Clinical cognitive decline, leading to Alzheimer’s Disease Dementia (ADD), has long been interpreted as a disconnection syndrome, hindering the information flow capacity of the brain, hence leading to the well-known symptoms of ADD. The structural and functional brain connectome analyses play a central role in studies of brain from this perspective. However, most current research implicitly assumes that the changes accompanying the progression of cognitive decline are monotonous in time, whether measured across the entire brain or in fixed cortical regions. We investigate the structural and functional connectivity-wise reorganization of the brain without such assumptions across the entire spectrum. We utilize nodal assortativity as a local topological measure of connectivity and follow a data-centric approach to identify and verify relevant local regions, as well as to understand the nature of underlying reorganization. The analysis of our preliminary experimental data points to statistically significant, hyper and hypo-assortativity regions that depend on the disease’s stage, and differ for structural and functional connectomes. Our results suggest a new perspective into the dynamic, potentially a mix of degenerative and compensatory, topological alterations that occur in the brain as cognitive decline progresses.

Autism spectrum disorder (ASD) is a neurodevelopmental condition characterized by impairments in social interaction and communication, along with atypical behavioral patterns. Affected individuals often seem isolated in their inner world and exhibit particular sensory reactions. The World Health Organization has indicated a persistent increase in the global prevalence of autism, with approximately 1 in 127 persons affected worldwide. This study contributes to the growing research effort by presenting a comprehensive analysis of functional connectivity patterns for ASD prediction using rs-fMRI datasets. A novel approach was used for ASD identification using the ABIDE II dataset, based on functional networks derived from BOLD signals. The sparse functional brain connectome (Lean-NET) model is employed to construct subject-specific connectomes, from which local graph metrics are extracted to quantify regional network properties. Statistically significant features are selected using Welch’s t-test, then subjected to False Discovery Rate (FDR) correction and classified using a Support Vector Machine (SVM). Our experimental results demonstrate that locally derived graph metrics effectively discriminate ASD from typically developing (TD) subjects and achieve accuracy ranging from 70% up to 91%, highlighting the potential of graph learning approaches for functional connectivity analysis and ASD characterization.

Alzheimer’s Disease and Dementia (ADD) progresses along a continuum of cognitive decline, typically from Subjective Cognitive Impairment (SCI) to Mild Cognitive Impairment (MCI) and eventually to dementia. While many studies have focused on classifying these clinical stages, fewer have examined whether brain connectomes encode this continuum in a low-dimensional, interpretable form. Motivated by the hypothesis that structural brain connectomes undergo complex yet compact changes across cognitive decline, we propose a Graph Neural Network (GNN)-based framework that embeds these connectomes into a two-dimensional manifold to capture the evolving patterns of structural connectivity associated with cognitive deterioration. Using attention-based graph aggregation and Principal Component Analysis (PCA), we find that MCI subjects consistently occupy an intermediate position between SCI and ADD, and that the observed transitions align with known clinical biomarkers of ADD pathology. This hypothesis-driven analysis is further supported by the model’s robust separation performance, with ROC-AUC scores of 0.93 for ADD vs. SCI and 0.81 for ADD vs. MCI. These findings offer an interpretable and neurologically grounded representation of dementia progression, emphasizing structural connectome alterations as potential markers of cognitive decline.

Neurological disorders such as Alzheimer's disease, Parkinson's disease, and autism disrupt the brain's structural and functional organization, particularly in specific regions, and ultimately lead to cognitive impairments. In Alzheimer's disease-related dementia, neuronal degeneration impairs structural connectivity between brain regions, which in turn leads to functional breakdowns. This phenomenon, referred to as disconnection syndrome, manifests as connectivity breakdowns in affected regions, with these localized changes indirectly influencing the entire brain network. As the disease progresses, patterns consistent with compensatory-type reorganization have been described in the literature, accompanied by structural and functional changes that have been hypothesized to transiently mitigate cognitive decline during early stages. This study examines the structural and functional reorganization of the brain across the clinical spectrum of Alzheimer's disease by analyzing local nodal changes using measures such as degree, strength, clustering coefficient, and betweenness centrality. Our findings show that early-stage nodal patterns are consistent with this hypothesized reorganization, whereas later-stage changes are dominated by progressive structural decline alongside persistent functional reorganization. Because the present study is cross-sectional and group-level, the compensatory interpretation should be regarded as a working hypothesis rather than a confirmed mechanism, and these exploratory patterns require validation in independent and longitudinal cohorts before clinical translation.