arXiv subjects

Sina Khanmohammadi

Publications and source records attributed to Sina Khanmohammadi.

5 recordsLinked to original sources

arXiv2026

Structurally Constrained Brain Network Dynamics Reveal Reduced Functional Flexibility in Cocaine Use Disorder

Cocaine Use Disorder (CUD) is associated with widespread alterations in large-scale functional brain networks, yet the mechanisms contributing to these changes and their relationship to clinical and cognitive outcomes remain poorly understood. To address this gap, we introduce a framework to extract structurally informed dynamic functional connectivity patterns. We then leverage these connectivity patterns to characterize differences in functional brain network organization associated with CUD and to examine their relationship with clinical measures. Specifically, we applied Laplacian spectral smoothing to each participant's functional connectivity matrix using individualized structural priors derived from diffusion imaging. These structurally informed connectivity features were subsequently used to examine cross-network interactions and characterize dynamic community organization across functional brain states. Our findings indicate that individuals with cocaine use disorder exhibit increased integration and recruitment accompanied by reduced flexibility in the functional brain networks, with the most pronounced alterations in visual, attentional, and control systems. In addition, structurally informed functional connectivity features were predictive of weekly cocaine use within the CUD cohort. Overall, these results highlight the value of structurally informed dynamic connectivity measures for characterizing network-level alterations associated with cocaine addiction and for linking these alterations to clinically meaningful measures of cocaine use severity.

q-bio.NC↗

arXiv2026

Presurgical Neural Energy Landscapes Predict Postoperative Working Memory Outcome After Brain Tumor Resection

Surgical resection is the primary treatment option for brain tumor patients, but it carries the risk of postoperative cognitive impairments. This study investigates how tumor-induced alterations in presurgical neural dynamics relate to postoperative working memory outcome assessed by Spatial Span (SSP) test. We analyzed functional magnetic resonance imaging (fMRI) of brain tumor patients before surgery and extracted energy landscapes of high-order brain interactions. We then examined the relation between these energy features and postoperative working memory performance using statistical and machine learning (random forest) models. Patients with lower postoperative SSP Scores (2 to 5) exhibited fewer but more extreme transitions between local energy minima and maxima, whereas patients with higher SSP Scores (6 to 9) showed more frequent but less extreme shifts. Furthermore, the presurgical high-order energy features were able to accurately predict postoperative working memory outcome with a mean accuracy of 90%, F1 score of 87.5%, and an AUC of 0.95. Our study suggests that the brain tumor-induced disruptions in high-order neural dynamics before surgery are predictive of postoperative working memory outcome. Our findings pave the path for personalized surgical planning and targeted interventions to mitigate cognitive risks associated with brain tumor resection.

eess.SP↗

arXiv2026

MSGCN: Multiplex Spatial Graph Convolution Network for Interlayer Link Weight Prediction

Graph Neural Networks (GNNs) have been widely used for various learning tasks, ranging from node classification to link prediction. They have demonstrated excellent performance in multiple domains involving graph-structured data. However, an important but less explored learning task is link weight prediction which is more complex than binary link classification. Link weight prediction becomes even more challenging when considering multilayer networks, where nodes can be connected across multiple layers. To address these challenges, we propose a new method called Multiplex Spatial Graph Convolution Network (MSGCN), which spatially embeds information across multiple layers to predict interlayer link weights. The MSGCN method generalizes spatial graph convolution to multiplex networks and captures the geometric structure of nodes across multiple layers. Extensive experiments using data with known interlayer link information show that the MSGCN model has robust, accurate, and generalizable link weight prediction performance across a wide variety of network structures. We also demonstrate a real-world application of the proposed method using the London transportation network. In this setting, MSGCN accurately predicts passenger loads in the multiplex network, where the interlayer link weights represent the number of passengers traveling between stations that are not directly connected.

cs.LG↗

arXiv2026

Continuous Energy Landscape Model for Analyzing Brain State Transitions

Energy landscape models characterize neural dynamics by assigning energy values to each brain state that reflect their stability or probability of occurrence. The conventional energy landscape models rely on binary brain state representation, where each region is considered either active or inactive based on some signal threshold. However, this binarization leads to significant information loss and an exponential increase in the number of possible brain states, making the calculation of energy values infeasible for large numbers of brain regions. To overcome these limitations, we propose a novel continuous energy landscape framework that employs Graph Neural Networks (GNNs) to learn a continuous precision matrix directly from functional MRI (fMRI) signals, preserving the full range of signal values during energy landscape computation. We validated our approach using both synthetic data and real-world fMRI datasets from brain tumor patients. Our results on synthetic data generated from a switching linear dynamical system (SLDS) and a Kuramoto model show that the continuous energy model achieved higher likelihood and more accurate recovery of basin geometry, state occupancy, and transition dynamics than conventional binary energy landscape models. In addition, results from the fMRI dataset indicate a 0.27 increase in AUC for predicting working memory and executive function, along with a 0.35 improvement in explained variance (R2) for predicting reaction time. These findings highlight the advantages of utilizing the full signal values in energy landscape models for capturing neuronal dynamics, with strong implications for diagnosing and monitoring neurological disorders.

eess.SP↗

arXiv2025

SINDyG: Sparse Identification of Nonlinear Dynamical Systems from Graph-Structured Data, with Applications to Stuart-Landau Oscillator Networks

The combination of machine learning (ML) and sparsity-promoting techniques is enabling direct extraction of governing equations from data, revolutionizing computational modeling in diverse fields of science and engineering. The discovered dynamical models could be used to address challenges in climate science, neuroscience, ecology, finance, epidemiology, and beyond. However, most existing sparse identification methods for discovering dynamical systems treat the whole system as one without considering the interactions between subsystems. As a result, such models are not able to capture small changes in the emergent system behavior. To address this issue, we developed a new method called Sparse Identification of Nonlinear Dynamical Systems from Graph-structured data (SINDyG), which incorporates the network structure into sparse regression to identify model parameters that explain the underlying network dynamics. We tested our proposed method using several case studies of neuronal dynamics, where we modeled the macroscopic oscillation of a population of neurons using the extended Stuart-Landau (SL) equation and utilize the SINDyG method to identify the underlying nonlinear dynamics. Our extensive computational experiments validate the improved accuracy and simplicity of discovered network dynamics when compared to the original SINDy approach. The proposed graph-informed penalty can be easily integrated with other symbolic regression algorithms, enhancing model interpretability and performance by incorporating network structure into the regression process.

eess.SY↗