SN + EN network pair (mean accuracy = 86.43%, AUC = 0.91, sensitivity = 86.45%, specificity = 87.54%); for AD, the DMN + EN network pair (mean accuracy = 86.63%, AUC = 0.89, sensitivity = 88.37%, specificity = 84.62%); and for the bvFTD vs. AD classification, the DMN + SN network pair (mean accuracy = 82.67%, AUC = 0.86, sensitivity = 81.27%, specificity = 83.01%). Moreover, the DFCA classification systematically outperformed canonical connectivity approaches (including both static and linear dynamic connectivity). Our findings suggest that non-linear dynamical fluctuations surpass two traditional seed-based functional connectivity approaches and provide a pathophysiological characterization of global brain networks in neurodegenerative conditions (AD and bvFTD) across multicenter data.
Assuntos
Doença de Alzheimer/diagnóstico por imagem , Encéfalo/diagnóstico por imagem , Conectoma , Função Executiva , Demência Frontotemporal/diagnóstico por imagem , Vias Neurais/diagnóstico por imagem , Idoso , Doença de Alzheimer/fisiopatologia , Teorema de Bayes , Encéfalo/fisiopatologia , Estudos de Casos e Controles , Rede de Modo Padrão/diagnóstico por imagem , Rede de Modo Padrão/fisiopatologia , Vias Eferentes/diagnóstico por imagem , Vias Eferentes/fisiopatologia , Feminino , Demência Frontotemporal/fisiopatologia , Neuroimagem Funcional , Humanos , Aprendizado de Máquina , Imageamento por Ressonância Magnética , Masculino , Pessoa de Meia-Idade , Vias Neurais/fisiopatologia , Vias Visuais/diagnóstico por imagem , Vias Visuais/fisiopatologiaRESUMO
OBJECTIVES: Behavioral variant frontotemporal dementia (bvFTD) is characterized by early atrophy in the frontotemporoinsular regions. These regions overlap with networks that are engaged in social cognition-executive functions, two hallmarks deficits of bvFTD. We examine (i) whether Network Centrality (a graph theory metric that measures how important a node is in a brain network) in the frontotemporoinsular network is disrupted in bvFTD, and (ii) the level of involvement of this network in social-executive performance. METHODS: Patients with probable bvFTD, healthy controls, and frontoinsular stroke patients underwent functional MRI resting-state recordings and completed social-executive behavioral measures. RESULTS: Relative to the controls and the stroke group, the bvFTD patients presented decreased Network Centrality. In addition, this measure was associated with social cognition and executive functions. To test the specificity of these results for the Network Centrality of the frontotemporoinsular network, we assessed the main areas from six resting-state networks. No group differences or behavioral associations were found in these networks. Finally, Network Centrality and behavior distinguished bvFTD patients from the other groups with a high classification rate. CONCLUSIONS: bvFTD selectively affects Network Centrality in the frontotemporoinsular network, which is associated with high-level social and executive profile.