Continuous Energy Landscape Model for Analyzing Brain State Transitions

TL;DR

This paper introduces a continuous energy landscape model using Graph Neural Networks to analyze brain state transitions from fMRI data, overcoming limitations of binary models and improving prediction accuracy.

Contribution

The study presents a novel continuous energy landscape framework that preserves full signal information and employs GNNs, enhancing modeling of neural dynamics compared to traditional binary approaches.

Findings

Higher likelihood and more accurate basin recovery in synthetic data

0.27 increase in AUC for cognitive prediction

0.35 improvement in R2 for reaction time prediction

Abstract

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.