NeuroKoop: Neural Koopman Fusion of Structural-Functional Connectomes for Identifying Prenatal Drug Exposure in Adolescents

2025-08-22

AI Summary

Prenatal cannabis exposure (PCE) poses significant challenges for characterizing its impact on adolescent brain development due to the complexity of multimodal neuroimaging data and limitations of conventional modeling approaches. To address this, we propose a neural Koopman-driven latent-space fusion framework—the first to integrate dynamical systems theory into brain network fusion. Our method employs graph neural networks to jointly encode source-based morphometry (SBM) and functional network connectivity (FNC), and leverages the Koopman operator to model nonlinear dynamic coupling between structural and functional connectomes. This enables effective capture of complementary cross-modal features. Evaluated on the Adolescent Brain Cognitive Development (ABCD) Study cohort (N > 2,000), the framework significantly improves classification accuracy for PCE status and identifies neurodevelopmentally meaningful structure–function coupling patterns. These findings establish a novel paradigm for mechanistic investigation and early risk stratification of prenatal neurotoxicant exposure.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Search and Optimization: Mixed Discrete/Continuous Search
• Machine Learning: Multimodal Learning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Understanding how prenatal exposure to psychoactive substances such as cannabis shapes adolescent brain organization remains a critical challenge, complicated by the complexity of multimodal neuroimaging data and the limitations of conventional analytic methods. Existing approaches often fail to fully capture the complementary features embedded within structural and functional connectomes, constraining both biological insight and predictive performance. To address this, we introduced NeuroKoop, a novel graph neural network-based framework that integrates structural and functional brain networks utilizing neural Koopman operator-driven latent space fusion. By leveraging Koopman theory, NeuroKoop unifies node embeddings derived from source-based morphometry (SBM) and functional network connectivity (FNC) based brain graphs, resulting in enhanced representation learning and more robust classification of prenatal drug exposure (PDE) status. Applied to a large adolescent cohort from the ABCD dataset, NeuroKoop outperformed relevant baselines and revealed salient structural-functional connections, advancing our understanding of the neurodevelopmental impact of PDE.

Problem

• Identifying prenatal drug exposure effects on adolescent brains
• Integrating structural and functional brain connectome data
• Improving predictive classification using neural Koopman fusion

Innovation

• Neural Koopman operator-driven latent space fusion
• Graph neural network integrating structural-functional connectomes
• Unifies SBM and FNC embeddings for enhanced classification